feat(sdd): follow a task's declared implementation tier at dispatch

The skeleton-first task template carries a Tier field the planner marks
deliberately. Model Selection now follows it instead of re-deciding at
dispatch, the implementer template's model slot reads it at fill time, and
an explicit mechanical ruling overrides the mid-tier contract floor —
the planner has already ruled the deliverable fully specified.

Task templates without a Tier field are unaffected: every route falls
through to the existing Model Selection guidance.

.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
     {
       "name": "superpowers",
       "description": "Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques",
-      "version": "6.2.0",
+      "version": "6.3.0",
       "source": "./",
       "author": {
         "name": "Jesse Vincent",

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "superpowers",
   "description": "Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques",
-  "version": "6.2.0",
+  "version": "6.3.0",
   "author": {
     "name": "Jesse Vincent",
     "email": "jesse@fsck.com"

.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.2.0",
+  "version": "6.3.0",
   "description": "An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.",
   "author": {
     "name": "Jesse Vincent",
@@ -21,7 +21,7 @@
     "workflow"
   ],
   "skills": "./skills/",
-  "hooks": "./hooks/hooks-codex.json",
+  "hooks": {},
   "interface": {
     "displayName": "Superpowers",
     "shortDescription": "Planning, TDD, debugging, and delivery workflows for coding agents",

.cursor-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "superpowers",
   "displayName": "Superpowers",
   "description": "Core skills library: TDD, debugging, collaboration patterns, and proven techniques",
-  "version": "6.2.0",
+  "version": "6.3.0",
   "author": {
     "name": "Jesse Vincent",
     "email": "jesse@fsck.com"

.devin-plugin/plugin.json

@@ -0,0 +1,22 @@
+{
+  "name": "superpowers",
+  "version": "6.3.0",
+  "description": "An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.",
+  "author": {
+    "name": "Jesse Vincent",
+    "email": "jesse@fsck.com"
+  },
+  "homepage": "https://github.com/obra/superpowers",
+  "repository": "https://github.com/obra/superpowers",
+  "license": "MIT",
+  "keywords": [
+    "brainstorming",
+    "subagent-driven-development",
+    "skills",
+    "planning",
+    "tdd",
+    "debugging",
+    "code-review",
+    "workflow"
+  ]
+}

.gitignore

@@ -11,3 +11,9 @@ triage/
 # development (see CLAUDE.md / README.md). It is not part of the published
 # plugin, so the whole directory is ignored here.
 evals/
+
+# Python
+__pycache__/
+*.pyc
+*.pyo
+.pytest_cache/

.hermes-plugin/__init__.py

@@ -0,0 +1,104 @@
+import os
+import re
+from pathlib import Path
+
+BOOTSTRAP_MARKER = "superpowers:using-superpowers bootstrap for hermes"
+
+
+def _skills_dir() -> str:
+    """Locate the stock skills/ tree for either supported install layout.
+
+    - git-clone install (`hermes plugins install obra/superpowers`): the plugin
+      dir is the repo root, so `.hermes-plugin/` and `skills/` are siblings and
+      this module resolves `../skills`.
+    - flattened install (plugin files copied to the plugin dir root): `skills/`
+      sits next to this module.
+
+    Raises loudly when neither matches — a bootstrap that silently skips is how
+    a broken install masquerades as a working one.
+    """
+    here = os.path.dirname(os.path.realpath(__file__))
+    candidates = (
+        os.path.realpath(os.path.join(here, "..", "skills")),
+        os.path.realpath(os.path.join(here, "skills")),
+    )
+    for cand in candidates:
+        if os.path.isfile(os.path.join(cand, "using-superpowers", "SKILL.md")):
+            return cand
+    raise RuntimeError(
+        "superpowers plugin: cannot find the skills/ tree "
+        f"(looked at {candidates}). Reinstall with "
+        "`hermes plugins install obra/superpowers`."
+    )
+
+
+def _strip_frontmatter(content: str) -> str:
+    match = re.match(r"^---\n[\s\S]*?\n---\n([\s\S]*)$", content)
+    return (match.group(1) if match else content).strip()
+
+
+def _build_bootstrap(skills_dir: str) -> str:
+    with open(
+        os.path.join(skills_dir, "using-superpowers", "SKILL.md"),
+        encoding="utf-8",
+    ) as f:
+        body = _strip_frontmatter(f.read())
+
+    tools_path = os.path.join(
+        skills_dir, "using-superpowers", "references", "hermes-tools.md"
+    )
+    with open(tools_path, encoding="utf-8") as f:
+        tool_mapping = f.read().strip()
+
+    return (
+        f"<EXTREMELY_IMPORTANT>\n"
+        f"{BOOTSTRAP_MARKER}\n\n"
+        f"You have superpowers.\n\n"
+        f"The using-superpowers skill content is included below and is already "
+        f"loaded for this Hermes session. Follow it now. "
+        f"Do not try to load using-superpowers again.\n\n"
+        f"{body}\n\n"
+        f"## Loading Superpowers Skills on Hermes\n\n"
+        f"Superpowers skills are registered with Hermes' native skill loader: "
+        f'invoke one with `skill_view("superpowers:skill-name")` '
+        f'(for example `skill_view("superpowers:brainstorming")`). '
+        f"If a namespaced lookup returns 'not found', read the skill file "
+        f"directly instead:\n"
+        f'`read_file("{skills_dir}/skill-name/SKILL.md")`\n\n'
+        f"The superpowers skills directory is: `{skills_dir}`\n\n"
+        f"{tool_mapping}\n"
+        f"</EXTREMELY_IMPORTANT>"
+    )
+
+
+def register(ctx):
+    skills_dir = _skills_dir()
+    bootstrap = _build_bootstrap(skills_dir)
+
+    # Register every stock skill with Hermes' native loader so skill_view can
+    # load them on demand. Standard markdown; no conversion (plugin guide).
+    # register_skill requires a pathlib.Path — a str raises AttributeError and
+    # hermes silently disables the whole plugin (verified 2026-07-23).
+    for name in sorted(os.listdir(skills_dir)):
+        skill_md = os.path.join(skills_dir, name, "SKILL.md")
+        if os.path.isfile(skill_md):
+            ctx.register_skill(name, Path(skill_md))
+
+    # pre_llm_call returning {"context": ...} is the documented injection path
+    # (on_session_start return values are ignored, and ctx.inject_message
+    # refuses from that hook — verified empirically 2026-07-23). The context is
+    # appended to the first turn's user message.
+    def pre_llm_call(
+        session_id=None,
+        user_message=None,
+        conversation_history=None,
+        is_first_turn=None,
+        model=None,
+        platform=None,
+        **kwargs,
+    ):
+        if is_first_turn:
+            return {"context": bootstrap}
+        return None
+
+    ctx.register_hook("pre_llm_call", pre_llm_call)

.hermes-plugin/plugin.yaml

@@ -0,0 +1,6 @@
+name: superpowers
+version: 6.3.0
+description: Superpowers skills and workflow bootstrap for Hermes Agent
+author: obra
+provides_hooks:
+  - pre_llm_call

.kimi-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.2.0",
+  "version": "6.3.0",
   "description": "An agentic skills framework and software development methodology.",
   "author": {
     "name": "Jesse Vincent",

.version-bump.json

@@ -1,9 +1,11 @@
 {
   "files": [
     { "path": "package.json", "field": "version" },
+    { "path": ".hermes-plugin/plugin.yaml", "field": "version" },
     { "path": ".claude-plugin/plugin.json", "field": "version" },
     { "path": ".cursor-plugin/plugin.json", "field": "version" },
     { "path": ".codex-plugin/plugin.json", "field": "version" },
+    { "path": ".devin-plugin/plugin.json", "field": "version" },
     { "path": ".kimi-plugin/plugin.json", "field": "version" },
     { "path": ".claude-plugin/marketplace.json", "field": "plugins.0.version" },
     { "path": "gemini-extension.json", "field": "version" }

CODE_OF_CONDUCT.md

@@ -1,128 +1,130 @@
-# Contributor Covenant Code of Conduct
+# Prime Radiant Community Code of Conduct
 
 ## Our Pledge
 
-We as members, contributors, and leaders pledge to make participation in our
-community a harassment-free experience for everyone, regardless of age, body
-size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
-nationality, personal appearance, race, religion, or sexual identity
-and orientation.
+We pledge to make our community welcoming, safe, and equitable for all.
 
-We pledge to act and interact in ways that contribute to an open, welcoming,
-diverse, inclusive, and healthy community.
+We are committed to fostering an environment that respects and promotes the dignity, rights, and contributions of all individuals, regardless of characteristics including race, ethnicity, caste, color, age, physical characteristics, neurodiversity, disability, sex or gender, gender identity or expression, sexual orientation, language, philosophy or religion, national or social origin, socio-economic position, level of education, or other status. The same privileges of participation are extended to everyone who participates in good faith and in accordance with this Covenant.
 
-## Our Standards
+The guidelines within and enforcement of the Prime Radiant Community Code of Conduct apply equally to everyone participating in the Prime Radiant community, including members of the Prime Radiant team.
 
-Examples of behavior that contributes to a positive environment for our
-community include:
+## Encouraged Behaviors
 
-* Demonstrating empathy and kindness toward other people
-* Being respectful of differing opinions, viewpoints, and experiences
-* Giving and gracefully accepting constructive feedback
-* Accepting responsibility and apologizing to those affected by our mistakes,
-  and learning from the experience
-* Focusing on what is best not just for us as individuals, but for the
-  overall community
+While acknowledging differences in social norms, we all strive to meet our community's expectations for positive behavior. We also understand that our words and actions may be interpreted differently than we intend based on culture, background, or native language.
 
-Examples of unacceptable behavior include:
+With these considerations in mind, we agree to behave mindfully toward each other and act in ways that center our shared values, including:
 
-* The use of sexualized language or imagery, and sexual attention or
-  advances of any kind
-* Trolling, insulting or derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or email
-  address, without their explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-  professional setting
+1. Respecting the **purpose of our community**, our activities, and our ways of gathering.
+2. Engaging **kindly and honestly** with others.
+3. Respecting **different viewpoints** and experiences.
+4. **Taking responsibility** for our actions and contributions.
+5. Gracefully giving and accepting **constructive feedback**.
+6. Committing to **repairing harm** when it occurs.
+7. Behaving in other ways that promote and sustain the **well-being of our community**.
 
-## Enforcement Responsibilities
+## Restricted Behaviors
 
-Community leaders are responsible for clarifying and enforcing our standards of
-acceptable behavior and will take appropriate and fair corrective action in
-response to any behavior that they deem inappropriate, threatening, offensive,
-or harmful.
+We agree to restrict the following behaviors in our community. Instances, threats, and promotion of these behaviors are violations of this Code of Conduct.
 
-Community leaders have the right and responsibility to remove, edit, or reject
-comments, commits, code, wiki edits, issues, and other contributions that are
-not aligned to this Code of Conduct, and will communicate reasons for moderation
-decisions when appropriate.
+1. **Harassment.** Violating explicitly expressed boundaries or engaging in unnecessary personal attention after any clear request to stop.
+2. **Character attacks.** Making insulting, demeaning, or pejorative comments directed at a community member or group of people.
+3. **Inciting conflict.** Deliberately engaging in discussions meant to cause arguments or a hostile environment.
+4. **Stereotyping or discrimination.** Characterizing anyone’s personality or behavior on the basis of immutable identities or traits.
+5. **Sexualization.** Behaving in a way that would generally be considered inappropriately intimate in the context or purpose of the community.
+6. **Violating confidentiality.** Sharing or acting on someone's personal or private information without their permission.
+7. **Endangerment.** Causing, encouraging, or threatening violence or other harm toward any person or group.
+8. Behaving in other ways that **threaten the well-being** of our community.
+
+### Other Restrictions
+
+1. **Divisive topics.** Discussing inflammatory topics that are unrelated to the community as a whole.
+2. **Offensive content.** Any text or image that is offensive or violates any of the other restricted behaviors, including as part of a username, profile, status, avatar, or other publicly displayed identifier.
+3. **Misleading identity.** Impersonating someone else for any reason, misrepresenting yourself as associated with Prime Radiant or any company, or pretending to be someone else to evade enforcement actions.
+4. **Failing to credit sources.** Not properly crediting the sources of content you contribute, or representing work created by someone else as your own.
+5. **Advertising and promotional materials.** Sharing marketing or other commercial content, invite links, or irrelevant self-promotion, as well as buying, trading, or asking for donations.
+6. **Spam posts.** Spamming, including, but not limited to, posting a flood of messages in a short period of time, irrelevant content, or excessive links.
+7. **Unsolicited mentions and direct messages.** Engaging in harassment by excessively mentioning someone by username or replying, or direct messaging someone without explicit invitation.
+8. **Irresponsible communication.** Failing to responsibly present content which includes, links, or describes any other restricted behaviors.
+9. Other conduct that could reasonably be considered **unprofessional** or **inappropriate**.
+
+## Reporting an Issue
+
+Tensions can occur between community members even when they are trying their best to collaborate. Not every conflict represents a code of conduct violation, and this Code of Conduct reinforces encouraged behaviors and norms that can help avoid conflicts and minimize harm. You are welcome to report concerns, even if they seem minor, as they can be helpful in identifying patterns of behavior that may not be concerning in isolation, but when viewed collectively may be more significant.
+
+When an incident does occur, it is important to report it promptly. To report a possible violation anywhere in the community, email [conduct@primeradiant.com](mailto:conduct@primeradiant.com). On the Prime Radiant Discord server, you can mention `@moderators` in a public channel, or report via a support ticket, created through the `#support-ticket` channel. In the event that you need to report a member of the Prime Radiant team, you can contact Kattni at [kattni@primeradiant.com](mailto:kattni@primeradiant.com) or Drew at [drew@primeradiant.com](mailto:drew@primeradiant.com).
+
+Community Moderators take reports of violations seriously and will make every effort to respond in a timely manner. They will investigate all reports of code of conduct violations, reviewing messages, logs, and recordings, or interviewing witnesses and other participants. Community Moderators will keep investigation and enforcement actions as transparent as possible while prioritizing safety and confidentiality. In order to honor these values, enforcement actions are carried out in private with the involved parties, but communicating to the whole community may be part of a mutually agreed upon resolution. If moderators determine that a public statement needs to be made, the identities of all victims and reporters will remain confidential unless those individuals instruct otherwise.
+
+In your report, please include:
+
+- **Your contact info** so the team can get in touch with you if they need to follow up.
+- **Names (real, nicknames, or pseudonyms) of any individuals involved.** If there were other witnesses besides you, please try to include them as well.
+- **When and where the incident occurred.** Please be as specific as possible.
+- **Your account of what occurred.** If there is a publicly available record (e.g. a Discord or GitHub message) please include a link.
+- **Any extra context** you believe existed for the incident.
+- **If you believe this incident is ongoing.**
+- **If you believe any member of the team has a conflict of interest** in adjudicating the incident.
+- **What, if any, corrective response** you believe would be appropriate.
+- **Any other information** you believe the team should have.
+
+Moderators are obligated to maintain confidentiality with regard to the reporter and details of an incident.
+
+## Report Followup
+
+You will receive a response acknowledging receipt of your report within 24 business hours.
+
+If a member of the team is one of the named parties, they will not be included in any discussions, and will not be provided with any confidential details from the reporter.
+
+If anyone on the moderation team believes they have a conflict of interest in adjudicating on a reported issue, they will inform the other team members, and recuse themselves from any discussion about the issue. Following this declaration, they will not be provided with any confidential details from the reporter.
+
+The team will immediately review the incident and determine:
+
+- What happened.
+- Whether this event constitutes a code of conduct violation.
+- Who the reported person is.
+- Whether this is an ongoing situation, or if there is a threat to anyone's physical safety. 
+
+If this is determined to be an ongoing incident or a threat to physical safety, the team's immediate priority will be to protect everyone involved. This means they may delay an official response until they believe that the situation has concluded and that everyone is physically safe.
+
+The moderation team will respond within one week to the person who filed the report with either a resolution or an explanation of why the situation is not yet resolved.
+
+Once the team has determined their final action, they'll contact the reporter to let them know what action (if any) they'll be taking. They'll take into account feedback from the reporter on the appropriateness of the response, but do not guarantee they'll act on it.
+
+Finally, to maintain transparency in the reporting and enforcement process, whenever possible, a public transparency report of the incident will be made. A public report may not be made if the specifics of the incident do not allow the team to preserve anonymity, or if there is potential for ongoing harm.
+
+## Addressing and Repairing Harm
+
+If an investigation by the Community Moderators finds that this Code of Conduct has been violated, the following enforcement ladder may be used to determine how best to repair harm, based on the incident's impact on the individuals involved and the community as a whole. Depending on the severity of a violation, lower rungs on the ladder may be skipped.
+
+1) Warning
+   1) Event: A violation involving a single incident or series of incidents.
+   2) Consequence: A private, written warning from the Community Moderators.
+   3) Repair: Examples of repair include a private written apology, acknowledgement of responsibility, and seeking clarification on expectations.
+2) Temporarily Limited Activities
+   1) Event: A repeated incidence of a violation that previously resulted in a warning, or the first incidence of a more serious violation.
+   2) Consequence: A private, written warning with a time-limited cooldown period designed to underscore the seriousness of the situation and give the community members involved time to process the incident. The cooldown period may be limited to particular communication channels or interactions with particular community members.
+   3) Repair: Examples of repair may include making an apology, using the cooldown period to reflect on actions and impact, and being thoughtful about re-entering community spaces after the period is over.
+3) Temporary Suspension
+   1) Event: A pattern of repeated violation which the Community Moderators have tried to address with warnings, or a single serious violation.
+   2) Consequence: A private written warning with conditions for return from suspension. In general, temporary suspensions give the person being suspended time to reflect upon their behavior and possible corrective actions.
+   3) Repair: Examples of repair include respecting the spirit of the suspension, meeting the specified conditions for return, and being thoughtful about how to reintegrate with the community when the suspension is lifted.
+4) Permanent Ban
+   1) Event: A pattern of repeated code of conduct violations that other steps on the ladder have failed to resolve, or a violation so serious that the Community Moderators determine there is no way to keep the community safe with this person as a member.
+   2) Consequence: Access to all community spaces, tools, and communication channels is removed. In general, permanent bans should be rarely used, should have strong reasoning behind them, and should only be resorted to if working through other remedies has failed to change the behavior.
+   3) Repair: There is no possible repair in cases of this severity.
+
+This enforcement ladder is intended as a guideline. It does not limit the ability of Community Managers to use their discretion and judgment, in keeping with the best interests of our community.
 
 ## Scope
 
-This Code of Conduct applies within all community spaces, and also applies when
-an individual is officially representing the community in public spaces.
-Examples of representing our community include using an official e-mail address,
-posting via an official social media account, or acting as an appointed
-representative at an online or offline event.
+This Code of Conduct applies within all community spaces, including GitHub and the Prime Radiant Discord server. It also applies when an individual is officially representing the community in public or other spaces. Examples of representing the community include using an official email address, posting via an official social media account, or acting as an appointed representative at an online or offline event.
 
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported to the community leaders responsible for enforcement at
-jesse@primeradiant.com.
-All complaints will be reviewed and investigated promptly and fairly.
-
-All community leaders are obligated to respect the privacy and security of the
-reporter of any incident.
-
-## Enforcement Guidelines
-
-Community leaders will follow these Community Impact Guidelines in determining
-the consequences for any action they deem in violation of this Code of Conduct:
-
-### 1. Correction
-
-**Community Impact**: Use of inappropriate language or other behavior deemed
-unprofessional or unwelcome in the community.
-
-**Consequence**: A private, written warning from community leaders, providing
-clarity around the nature of the violation and an explanation of why the
-behavior was inappropriate. A public apology may be requested.
-
-### 2. Warning
-
-**Community Impact**: A violation through a single incident or series
-of actions.
-
-**Consequence**: A warning with consequences for continued behavior. No
-interaction with the people involved, including unsolicited interaction with
-those enforcing the Code of Conduct, for a specified period of time. This
-includes avoiding interactions in community spaces as well as external channels
-like social media. Violating these terms may lead to a temporary or
-permanent ban.
-
-### 3. Temporary Ban
-
-**Community Impact**: A serious violation of community standards, including
-sustained inappropriate behavior.
-
-**Consequence**: A temporary ban from any sort of interaction or public
-communication with the community for a specified period of time. No public or
-private interaction with the people involved, including unsolicited interaction
-with those enforcing the Code of Conduct, is allowed during this period.
-Violating these terms may lead to a permanent ban.
-
-### 4. Permanent Ban
-
-**Community Impact**: Demonstrating a pattern of violation of community
-standards, including sustained inappropriate behavior,  harassment of an
-individual, or aggression toward or disparagement of classes of individuals.
-
-**Consequence**: A permanent ban from any sort of public interaction within
-the community.
+Behavior outside of official Prime Radiant spaces may also be considered as supporting evidence for a report if that behavior establishes a pattern, or represents a potential risk to the Prime Radiant community.
 
 ## Attribution
 
-This Code of Conduct is adapted from the [Contributor Covenant][homepage],
-version 2.0, available at
-https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+This Code of Conduct is adapted from the Contributor Covenant, version 3.0, permanently available at [https://www.contributor-covenant.org/version/3/0/](https://www.contributor-covenant.org/version/3/0/).
 
-Community Impact Guidelines were inspired by [Mozilla's code of conduct
-enforcement ladder](https://github.com/mozilla/diversity).
+Contributor Covenant is stewarded by the Organization for Ethical Source and licensed under CC BY-SA 4.0. To view a copy of this license, visit [https://creativecommons.org/licenses/by-sa/4.0/](https://creativecommons.org/licenses/by-sa/4.0/)
 
-[homepage]: https://www.contributor-covenant.org
-
-For answers to common questions about this code of conduct, see the FAQ at
-https://www.contributor-covenant.org/faq. Translations are available at
-https://www.contributor-covenant.org/translations.
+For answers to common questions about Contributor Covenant, see the FAQ at [https://www.contributor-covenant.org/faq](https://www.contributor-covenant.org/faq). Translations are provided at [https://www.contributor-covenant.org/translations](https://www.contributor-covenant.org/translations). Additional enforcement and community guideline resources can be found at [https://www.contributor-covenant.org/resources](https://www.contributor-covenant.org/resources). The enforcement ladder was inspired by the work of [Mozilla’s code of conduct team](https://github.com/mozilla/inclusion).

README.md

@@ -2,10 +2,33 @@
 
 Superpowers is a complete software development methodology for your coding agents, built on top of a set of composable skills and some initial instructions that make sure your agent uses them.
 
+## Table of Contents
 
-## Quickstart
-
-Give your agent Superpowers: [Claude Code](#claude-code), [Antigravity](#antigravity), [Codex App](#codex-app), [Codex CLI](#codex-cli), [Cursor](#cursor), [Factory Droid](#factory-droid), [Gemini CLI](#gemini-cli), [GitHub Copilot CLI](#github-copilot-cli), [Kimi Code](#kimi-code), [OpenCode](#opencode), [Pi](#pi).
+- [How it works](#how-it-works)
+- [Commercial Services](#commercial-services)
+- [Getting Started](#installation)
+  - [Claude Code](#claude-code)
+  - [Antigravity](#antigravity)
+  - [Codex App](#codex-app)
+  - [Codex CLI](#codex-cli)
+  - [Cursor](#cursor)
+  - [Devin CLI](#devin-cli)
+  - [Factory Droid](#factory-droid)
+  - [Gemini CLI](#gemini-cli)
+  - [GitHub Copilot CLI](#github-copilot-cli)
+  - [Grok Build CLI](#grok-build-cli)
+  - [Kimi Code](#kimi-code)
+  - [OpenCode](#opencode)
+  - [Pi](#pi)
+  - [Hermes Agent](#hermes-agent)
+- [The Basic Workflow](#the-basic-workflow)
+- [Community](#community)
+- [What's Inside](#whats-inside)
+- [Philosophy](#philosophy)
+- [Contributing](#contributing)
+- [Updating](#updating)
+- [License](#license)
+- [Visual companion telemetry](#visual-companion-telemetry)
 
 ## How it works
 
@@ -92,22 +115,6 @@ Superpowers is available via the [official Codex plugin marketplace](https://git
 
 - Select `Install Plugin`.
 
-#### Codex: compaction re-injection hook
-
-Codex compacts long sessions, replacing the transcript with a summary that
-drops Superpowers' skill instructions mid-run — long autonomous workflows
-(like subagent-driven-development) then drift back to harness defaults.
-Claude Code re-injects the bootstrap after every compaction; the plugin ships
-a SessionStart hook (`hooks/hooks-codex.json`) that restores the same
-behavior on Codex (0.145+). It fires only on post-compaction re-starts
-(`source: "compact"`) and is silent at normal session start.
-
-The hook installs with the plugin — no configuration needed. Codex asks you
-to review and trust it once, the first time it loads after install or update.
-Headless automation (CI, eval harnesses) must pass
-`--dangerously-bypass-hook-trust` instead, because untrusted hooks are
-skipped silently.
-
 ### Cursor
 
 - In Cursor Agent chat, install from marketplace:
@@ -118,6 +125,20 @@ skipped silently.
 
 - Or search for "superpowers" in the plugin marketplace.
 
+### Devin CLI
+
+- Install the plugin from this repository:
+
+  ```bash
+  devin plugins install obra/superpowers
+  ```
+
+- Update to the latest version with:
+
+  ```bash
+  devin plugins update superpowers
+  ```
+
 ### Factory Droid
 
 - Register the marketplace:
@@ -160,6 +181,22 @@ skipped silently.
   copilot plugin install superpowers@superpowers-marketplace
   ```
 
+### Grok Build CLI
+
+Superpowers is available via the [official Grok plugin marketplace](https://github.com/xai-org/plugin-marketplace).
+
+- Install the plugin from xAI's official marketplace:
+
+  ```bash
+  grok plugin install superpowers@xai-official --trust
+  ```
+
+- Or open the marketplace in the TUI, search for Superpowers, and install it:
+
+  ```text
+  /marketplace
+  ```
+
 ### Kimi Code
 
 Superpowers is available in Kimi Code's plugin marketplace.
@@ -209,6 +246,18 @@ pi -e /path/to/superpowers
 
 The Pi package loads the Superpowers skills and a small extension that injects the `using-superpowers` bootstrap at session startup and again after compaction. Pi has native skills, so no compatibility `Skill` tool is required. Subagent and task-list tools remain optional Pi companion packages.
 
+### Hermes Agent
+
+Install Superpowers as a Hermes plugin from this repository:
+
+```bash
+hermes plugins install obra/superpowers --enable
+```
+
+Restart any active Hermes sessions after installing. Note: Hermes has no
+post-compaction hook, so a very long session that compacts over its first
+turn loses the bootstrap — start a fresh session if skills stop triggering.
+
 ## The Basic Workflow
 
 1. **brainstorming** - Activates before writing code. Refines rough ideas through questions, explores alternatives, presents design in sections for validation. Saves design document.
@@ -227,6 +276,14 @@ The Pi package loads the Superpowers skills and a small extension that injects t
 
 **The agent checks for relevant skills before any task.** Mandatory workflows, not suggestions.
 
+## Community
+
+Superpowers is built by [Jesse Vincent](https://blog.fsck.com) and the rest of the folks at [Prime Radiant](https://primeradiant.com).
+
+- **Discord**: [Join us](https://discord.gg/35wsABTejz) for community support, questions, and sharing what you're building with Superpowers
+- **Issues**: https://github.com/obra/superpowers/issues
+- **Release announcements**: [Sign up](https://primeradiant.com/superpowers/) to get notified about new versions
+
 ## What's Inside
 
 ### Skills Library
@@ -287,11 +344,3 @@ MIT License - see LICENSE file for details
 ## Visual companion telemetry
 
 Because skills and plugins don't provide any feedback to creators, we have no idea how many of you are using Superpowers. By default, the Prime Radiant logo on brainstorming's optional visual companion feature is loaded from our website. It includes the version of Superpowers in use. It does not include any details about your project, prompt, or coding agent. We don't see your clicks or anything about what you're building. This helps us have a rough idea of how many folks are using Superpowers and which version of Superpowers they're using. It's 100% optional. To disable this, set the environment variable `SUPERPOWERS_DISABLE_TELEMETRY` to any true value. Superpowers also honors Claude Code's `DISABLE_TELEMETRY` and `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` opt-outs.
-
-## Community
-
-Superpowers is built by [Jesse Vincent](https://blog.fsck.com) and the rest of the folks at [Prime Radiant](https://primeradiant.com).
-
-- **Discord**: [Join us](https://discord.gg/35wsABTejz) for community support, questions, and sharing what you're building with Superpowers
-- **Issues**: https://github.com/obra/superpowers/issues
-- **Release announcements**: [Sign up](https://primeradiant.com/superpowers/) to get notified about new versions

RELEASE-NOTES.md

@@ -1,5 +1,44 @@
 # Superpowers Release Notes
 
+## v6.3.0 (2026-08-12)
+
+### Harness Support
+
+- **Devin CLI**: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start. (#1995)
+- **Hermes Agent**: install from a git clone; skills register with Hermes' native loader and the bootstrap loads on the first turn. (#1922, #2025)
+- **Grok Build CLI** added to the install docs. (#1919)
+
+### Brainstorming
+
+- **Ceremony now scales to the task.** Requests are classified as spike, bounded, or architectural; small tasks skip the two-document ritual. Every path still stops for your approval before implementation. (#2063)
+
+### Subagent-Driven Development
+
+- **Controllers no longer stall on plan conflicts.** Non-catastrophic conflicts and ambiguities get a recorded ruling and work continues; only destructive or irreversible actions still stop for a human. One donated session had sat blocked for almost nine hours on a question the controller could have decided. (#2077)
+- **The pre-dispatch conflict scan records its checks in the ledger** instead of just asserting the plan is clean. (#2080)
+- **Small same-shape tasks batch into one dispatch**, cutting subagent cost sharply on micro-task plans; batch reviews verify every file in the brief made it into the diff. (#2078)
+- **Implementers and reviewers may not spawn their own subagents**, which was producing duplicate reviews. (#2059)
+- **Plans carry a `Spec:` pointer** and SDD reads the spec at setup, so plan conflicts get resolved against the design instead of guessed at. (#2086)
+- Reviewers re-read evidence they find illegible instead of re-running the test suite (#2089), and circuit-breaker rulings now show up in the Finish report.
+
+### Codex
+
+- Subagent waits are event-driven instead of poll-heavy, spawns pin model and reasoning effort explicitly, and the multi-agent reference is corrected against Codex source. (#2060, #2061, #2062)
+
+### Finishing a Development Branch
+
+- **Worktree removal no longer destroys untracked files.** When `git worktree remove` refuses because the tree holds uncommitted work, the skill stops, names the files, and asks — instead of reaching for `--force`. (#2016, #1223, #2024)
+
+### Fixes
+
+- `render-graphs.js` in writing-skills works on Windows.
+- Corrected Copilot CLI backgrounding guidance for Windows. (#1929, #2006)
+- `bump-version.sh` covers the Hermes manifest.
+
+### Documentation
+
+- README: added a table of contents and reorganized Getting Started.
+
 ## v6.2.0 (2026-07-23)
 
 ### Subagent-Driven Development

docs/porting-to-a-new-harness.md

@@ -237,12 +237,10 @@ nesting differ per harness**.
 - Manifests: `.cursor-plugin/plugin.json` is the Shape A manifest example that
   points the harness at `./skills/` and the right `hooks-*.json`. Claude Code's
   `.claude-plugin/plugin.json` sets neither field — it auto-discovers `skills/`
-  and `hooks/hooks.json` by convention. Codex's `.codex-plugin/plugin.json`
-  points `hooks` at `./hooks/hooks-codex.json` — a compaction-only hook, not a
-  bootstrap injector: Codex surfaces skills natively at session start, so its
-  hook fires only on post-compaction re-starts. The explicit pointer also
-  suppresses Codex's `hooks/hooks.json` auto-discovery fallback, which would
-  otherwise run the Claude Code hook.
+  and `hooks/hooks.json` by convention. Do **not** copy Codex's
+  `.codex-plugin/plugin.json` for Shape A: it declares an empty `hooks` object
+  specifically to suppress Codex's `hooks/hooks.json` auto-discovery, because
+  Codex surfaces skills natively and runs no session-start hook.
 
 > **A hook *system* is not a session-start *event*.** A harness can have a
 > `hooks.json` mechanism — and even contain the literal string `SessionStart` in
@@ -787,7 +785,7 @@ Use this as the live index; when in doubt, read the files, not this table.
 | Harness | Entry point | Bootstrap mechanism | Tool mapping | Tests | Distribution |
 |---|---|---|---|---|---|
 | Claude Code | `.claude-plugin/plugin.json` + `hooks/hooks.json` | shell hook → `hooks/session-start` (`hookSpecificOutput.additionalContext`) | native `Skill` tool; no adapter file needed | `tests/hooks/` | marketplace |
-| Codex | `.codex-plugin/plugin.json` + `hooks/hooks-codex.json` | native skill discovery at startup; shell hook → `hooks/session-start-codex` re-injects after compaction only | `references/codex-tools.md` | `tests/codex/`, `tests/codex-plugin-sync/` | fork sync (`scripts/sync-to-codex-plugin.sh`) |
+| Codex | `.codex-plugin/plugin.json` (declares empty `hooks`) | native skill discovery (no session-start hook) | `references/codex-tools.md` | `tests/codex/`, `tests/codex-plugin-sync/` | fork sync (`scripts/sync-to-codex-plugin.sh`) |
 | Cursor | `.cursor-plugin/plugin.json` + `hooks/hooks-cursor.json` | shell hook → `hooks/session-start` (`additional_context`) | none needed (Claude Code–compatible tool surface) | `tests/hooks/` | hand-authored |
 | Copilot CLI | (shares Claude Code hook path; `COPILOT_CLI` env) | shell hook → `hooks/session-start` (`additionalContext`) | none needed (Claude Code–compatible tool surface) | `tests/hooks/` | — |
 | Gemini CLI | `gemini-extension.json` + `GEMINI.md` | instructions file `@`-includes bootstrap + mapping | `references/gemini-tools.md` | — | `gemini extensions install` |

docs/superpowers/plans/2026-08-06-hermes-version-bump-wiring.md

@@ -0,0 +1,304 @@
+# Hermes Version-Bump Wiring Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Keep the Hermes YAML manifest version synchronized with every other declared release manifest.
+
+**Spec:** `docs/superpowers/specs/2026-08-05-hermes-version-bump-wiring-design.md`
+
+**Architecture:** Extend the existing release script with a small extension-based dispatcher: JSON continues through `jq`, while `.yaml` uses Mike Farah `yq` v4. Before the mutating bump loop, read every present manifest through that dispatcher so deterministic format or field failures occur before the first write.
+
+**Tech Stack:** Bash 3.2-compatible shell, `jq`, Mike Farah `yq` v4, existing shell-lint tooling.
+
+## Global Constraints
+
+- Support only `.json` and `.yaml`; `.yml` and other extensions remain unsupported.
+- YAML fields are present top-level strings; nested YAML fields are out of scope.
+- Pass the YAML field and new value through environment data, never interpolate either into a `yq` expression.
+- Keep `yq` confined to maintainer release tooling; do not add a plugin runtime dependency.
+- Preserve the existing missing-file behavior: `--check` reports missing files and a bump skips them.
+- Preflight only the mutating bump path; do not add rollback or transactional writes.
+- Do not change audit status behavior, version validation, or the existing JSON field-expression implementation.
+
+---
+
+## File Map
+
+- Create: `tests/version-bump/test-bump-version.sh`
+  - Exercise the real script in temporary JSON/YAML fixtures and check the real registry.
+- Modify: `scripts/bump-version.sh`
+  - Add YAML read/write helpers, format dispatch, and bump-only read preflight.
+- Modify: `.version-bump.json`
+  - Register `.hermes-plugin/plugin.yaml` at top-level field `version`.
+
+### Task 1: Wire Hermes Into The Existing Version-Bump Script
+
+**Files:**
+- Create: `tests/version-bump/test-bump-version.sh`
+- Modify: `scripts/bump-version.sh`
+- Modify: `.version-bump.json`
+
+**Interfaces:**
+- Consumes: `.version-bump.json` records shaped as `{ "path": string, "field": string }`.
+- Produces: `read_manifest_field FILE FIELD`, `write_manifest_field FILE FIELD VALUE`, and `preflight_manifests` Bash helpers.
+
+- [ ] **Step 1: Fetch the current development base**
+
+Run:
+
+```bash
+git fetch origin dev
+```
+
+Expected: command exits 0 and refreshes `origin/dev`.
+
+- [ ] **Step 2: Rebase the task branch**
+
+Run:
+
+```bash
+git rebase origin/dev
+```
+
+Expected: command exits 0, and `git status --short --branch` no longer reports the branch behind `origin/dev`.
+
+- [ ] **Step 3: Add the initial failing behavioral test**
+
+Create `tests/version-bump/test-bump-version.sh` with the happy-path fixture and real registry assertion:
+
+```bash
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+SCRIPT_SOURCE="$REPO_ROOT/scripts/bump-version.sh"
+TEST_ROOT="$(mktemp -d)"
+
+cleanup() {
+  rm -rf "$TEST_ROOT"
+}
+trap cleanup EXIT
+
+fail() {
+  echo "FAIL: $*" >&2
+  exit 1
+}
+
+make_fixture() {
+  local repo="$1"
+  local yaml_body="$2"
+
+  mkdir -p "$repo/scripts" "$repo/.hermes-plugin"
+  cp "$SCRIPT_SOURCE" "$repo/scripts/bump-version.sh"
+  cat >"$repo/.version-bump.json" <<'JSON'
+{
+  "files": [
+    { "path": "package.json", "field": "version" },
+    { "path": ".hermes-plugin/plugin.yaml", "field": "version" }
+  ],
+  "audit": { "exclude": [] }
+}
+JSON
+  cat >"$repo/package.json" <<'JSON'
+{
+  "name": "fixture",
+  "version": "1.2.3"
+}
+JSON
+  printf '%s\n' "$yaml_body" >"$repo/.hermes-plugin/plugin.yaml"
+}
+
+happy_repo="$TEST_ROOT/happy"
+make_fixture "$happy_repo" $'name: superpowers\nversion: 1.2.3'
+
+/bin/bash "$happy_repo/scripts/bump-version.sh" --check >"$TEST_ROOT/check.out"
+/bin/bash "$happy_repo/scripts/bump-version.sh" --audit >"$TEST_ROOT/audit.out"
+/bin/bash "$happy_repo/scripts/bump-version.sh" 2.3.4 >"$TEST_ROOT/bump.out"
+
+[[ "$(jq -r '.version' "$happy_repo/package.json")" == "2.3.4" ]] \
+  || fail "JSON manifest was not bumped"
+[[ "$(yq -r '.version' "$happy_repo/.hermes-plugin/plugin.yaml")" == "2.3.4" ]] \
+  || fail "YAML manifest was not bumped"
+
+jq -e '
+  any(.files[];
+    .path == ".hermes-plugin/plugin.yaml" and .field == "version")
+' "$REPO_ROOT/.version-bump.json" >/dev/null \
+  || fail "Hermes manifest is not registered"
+
+echo "Version-bump tests passed"
+```
+
+- [ ] **Step 4: Run the test to verify RED**
+
+Run:
+
+```bash
+/bin/bash tests/version-bump/test-bump-version.sh
+```
+
+Expected: FAIL before `Version-bump tests passed`; the current JSON-only reader cannot process the YAML fixture.
+
+- [ ] **Step 5: Add minimal YAML dispatch and register Hermes**
+
+In `scripts/bump-version.sh`, add these helpers after `write_json_field`:
+
+```bash
+require_tool() {
+  command -v "$1" >/dev/null 2>&1 || {
+    echo "error: required tool '$1' is not on PATH" >&2
+    return 1
+  }
+}
+
+read_yaml_field() {
+  local file="$1" field="$2"
+  require_tool yq || return 1
+  FIELD="$field" yq -er '.[strenv(FIELD)] | select(tag == "!!str")' "$file"
+}
+
+write_yaml_field() {
+  local file="$1" field="$2" value="$3"
+  FIELD="$field" VALUE="$value" \
+    yq -i '.[strenv(FIELD)] = strenv(VALUE)' "$file"
+}
+
+read_manifest_field() {
+  local file="$1"
+
+  case "$file" in
+    *.json) read_json_field "$@" ;;
+    *.yaml) read_yaml_field "$@" ;;
+    *)
+      echo "error: unsupported manifest format: $file" >&2
+      return 1
+      ;;
+  esac
+}
+
+write_manifest_field() {
+  local file="$1"
+
+  case "$file" in
+    *.json) write_json_field "$@" ;;
+    *.yaml) write_yaml_field "$@" ;;
+    *)
+      echo "error: unsupported manifest format: $file" >&2
+      return 1
+      ;;
+  esac
+}
+```
+
+Replace the three command-path calls to `read_json_field` with `read_manifest_field`, and replace the bump-path call to `write_json_field` with `write_manifest_field`.
+
+Add this exact entry to `.version-bump.json` immediately after `package.json`:
+
+```json
+{ "path": ".hermes-plugin/plugin.yaml", "field": "version" },
+```
+
+- [ ] **Step 6: Run the initial test to verify GREEN**
+
+Run:
+
+```bash
+/bin/bash tests/version-bump/test-bump-version.sh
+```
+
+Expected: PASS with `Version-bump tests passed`.
+
+- [ ] **Step 7: Add the failing no-partial-write regression**
+
+Insert this block before the final success message in `tests/version-bump/test-bump-version.sh`:
+
+```bash
+invalid_repo="$TEST_ROOT/invalid"
+make_fixture "$invalid_repo" $'name: superpowers\nversion: 123'
+cp "$invalid_repo/package.json" "$TEST_ROOT/package.before"
+cp "$invalid_repo/.hermes-plugin/plugin.yaml" "$TEST_ROOT/plugin.before"
+
+if /bin/bash "$invalid_repo/scripts/bump-version.sh" 2.3.4 \
+  >"$TEST_ROOT/invalid.out" 2>&1; then
+  fail "bump accepted a non-string YAML version"
+fi
+
+cmp -s "$TEST_ROOT/package.before" "$invalid_repo/package.json" \
+  || fail "JSON manifest changed before YAML validation failed"
+cmp -s "$TEST_ROOT/plugin.before" "$invalid_repo/.hermes-plugin/plugin.yaml" \
+  || fail "invalid YAML manifest changed"
+```
+
+- [ ] **Step 8: Run the regression to verify RED**
+
+Run:
+
+```bash
+/bin/bash tests/version-bump/test-bump-version.sh
+```
+
+Expected: FAIL with `JSON manifest changed before YAML validation failed`; without preflight, the JSON manifest is written before the later YAML reader rejects its non-string version.
+
+- [ ] **Step 9: Add the bump-only preflight**
+
+Add this helper after `declared_files` in `scripts/bump-version.sh`:
+
+```bash
+preflight_manifests() {
+  local path field fullpath
+
+  require_tool jq || return 1
+  while IFS=$'\t' read -r path field; do
+    fullpath="$REPO_ROOT/$path"
+    [[ -f "$fullpath" ]] || continue
+
+    if ! read_manifest_field "$fullpath" "$field" >/dev/null; then
+      echo "error: cannot read declared manifest: $path ($field)" >&2
+      return 1
+    fi
+  done < <(declared_files)
+}
+```
+
+Call it in `cmd_bump` after version-format validation and before the first bump output or write:
+
+```bash
+  preflight_manifests
+
+  echo "Bumping all declared files to $new_version..."
+```
+
+- [ ] **Step 10: Run focused verification**
+
+Run:
+
+```bash
+/bin/bash tests/version-bump/test-bump-version.sh
+scripts/lint-shell.sh scripts/bump-version.sh tests/version-bump/test-bump-version.sh
+scripts/bump-version.sh --check
+git diff --check
+```
+
+Expected:
+
+- The behavioral test prints `Version-bump tests passed`.
+- Shell lint reports both scripts with no errors.
+- `--check` lists eight declared manifests, including `.hermes-plugin/plugin.yaml`, all at `6.2.0`.
+- `git diff --check` prints nothing.
+
+- [ ] **Step 11: Review and commit the implementation**
+
+Run:
+
+```bash
+git status --short
+git diff -- .version-bump.json scripts/bump-version.sh tests/version-bump/test-bump-version.sh
+git add .version-bump.json scripts/bump-version.sh tests/version-bump/test-bump-version.sh
+git commit \
+  -m "fix(release): wire Hermes into version bumps" \
+  -m "Register the Hermes YAML manifest alongside the existing JSON manifests. Route manifest reads and writes by extension through jq or Mike Farah yq v4, with field names and values passed as data." \
+  -m "Preflight every present manifest before the mutating bump loop so a deterministic YAML read failure cannot leave earlier JSON manifests partially updated. Cover check, audit, bump, registry wiring, and byte-for-byte no-partial-write behavior with one focused fixture test."
+```
+
+Expected: the commit succeeds with only the three implementation paths staged.

docs/superpowers/specs/2026-07-30-codex-efficiency-fixes-design.md

@@ -0,0 +1,252 @@
+# Codex Efficiency Fixes — Design
+
+Date: 2026-07-30
+Status: approved by Jesse (in-session)
+Branch: `codex-efficiency-fixes` off `dev`
+
+## Sources
+
+- Eval campaign closeout: `superpowers-autoresearch/reports/2026-07-codex-efficiency-campaign.md`
+  (treatment table §4; every treatment below has a scorer and a measured
+  `dev` baseline).
+- Codex source recon: `superpowers-autoresearch/docs/2026-07-29-codex-multiagent-v2-capabilities.md`
+  (file:line citations against the Codex CLI source; grounds T2, T3, T5).
+- Published experiment write-ups: `superpowers-evals/docs/experiments/`.
+- Drew's spinout stack (PRs #2036, #2035) is **evidence, not adopted text**:
+  Jesse wants to dig into those fixes in more detail before adopting any
+  of them; they inform the problem statements only.
+
+## Goal
+
+Ship the five evidence-strong treatments from the codex-efficiency eval
+campaign as superpowers skill/doc changes, each graded against its
+pre-registered criterion by the campaign's scorers before its PR is cut.
+Phase 2 (everything else in the closeout treatment table) follows, each
+item gated on new baseline work first.
+
+## Scope decisions (settled with Jesse)
+
+- **Phase 1 = the evidence-strong five** (T1–T5 below). Phase 2 items
+  each need a failing baseline before any fix ships (discrimination
+  rule: inconclusive-by-zero is a stop).
+- **One branch, PR per treatment.** Development and batteries happen on
+  `codex-efficiency-fixes`; when a treatment beats its criterion, it is
+  cut into its own PR against `dev` with its eval evidence. No merge
+  without Jesse's per-PR approval.
+- **T4 ships cross-harness with a global regression battery** (Claude
+  Code, Codex, Gemini), variant C shape: ceremony scales, approval never
+  does.
+
+## The five treatments
+
+### T1. SDD worker-review prohibition
+
+**Evidence:** 9/9 depth-2 spawns across 4 corpora were implementer-issued
+reviewers; all 9 were same-task duplicates of the review the controller
+dispatches anyway. The dispatch contract never says review is not the
+worker's job; "self-review" in the implementer prompt gets reified into a
+reviewer subagent on harnesses where children can spawn (Codex).
+
+**Changes:**
+- `skills/subagent-driven-development/implementer-prompt.md`: an explicit
+  "You do not dispatch subagents" clause — self-review means reading your
+  own diff; the controller owns all review dispatch; a reviewer you spawn
+  duplicates a review the process already provides.
+- `skills/subagent-driven-development/SKILL.md`: one dispatch-contract
+  line in the task loop, plus a Red Flags row: "An independent review
+  would strengthen my report" → review is the controller's next step;
+  your reviewer is a duplicate seat.
+- Harness-agnostic wording (no-op where children cannot spawn).
+
+**Graded by:** `score_e6.py` (depth-2 spawns by spawner role, duplicate
+review families); `score_e5.py` for the same-scope variant.
+**Baseline:** 9/9 worker-issued, 0 counter-examples.
+**Criterion:** 0 worker-issued depth-2 spawns AND review coverage
+preserved (every task still gets exactly one controller-dispatched task
+review).
+
+### T2. Event-driven waiting
+
+**Evidence:** 60–78% of `wait_agent` calls time out in every corpus
+(dev 67.1%, spinout 60.2%). Source recon: V2 waits are event
+subscriptions, not polls — one long wait has the same wake latency as a
+10s poll at ~1/90th the calls; a completed child's FINAL_ANSWER is pushed
+into the parent's mailbox and drained into the next model request with no
+wait at all.
+
+**Changes** (`skills/using-superpowers/references/codex-tools.md`):
+- Never short-timeout poll.
+- While local work remains, do not wait — child results arrive with your
+  next turn via the mailbox.
+- When genuinely idle, issue ONE `wait_agent` with a long `timeout_ms`
+  (900000+; harness max 3600000).
+- V2 caveat stated: completion mail carries `trigger_turn=false` and will
+  not wake an idle controller — that is the one job `wait_agent` has.
+
+**Graded by:** `score_e7.py` (timeout rate, inter-poll cadence,
+cache-rebill estimate — the rebill figure stays labeled as an estimate).
+**Baseline:** dev 67.1% timeout rate.
+**Criterion:** timeout rate < 25% with no loss of task completion.
+
+### T3. codex-tools.md corrections
+
+**Evidence:** five claims in the current guidance are contradicted by the
+Codex source (all file:line-cited in the capabilities doc):
+1. `close_agent` does not exist in multi-agent V2 (V1-only). V2 LRU-evicts
+   finished children automatically; not closing costs nothing;
+   `followup_task` transparently reloads an evicted child.
+2. Fix rounds can always resume the implementer via `followup_task` —
+   dev's "if your harness cannot send another message to a spawned agent,
+   dispatch each fix round as a fresh implementer" branch is dead on V2.
+3. Role files (`~/.codex/agents/**.toml`) DO attach to spawns via
+   `agent_type` on isolated forks (0.145+).
+4. Full-history forks accept `model`/`reasoning_effort` overrides; only
+   `agent_type` is refused. (Isolated forks remain the SDD guidance for
+   context-hygiene reasons, stated accurately.)
+5. Dispatch guidance must never name non-V2 model presets — the V2 spawn
+   allowlist is v2 presets only; others hard-error.
+
+**Changes:** rewrite the multi-agent paragraph of
+`skills/using-superpowers/references/codex-tools.md` to be
+version-honest (V1 vs V2 behavior labeled where they differ).
+
+**Graded by:** source citation (already verified); no scorer regressions
+on the shared battery. `score_e8.py` is retained as a V1/V2 schema
+detector, not a hygiene grader — no `close_agent` checklist ships.
+
+### T4. Brainstorming three-path router (variant C: approval always)
+
+**Evidence:** micro — the current HARD-GATE text pushes a bounded task to
+FULL ceremony 5/5, while Z-null (no guidance) and a three-path router
+both differentiate 5/5: the absolute wording suppresses discrimination
+the model draws natively. FULL battery — ceremony volume scales
+moderately (16.7 vs 24.0 tool calls, bounded vs arch), but the
+two-document ritual (spec file → plan file) ran unconditionally in every
+rep. The measured waste is the unconditional artifact ritual, not the
+approval gate.
+
+**Design (variant C):** three paths scale the ARTIFACT; every path keeps
+human approval before implementation:
+- **Spike** (feasibility question, explicitly throwaway): present the
+  question and the intended probe in 2–3 sentences, get a nod, go. No
+  docs. Findings return as a recommendation; anything built stays labeled
+  throwaway.
+- **Bounded** (well-scoped change to an existing, understood flow):
+  present a short design in chat, get approval, implement. No spec file,
+  no writing-plans invocation.
+- **Architectural** (restructures components, new subsystem, public
+  interface change): the full current flow — spec doc, review,
+  writing-plans.
+
+**Guards (all ship with the router):**
+- Classification is said out loud ("this looks bounded, so I'll present a
+  short design here rather than write a spec") so the human can override.
+- When in doubt between two paths, take the heavier one.
+- One-way ratchet: hidden complexity discovered mid-path upgrades the
+  path; never downgrade mid-task.
+- New Red Flags rows targeting classification-as-escape-hatch ("I'll call
+  it bounded to skip the doc").
+
+**Changes** (`skills/brainstorming/SKILL.md`): HARD-GATE keeps "no
+implementation before approval" and drops "regardless of perceived
+simplicity" as the ceremony driver; anti-pattern section reframed (the
+sin is skipping approval, not skipping documents); checklist steps 6–9
+become the architectural path; process-flow graph gains the router; Red
+Flags rows added. This is carefully-tuned content — the edit follows
+writing-skills methodology and ships only with the full eval evidence
+below.
+
+**Graded by (three layers):**
+1. **Micro** (`ceremony-path-micro.py`, adapted): variant C literal text,
+   plus adversarially ambiguous briefs the campaign never tested (a task
+   that pattern-matches bounded but hides a public interface change).
+   Criteria: spike/bounded/arch differentiate (≥4/5 per cell); ambiguous
+   briefs escalate to FULL (≥4/5); arch never downgrades (5/5).
+2. **Codex ceremony battery:** `cx-ceremony-{spike,bounded,arch}` on the
+   fix arm, 3 reps each, `score_e4.py` census. Criteria: bounded reps
+   show an approval turn but zero committed spec files and zero
+   writing-plans ritual; arch reps keep the full two-doc flow; spike reps
+   stay minimal.
+3. **Global regression battery:** the same three ceremony scenarios on
+   Claude Code and Gemini (rig work: those scenarios are currently
+   codex-gated), 3 reps each; plus the triggering acceptance check
+   ("Let's make a react todo list" auto-triggers brainstorming into the
+   full/architectural path) on all three harnesses.
+
+### T5. Explicit model on child-issued spawns
+
+**Evidence:** root spawns are 100% explicit-model at CLI 0.146 (dev
+14/14); the live gap is depth-2 — 2/2 child-issued spawns omitted
+`model`. Source recon: `model` without `reasoning_effort` resets effort
+to the MODEL's default, not the parent's.
+
+**Changes** (`skills/using-superpowers/references/codex-tools.md`):
+- Every spawn you issue — including as a child — sets `model` AND
+  `reasoning_effort`; the effort-reset trap is named.
+- Advise `[agents].default_subagent_model` and
+  `[agents].default_subagent_reasoning_effort` in `~/.codex/config.toml`
+  as the machine-level backstop for anything that slips through.
+
+**Graded by:** `score_e1.py` (per-spawn explicit-model rate, by depth) on
+the shared battery.
+**Baseline:** depth-2: 0/2 explicit.
+**Criterion:** every spawn at every depth carries explicit model +
+effort. Pre-registered caveat: if T1 eliminates depth-2 spawns entirely,
+T5 grades as root-spawn regression (hold 100%) plus doc correctness and
+is recorded inconclusive-by-zero at depth-2 — the config backstop is then
+the operative mechanism.
+
+## Grading plan
+
+- **Shared SDD battery** carries T1, T2, T5: `cx-sdd-small`, fix-branch
+  arm (`/tmp/sp-arm-fix`), 8 reps across both container lanes. Dev
+  baselines are already measured; no baseline re-runs.
+- **T4 batteries** as listed above (micro + codex ceremony + global
+  regression).
+- **Pre-registration:** every battery gets a hypothesis-log entry
+  (prediction, scorer, criterion) in
+  `superpowers-autoresearch/logs/2026-07-30-codex-efficiency-fixes.md`
+  BEFORE it runs. Standing rules carry over: append-only log, manual
+  inspection of scorer matches on fix-arm runs (non-circular
+  verification), no raw rollouts committed, correctness rides beside
+  cost in every verdict.
+- **Attribution:** orthogonal scorers on one combined branch; unexpected
+  regressions bisect by treatment commit.
+- **Budget:** shared battery ~$40, codex ceremony ~$40, global
+  regression ~$40–80, micros ~$5 → phase 1 ≈ $150–200 of the ~$850
+  remaining from the campaign's $1000.
+
+## Process
+
+- Work happens in the `codex-efficiency-fixes` worktree (branched off
+  `dev`); execution via subagent-driven-development from a written plan.
+- Skill-text changes follow writing-skills methodology.
+- Scenario/rig changes (un-gating ceremony scenarios for Claude
+  Code/Gemini, adversarial micro briefs) land in `superpowers-evals`
+  main, as authorized.
+- PR-per-treatment against `dev`, each with its eval evidence and the
+  standard identification block; merges only on Jesse's per-PR approval.
+
+## Phase 2 queue (baseline-first; not in this plan's tasks)
+
+Each item requires a failing baseline before any fix ships:
+1. **Dispatch routing / long-session drift** — needs a long-session
+   elicitation rig (fresh sessions don't reproduce the pathology at CLI
+   0.146). Drew's stack informs the treatment shape.
+2. **Verification leases / evidence receipts** — needs the
+   substring-aware duplicate counter added to `score_e3.py` first
+   (current baseline 1/23 exact-string pairs is too weak).
+3. **Remediation cap** — small-n baseline (2/3 reps) needs more reps.
+4. **Cross-task-race probe redesign** — `score_e5.py`'s probe is
+   inconclusive-by-zero by design tradeoff; needs a stronger probe.
+5. **E5 D4 shell-command parser** — fix-review-scope classifier cannot
+   parse compound commands; scorer work, not skill work.
+
+## Out of scope
+
+- Adopting Drew's spinout stack (#2036/#2035) or its text.
+- RoboRev, Codex token telemetry (separate codebases).
+- A `close_agent` hygiene checklist (V2 has no such tool — closed as
+  do-not-ship in the campaign).
+- Claude Code/Gemini-specific efficiency treatments beyond the T4
+  regression battery.

docs/superpowers/specs/2026-08-05-hermes-version-bump-wiring-design.md

@@ -0,0 +1,56 @@
+# Hermes Version-Bump Wiring Design
+
+**Date:** 2026-08-05
+**Revised:** 2026-08-06
+**Status:** Approved
+
+## Goal
+
+Keep `.hermes-plugin/plugin.yaml` in lockstep with the repository version by
+registering it in `.version-bump.json` and teaching `scripts/bump-version.sh`
+to process YAML without implementing a YAML parser in Bash.
+
+## Design
+
+- Add `{ "path": ".hermes-plugin/plugin.yaml", "field": "version" }` to
+  `.version-bump.json`.
+- Route `.json` through the existing `jq` helpers and `.yaml` through Mike
+  Farah `yq` v4. The YAML key and value are passed as data, not interpolated
+  into the expression.
+- Support only a present top-level YAML string field. Nested fields and `.yml`
+  are out of scope.
+- Route `--check`, `--audit`, and version updates through the same small
+  read/write dispatcher.
+- Before a version bump writes any manifest, run one read-only preflight that
+  validates the required tools and reads every present declared manifest
+  through the dispatcher. This prevents a deterministic YAML failure from
+  occurring after earlier JSON files have already been updated. Missing-file
+  behavior remains unchanged, and `--help` still works without `jq` or `yq`.
+
+The preflight is the only reliability addition. It does not make the script
+transactional or redesign its existing audit and error-status behavior.
+
+## Tests
+
+Three focused behavioral tests run the real script against an isolated
+temporary fixture and prove:
+
+- aligned JSON and YAML pass `--check` and `--audit`, and a bump updates both
+  formats;
+- an actual bump with JSON declared first and a later YAML manifest whose
+  top-level `version` is not a string exits nonzero and leaves every manifest
+  byte-for-byte unchanged; and
+- the real `.version-bump.json` registers the Hermes manifest.
+
+Verification also runs shell lint and `scripts/bump-version.sh --check` against
+the repository.
+
+## Non-Goals
+
+- No hand-written YAML parser.
+- No `.yml` or nested-YAML support.
+- No Hermes runtime changes.
+- No rollback framework, general config-schema layer, audit/status refactor, or
+  exhaustive failure matrix.
+- No change to the separate version-validation and JSON-expression issue found
+  during review.

gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
   "description": "Core skills library: TDD, debugging, collaboration patterns, and proven techniques",
-  "version": "6.2.0",
+  "version": "6.3.0",
   "contextFileName": "GEMINI.md"
 }

hooks/hooks-codex.json

@@ -1,17 +0,0 @@
-{
-  "hooks": {
-    "SessionStart": [
-      {
-        "matcher": "compact",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "\"${PLUGIN_ROOT}/hooks/run-hook.cmd\" session-start-codex",
-            "async": false,
-            "timeout": 30
-          }
-        ]
-      }
-    ]
-  }
-}

hooks/session-start-codex

@@ -1,56 +0,0 @@
-#!/usr/bin/env bash
-# Codex SessionStart hook for the superpowers plugin.
-#
-# Codex re-fires SessionStart with source:"compact" after every context
-# compaction (verified on codex-cli 0.145.0). Compaction replaces the live
-# context with a summary, which sheds the using-superpowers bootstrap and any
-# active skill's instructions — the measured cause of mid-session dispatch
-# drift in long multi-agent runs. This hook re-injects the bootstrap at
-# exactly that moment, restoring the same re-injection Claude Code performs
-# via its "startup|clear|compact" SessionStart matcher.
-#
-# On source:"startup" it emits nothing: the native Codex plugin path owns
-# session-start injection, and duplicating it here would recreate the
-# redundancy that led to the original session-start-codex hook's removal.
-#
-# Codex injects raw hook stdout into the model's context (verified with
-# sentinel probes), so output is plain text — not the JSON envelopes other
-# harnesses require of hooks/session-start.
-#
-# A hook failure must never break a session: every path fails open to empty
-# output and exit 0.
-
-set -u
-
-payload="$(cat 2>/dev/null || true)"
-
-# Act only on post-compaction re-fires. Tolerate arbitrary whitespace around
-# the JSON colon; anything unparseable falls through to a silent no-op.
-if ! printf '%s' "$payload" | grep -qE '"source"[[:space:]]*:[[:space:]]*"compact"'; then
-    exit 0
-fi
-
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-PLUGIN_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
-
-using_superpowers_content="$(cat "${PLUGIN_ROOT}/skills/using-superpowers/SKILL.md" 2>/dev/null)" || using_superpowers_content=""
-if [ -z "$using_superpowers_content" ]; then
-    exit 0
-fi
-
-# printf instead of heredocs throughout: heredocs hang on bash 5.3+.
-# See: https://github.com/obra/superpowers/issues/571
-printf '%s\n' "<EXTREMELY_IMPORTANT>"
-printf '%s\n\n' "You have superpowers."
-printf '%s\n\n' "**Below is the full content of your 'superpowers:using-superpowers' skill - your introduction to using skills. For all other skills, use the 'Skill' tool:**"
-printf '%s\n' "$using_superpowers_content"
-printf '%s\n\n' "</EXTREMELY_IMPORTANT>"
-printf '%s\n' "<CONTEXT_RESTORED>"
-printf '%s\n' "Your context was just summarized (compacted). The summary preserves your progress but not your working instructions — the files are authoritative."
-printf '%s\n' ""
-printf '%s\n' "Before your next tool call:"
-printf '%s\n' "- Re-read the SKILL.md of any skill you are mid-way through executing. If you are executing subagent-driven-development, re-read skills/subagent-driven-development/SKILL.md."
-printf '%s\n' "- On Codex, also re-read skills/using-superpowers/references/codex-tools.md and follow its dispatch rules on every spawn_agent call."
-printf '%s\n' "</CONTEXT_RESTORED>"
-
-exit 0

package.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.2.0",
+  "version": "6.3.0",
   "description": "Superpowers skills and runtime bootstrap for coding agents",
   "type": "module",
   "main": ".opencode/plugins/superpowers.js",

scripts/bump-version.sh

@@ -40,12 +40,72 @@ write_json_field() {
   jq "$jq_path = \"$value\"" "$file" > "$tmp" && mv "$tmp" "$file"
 }
 
+require_tool() {
+  command -v "$1" >/dev/null 2>&1 || {
+    echo "error: required tool '$1' is not on PATH" >&2
+    return 1
+  }
+}
+
+read_yaml_field() {
+  local file="$1" field="$2"
+  require_tool yq || return 1
+  FIELD="$field" yq -er '.[strenv(FIELD)] | select(tag == "!!str")' "$file"
+}
+
+write_yaml_field() {
+  local file="$1" field="$2" value="$3"
+  FIELD="$field" VALUE="$value" \
+    yq -i '.[strenv(FIELD)] = strenv(VALUE)' "$file"
+}
+
+read_manifest_field() {
+  local file="$1"
+
+  case "$file" in
+    *.json) read_json_field "$@" ;;
+    *.yaml) read_yaml_field "$@" ;;
+    *)
+      echo "error: unsupported manifest format: $file" >&2
+      return 1
+      ;;
+  esac
+}
+
+write_manifest_field() {
+  local file="$1"
+
+  case "$file" in
+    *.json) write_json_field "$@" ;;
+    *.yaml) write_yaml_field "$@" ;;
+    *)
+      echo "error: unsupported manifest format: $file" >&2
+      return 1
+      ;;
+  esac
+}
+
 # Read the list of declared files from config.
 # Outputs lines of "path<TAB>field"
 declared_files() {
   jq -r '.files[] | "\(.path)\t\(.field)"' "$CONFIG"
 }
 
+preflight_manifests() {
+  local path field fullpath
+
+  require_tool jq || return 1
+  while IFS=$'\t' read -r path field; do
+    fullpath="$REPO_ROOT/$path"
+    [[ -f "$fullpath" ]] || continue
+
+    if ! read_manifest_field "$fullpath" "$field" >/dev/null; then
+      echo "error: cannot read declared manifest: $path ($field)" >&2
+      return 1
+    fi
+  done < <(declared_files)
+}
+
 # Read the audit exclude patterns from config.
 audit_excludes() {
   jq -r '.audit.exclude[]' "$CONFIG" 2>/dev/null
@@ -68,7 +128,7 @@ cmd_check() {
       continue
     fi
     local ver
-    ver=$(read_json_field "$fullpath" "$field")
+    ver=$(read_manifest_field "$fullpath" "$field")
     printf "  %-45s  %s\n" "$path ($field)" "$ver"
     versions+=("$ver")
   done < <(declared_files)
@@ -101,7 +161,7 @@ cmd_audit() {
   current_version=$(
     while IFS=$'\t' read -r path field; do
       local fullpath="$REPO_ROOT/$path"
-      [[ -f "$fullpath" ]] && read_json_field "$fullpath" "$field"
+      [[ -f "$fullpath" ]] && read_manifest_field "$fullpath" "$field"
     done < <(declared_files) | sort | uniq -c | sort -rn | head -1 | awk '{print $2}'
   )
 
@@ -172,6 +232,8 @@ cmd_bump() {
     exit 1
   fi
 
+  preflight_manifests
+
   echo "Bumping all declared files to $new_version..."
   echo ""
 
@@ -182,8 +244,8 @@ cmd_bump() {
       continue
     fi
     local old_ver
-    old_ver=$(read_json_field "$fullpath" "$field")
-    write_json_field "$fullpath" "$field" "$new_version"
+    old_ver=$(read_manifest_field "$fullpath" "$field")
+    write_manifest_field "$fullpath" "$field" "$new_version"
     printf "  %-45s  %s -> %s\n" "$path ($field)" "$old_ver" "$new_version"
   done < <(declared_files)
 

scripts/package-codex-plugin.sh

@@ -40,9 +40,8 @@ Options:
   -h, --help               Show this help.
 
 The archive is rootless: .codex-plugin/, assets/, skills/, README.md, LICENSE,
-CODE_OF_CONDUCT.md, and the Codex SessionStart hook (hooks/hooks-codex.json plus
-its two scripts) sit at the archive root. Source-only repo files, other-harness
-hooks, tests, docs, and other harness manifests are intentionally not shipped.
+and CODE_OF_CONDUCT.md sit at the archive root. Source-only repo files, hooks, tests,
+docs, and other harness manifests are intentionally not shipped.
 EOF
 }
 
@@ -239,9 +238,6 @@ git -C "$REPO_ROOT" -c tar.umask=0022 archive --format=tar "$REF" -- \
   LICENSE \
   README.md \
   assets \
-  hooks/hooks-codex.json \
-  hooks/run-hook.cmd \
-  hooks/session-start-codex \
   skills \
   | tar -xpf - -C "$STAGE"
 
@@ -337,7 +333,7 @@ esac
 
 unexpected_paths="$(
   printf '%s\n' "$archive_paths" |
-    grep -E '(^superpowers/|^\.agents/|^hooks/hooks\.json$|^hooks/hooks-cursor\.json$|^hooks/session-start$|package\.json$|^\.git|^\.pytest_cache|^\.ruff_cache|^scripts/|^tests/|^docs/|^evals/|^lib/|^\.claude|^\.cursor|^\.kimi|^\.opencode|^\.pi|^AGENTS\.md$|^CLAUDE\.md$|^GEMINI\.md$|^RELEASE-NOTES\.md$|^CHANGELOG\.md$)' || true
+    grep -E '(^superpowers/|^\.agents/|^hooks/|package\.json$|^\.git|^\.pytest_cache|^\.ruff_cache|^scripts/|^tests/|^docs/|^evals/|^lib/|^\.claude|^\.cursor|^\.kimi|^\.opencode|^\.pi|^AGENTS\.md$|^CLAUDE\.md$|^GEMINI\.md$|^RELEASE-NOTES\.md$|^CHANGELOG\.md$)' || true
 )"
 if [[ -n "$unexpected_paths" ]]; then
   printf '%s\n' "$unexpected_paths" | sed 's/^/  /' >&2

scripts/sync-to-codex-plugin.sh

@@ -48,6 +48,7 @@ EXCLUDES=(
   "/.claude-plugin/"
   "/.codex/"
   "/.cursor-plugin/"
+  "/.devin-plugin/"
   "/.git/"
   "/.gitattributes"
   "/.github/"

skills/brainstorming/SKILL.md

@@ -7,20 +7,91 @@ description: "You MUST use this before any creative work - creating features, bu
 
 Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
 
-Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.
+Start by classifying how much process the request needs, then work
+through your path: understand the context, refine the idea, present a
+design, and get your human partner's approval.
 
 <HARD-GATE>
-Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity.
+Do NOT invoke any implementation skill, write any code, scaffold any
+project, or take any implementation action until you have told your
+human partner what you intend and they have approved it. This applies
+to EVERY task on EVERY path below — the ceremony scales with the task;
+the approval gate never does.
 </HARD-GATE>
 
-## Anti-Pattern: "This Is Too Simple To Need A Design"
+## Three Paths
 
-Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.
+Before your first question, classify the request and say the
+classification out loud — "this looks bounded, so I'll present a short
+design here rather than write a spec" — so your human partner can
+override it:
+
+- **Spike** — a feasibility question ("can we...", "is it possible...",
+  "quick and dirty is fine") whose output is an answer, not code you
+  keep. Present the question and what you'll try in 2-3 sentences, get
+  a nod, then find out as cheaply as correctness allows. No design
+  doc, no spec file. Report findings as a recommendation; anything you
+  built stays labeled throwaway.
+- **Bounded** — a well-scoped change to code that already exists in
+  this repo: a new flag, a small endpoint, a one-file fix.
+  Understanding the kind of app is not enough — bounded means the flow
+  you are changing is already here to read. If there is no existing
+  flow to change, the task is not bounded. Ask the clarifying
+  questions that matter, present a short design IN CHAT (a few
+  sentences to a few short paragraphs), and STOP. Implementation
+  starts only after your human partner says yes to that design — a
+  bounded task's approval is as hard a gate as an architectural
+  one. No spec file, no implementation plan document.
+- **Architectural** — new projects, new subsystems, changes that
+  restructure how components fit together or alter interfaces others
+  depend on. Follow the full process: questions, approaches, sectioned
+  design, written spec, then the writing-plans skill.
+
+When in doubt between two paths, take the heavier one. The ratchet is
+one-way: hidden complexity discovered mid-task upgrades the path —
+stop, say so, and step up. Nothing downgrades mid-task.
+
+## Anti-Pattern: "Too Simple To Need Approval"
+
+Every path ends with your human partner approving your intent before
+implementation. A todo list, a single-function utility, a config
+change — the design may be two sentences in chat, but you MUST present
+it and get approval. "Simple" tasks are where unexamined assumptions
+cause the most wasted work. What scales with simplicity is the
+artifact, never the approval.
+
+## Red Flags
+
+| Thought | Reality |
+|---------|---------|
+| "This is too simple to need a design" | Simple means a short design, not no design. Two sentences in chat, then approval. |
+| "I'll call it bounded and skip the spec" | Reaching for a label to skip work IS the doubt — take the heavier path. |
+| "It's bounded and the design is obvious — I'll start while they read it" | The gate is the approval, not the design's length. Present, then stop until you hear yes. |
+| "I understand this kind of app, so it's bounded" | Bounded measures the repo, not your familiarity. A new project has no existing flow — it is architectural. |
+| "The spike works, so I'll keep the code" | A spike's output is an answer. Keeping the code is a new request — classify it. |
+| "It grew, but I'm almost done — no need to re-classify" | Hidden complexity upgrades the path mid-task. Stop and say so. |
+| "They approved the spike, so the follow-up change is approved too" | Each task gets its own classification and its own approval. |
 
 ## Checklist
 
-You MUST create a task for each of these items and complete them in order:
+Classify first, announce the path, then create a task for each item on
+your path and complete them in order.
 
+**Spike:**
+1. **Explore project context** — enough to frame the probe
+2. **Present question + probe plan** — 2-3 sentences
+3. **Get approval** — a nod is enough
+4. **Investigate** — as cheaply as correctness allows
+5. **Report findings** — a recommendation; label anything built as throwaway
+
+**Bounded:**
+1. **Explore project context** — check files, docs, recent commits
+2. **Ask clarifying questions** — one at a time, the ones that matter
+3. **Present short design in chat** — approach, files touched, testing
+4. **Get approval** — STOP and wait for an explicit yes; presenting the design and starting in the same breath is skipping the gate
+5. **Implement** — proceed with the normal development workflow (TDD applies); no plan document
+
+**Architectural:**
 1. **Explore project context** — check files, docs, recent commits
 2. **Offer the visual companion just-in-time** — NOT upfront. The first time a question would genuinely be clearer shown than described, offer it then (its own message); on approval its browser tab opens for you. If no visual question ever arises, never offer it. See the Visual Companion section below.
 3. **Ask clarifying questions** — one at a time, understand purpose/constraints/success criteria
@@ -35,6 +106,13 @@ You MUST create a task for each of these items and complete them in order:
 
 ```dot
 digraph brainstorming {
+    "Classify: spike / bounded / architectural" [shape=diamond];
+    "Present question + probe (2-3 sentences)" [shape=box];
+    "Ask clarifying questions (bounded)" [shape=box];
+    "Present short design in chat" [shape=box];
+    "Human approves?" [shape=diamond];
+    "Investigate; report recommendation" [shape=doublecircle];
+    "Implement via normal workflow (no plan doc)" [shape=doublecircle];
     "Explore project context" [shape=box];
     "Ask clarifying questions" [shape=box];
     "Propose 2-3 approaches" [shape=box];
@@ -44,7 +122,17 @@ digraph brainstorming {
     "Spec self-review\n(fix inline)" [shape=box];
     "User reviews spec?" [shape=diamond];
     "Invoke writing-plans skill" [shape=doublecircle];
+    "Hidden complexity? Upgrade path" [shape=box];
 
+    "Classify: spike / bounded / architectural" -> "Present question + probe (2-3 sentences)" [label="spike"];
+    "Classify: spike / bounded / architectural" -> "Ask clarifying questions (bounded)" [label="bounded"];
+    "Classify: spike / bounded / architectural" -> "Explore project context" [label="architectural"];
+    "Present question + probe (2-3 sentences)" -> "Human approves?";
+    "Ask clarifying questions (bounded)" -> "Present short design in chat";
+    "Present short design in chat" -> "Human approves?";
+    "Human approves?" -> "Investigate; report recommendation" [label="spike: yes"];
+    "Human approves?" -> "Implement via normal workflow (no plan doc)" [label="bounded: yes"];
+    "Hidden complexity? Upgrade path" -> "Classify: spike / bounded / architectural";
     "Explore project context" -> "Ask clarifying questions";
     "Ask clarifying questions" -> "Propose 2-3 approaches";
     "Propose 2-3 approaches" -> "Present design sections";
@@ -58,10 +146,21 @@ digraph brainstorming {
 }
 ```
 
-**The terminal state is invoking writing-plans.** Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is writing-plans.
+**Terminal states are path-bound.** Architectural: the ONLY skill you
+invoke after brainstorming is writing-plans — never frontend-design,
+mcp-builder, or any other implementation skill. Bounded: after
+approval, implementation proceeds directly through the normal
+development workflow; no plan document. Spike: the terminal state is a
+reported recommendation.
 
 ## The Process
 
+The subsections below serve the bounded and architectural paths (a
+spike stops at "present the probe, get a nod"). Sections from
+**Exploring approaches** onward are architectural-path depth — for
+bounded work, context plus a few questions plus a short in-chat design
+is the whole process.
+
 **Understanding the idea:**
 
 - Check out the current project state first (files, docs, recent commits)
@@ -100,7 +199,7 @@ digraph brainstorming {
 - Where existing code has problems that affect the work (e.g., a file that's grown too large, unclear boundaries, tangled responsibilities), include targeted improvements as part of the design - the way a good developer improves code they're working in.
 - Don't propose unrelated refactoring. Stay focused on what serves the current goal.
 
-## After the Design
+## After the Design (architectural path)
 
 **Documentation:**
 

skills/brainstorming/visual-companion.md

@@ -83,10 +83,11 @@ scripts/start-server.sh --project-dir /path/to/project --open --foreground
 
 **Copilot CLI:**
 ```bash
-# Use --foreground and start the server via the bash tool with mode: "async"
-# so the process survives across turns. Capture the returned shellId for
-# read_bash / stop_bash if you need to interact with it later.
-scripts/start-server.sh --project-dir /path/to/project --open --foreground
+# Start it with Copilot CLI's non-blocking/background shell mechanism so the
+# server survives across turns. Keep --foreground so the harness, not the
+# script, owns backgrounding. The launcher is a .sh, so invoke it via bash
+# (on Windows, call Git Bash's bash.exe from the PowerShell tool).
+bash scripts/start-server.sh --project-dir /path/to/project --open --foreground
 ```
 
 **Other environments:** The server must keep running in the background across conversation turns. If your environment reaps detached processes, use `--foreground` and launch the command with your platform's background execution mechanism.

skills/finishing-a-development-branch/SKILL.md

@@ -174,6 +174,29 @@ git worktree remove "$WORKTREE_PATH"
 git worktree prune  # Self-healing: clean up any stale registrations
 ```
 
+**If removal is refused** (`contains modified or untracked files`): the
+worktree holds files that exist nowhere else — uncommitted plans, notes,
+or scratch work. Never `--force` on your own initiative. Show your human
+partner what is at stake and ask:
+
+```bash
+git -C "$WORKTREE_PATH" status --porcelain -uall
+```
+
+```
+Worktree removal refused — these files were never committed:
+
+<file list>
+
+1. Commit them to <branch> before cleanup
+2. Move them into <main repo root>
+3. Delete them (unrecoverable)
+
+Which?
+```
+
+Carry out the choice, then remove the worktree.
+
 **Otherwise:** The host environment owns this workspace — leave it in
 place. If your platform provides a workspace-exit tool, use it.
 
@@ -196,6 +219,7 @@ place. If your platform provides a workspace-exit tool, use it.
 | "'Yeah, get rid of it' counts as confirmation" | Only the typed word `discard` authorizes deletion. |
 | "The PR is up, so the worktree is clutter now" | PR feedback gets fixed in that worktree. It stays until the work lands. |
 | "This other worktree looks stale — I'll clean it too" | Clean up only worktrees under `.worktrees/` or `worktrees/`. Everything else belongs to the host. |
+| "Removal refused — `--force` is just finishing the cleanup" | The refusal means files exist only in that worktree. `--force` destroys them permanently. Show your human partner and ask. |
 | "The merged-result failure is probably flaky" | A failing merged result stops everything. Branch and worktree stay put while you investigate. |
 | "The base branch is obviously main" | Confirm the fork point or ask. Merging into the wrong base is expensive to undo. |
 | "The push was rejected — force-push will fix it" | A rejected push means the remote moved. Investigate; force-push only on your human partner's explicit request. |

skills/subagent-driven-development/SKILL.md

@@ -154,7 +154,10 @@ a ledger file, not only in todos.
   that happens, recover from `git log`.
 
 Read the plan once, note its context and Global Constraints, and create a
-todo per task.
+todo per task. If the plan names a Spec, read that too: the spec is the
+authority the plan argues from, and conflicts inside the plan resolve
+against it. A plan with no reachable spec gets a ledger note saying so —
+rulings made without one are provisional.
 
 Before dispatching Task 1, scan the plan once for conflicts, writing down
 what you checked as you check it:
@@ -170,6 +173,14 @@ its own text agrees with itself — the tests it specifies against the code it
 specifies, the files it creates against the files it later touches. "The scan
 is clean" without those rows is not a scan you ran.
 
+**When the plan's header declares `Plan shape: skeleton-first`,** the
+table gets a final section: the DISPATCH PLAN — group the pending tasks
+into waves. Tasks in the same wave are mutually file-disjoint and consume
+no interface still under construction — dispatch each wave's implementers
+concurrently, one worktree per task, and integrate before the next wave;
+tasks that fail those conditions serialize. On a skeleton-first plan, a
+scan without a dispatch plan is not a scan you ran.
+
 Write the table to the ledger. Rule on everything you find before execution
 begins — each finding against the plan text that mandates it — and record
 each ruling in the ledger. If the scan is clean, proceed without comment.
@@ -184,6 +195,10 @@ Use the least powerful model that can handle each role to conserve cost and incr
 
 **Mechanical implementation tasks** (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.
 
+When a task carries a **Tier:** field, follow it — the planner already
+ruled: mechanical → the cheapest available model; judgment → a standard
+model. Do not re-litigate the tier at dispatch.
+
 **Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.
 
 **Architecture and design tasks**: use the most capable available model.
@@ -205,7 +220,10 @@ most expensive — which silently defeats this section.
 **Turn count beats token price.** Wall-clock and context cost scale with how
 many turns a subagent takes, and the cheapest models routinely take 2-3× the
 turns on multi-step work — costing more overall. Use a mid-tier model as the
-floor for reviewers and for implementers working from prose descriptions.
+floor for reviewers and for implementers working from task contracts or
+prose descriptions — unless the task's Tier line says mechanical: the
+planner has already ruled the deliverable fully specified, so treat a
+mechanical-tier contract like spelled-out content.
 When the task's plan text contains the complete code to write, the
 implementation is transcription plus testing: use the cheapest tier for
 that implementer. Single-file mechanical fixes also take the cheapest tier.
@@ -256,7 +274,13 @@ and fix-round diffs need it.
   know; (4) your resolution of any ambiguity you noticed in the brief;
   (5) the report-file path and report contract. Exact values (numbers,
   magic strings, signatures, test cases) appear only in the brief. Never
-  make a subagent read the whole plan file.
+  make a subagent read the whole plan file. When the brief is a contract
+  (goal, success criteria, interfaces) rather than written-out code, item
+  (3) also carries the elaboration the contract leaves to dispatch time:
+  the interfaces as actually built by completed tasks, environment facts
+  and discoveries from earlier reports, and any amendment rulings. There
+  the success criteria name the cases the tests must cover, and the
+  implementer designs its own code and tests within the contract.
 - **Report file:** name the implementer's report file after the brief
   (brief `…/task-N-brief.md` → report `…/task-N-report.md`) and put it in
   the dispatch prompt. The implementer writes the full report there and
@@ -277,6 +301,26 @@ and fix-round diffs need it.
 - Record the implementer's agent identity from the dispatch result —
   fix-loop rounds 1-3 resume this agent.
 - Never dispatch multiple implementation subagents in parallel (conflicts).
+  The one exception is a skeleton-first plan whose dispatch plan shows two
+  or more pending tasks mutually file-disjoint with none consuming an
+  interface still under construction. Dispatch those implementers
+  concurrently, each in its own worktree:
+  - Record the integration base commit in the ledger before the first
+    concurrent dispatch.
+  - Create one worktree per concurrent task off that base
+    (`git worktree add <repo-root>/.worktrees/task-<N> -b task-<N>
+    <base>`); each dispatch's `Work from:` is its own worktree, and its
+    BASE is that worktree's HEAD.
+  - Review each task's diff as usual when it reports. Integrate reviewed
+    branches in plan order: merge each into the integration branch
+    (`git merge --no-ff task-<N>`), and run that task's verification
+    commands after each merge.
+  - A merge conflict or post-merge verification failure is that task's
+    fix-loop round 1: rebase the task branch onto the current
+    integration head in its worktree, then resume its implementer
+    there. Never resolve conflicts yourself.
+  - Remove each worktree (`git worktree remove`) once its branch is
+    integrated, and record the integrated range in the ledger as usual.
 
 Template: [implementer-prompt.md](implementer-prompt.md)
 
@@ -435,6 +479,16 @@ message as your other bookkeeping:
 - `Task <N>: complete (commits <base7>..<head7>, <K> parked)` after a
   tripped breaker
 
+**On a skeleton-first plan,** write one plan-check line with the
+completion line. Re-read the remaining tasks against what this task
+actually established — interfaces as built, environment facts,
+discoveries in the report — and append either `Plan holds` or
+`Amendment: Task <M>: <what changes and why>` to the ledger. An
+amendment is plan authority applied at the plan layer: from then on the
+amended text IS the plan's text, and it rides into every affected task's
+dispatch under item (3). Never dispatch a task whose brief a completed
+task's report has already invalidated.
+
 Then mark the todo complete and move on. Never move to the next task while
 the review has open Critical/Important issues that are neither fixed nor
 parked-with-ruling at the cap.

skills/subagent-driven-development/implementer-prompt.md

@@ -5,8 +5,11 @@ Use this template when dispatching an implementer subagent.
 ```
 Subagent (general-purpose):
   description: "Implement Task N: [task name]"
-  model: [MODEL — REQUIRED: choose per SKILL.md Model Selection; an omitted
-         model silently inherits the session's most expensive one]
+  model: [MODEL — REQUIRED: when the brief carries a Tier line, set from it:
+         mechanical → the cheapest model the subagent tool offers; judgment →
+         a standard mid-tier model. Otherwise choose per SKILL.md Model
+         Selection. An omitted model silently inherits the session's most
+         expensive one]
   prompt: |
     You are implementing Task N: [task name]
 

skills/subagent-driven-development/task-reviewer-prompt.md

@@ -84,6 +84,13 @@ Subagent (general-purpose):
     Warnings or other noise in the implementer's reported test output are
     findings — test output should be pristine.
 
+    Evidence you cannot see is not evidence that doesn't exist. If the
+    report or its test evidence looks truncated, or you cannot locate the
+    results it claims, re-read the file at its stated path — and if it is
+    genuinely missing or garbled, report that as a gap for the controller.
+    Re-running the suite to regenerate what you failed to read is not
+    verification; illegibility of the evidence is not invalidation of it.
+
     ## Part 1: Spec Compliance
 
     Compare the diff against What Was Requested:

skills/using-superpowers/SKILL.md

@@ -56,6 +56,7 @@ If your harness appears here, read its reference file for special instructions:
 - Codex: `references/codex-tools.md`
 - Pi: `references/pi-tools.md`
 - Antigravity: `references/antigravity-tools.md`
+- Hermes Agent: `references/hermes-tools.md`
 
 ## User Instructions
 

skills/using-superpowers/references/codex-tools.md

@@ -78,22 +78,6 @@ default_subagent_model = "<a mid-tier model from your spawn allowlist>"
 default_subagent_reasoning_effort = "medium"
 ```
 
-## Compaction sheds these instructions
-
-Context compaction replaces your transcript with a summary that keeps
-your progress but not your working instructions — the first
-post-compaction dispatch is where routing drift starts, and once one
-bare spawn lands, the broken pattern becomes its own precedent. The
-plugin ships a compaction re-injection hook (`hooks/hooks-codex.json`,
-Codex 0.145+) that restores the bootstrap after every compaction; it
-needs one-time trust approval, so if you never see a
-`<CONTEXT_RESTORED>` block after a compaction, tell your human partner
-the hook may be untrusted or unsupported on this version. Without it,
-re-ground yourself: when a summary appears in your context, re-read
-this file and the SKILL.md of the skill you are mid-way through
-executing before your next dispatch, and trust the ledger over your
-summarized memory of what happened.
-
 ## Environment Detection
 
 Skills that create worktrees or finish branches should detect their

skills/using-superpowers/references/hermes-tools.md

@@ -0,0 +1,56 @@
+# Hermes Agent Tool Mapping
+
+Skills speak in actions ("dispatch a subagent", "create a todo", "read a file"). On Hermes Agent these resolve to the tools below.
+
+## Tools
+
+| Action skills request | Hermes tool |
+|---|---|
+| Read a file | `read_file` |
+| Create a new file | `write_file` |
+| Edit a file (targeted patch) | `patch` |
+| Run a shell command | `terminal` |
+| Search file contents | `search_files` |
+| Find files by name | `terminal` with `find` |
+| Fetch a URL / read a webpage | `web_extract(urls=[...])` |
+| Search the web | `web_search(query=...)` |
+| Dispatch a subagent | `delegate_task(goal=..., context=..., toolsets=[...], role="leaf")` |
+| Task tracking | `todo` tool |
+| Invoke a skill | `skill_view("skill-name")` |
+
+## Instructions file
+
+When a skill mentions "your instructions file," on Hermes Agent this is **`AGENTS.md`** in the project directory, or **`SOUL.md`** globally at `~/.hermes/SOUL.md`.
+
+## Invoking a skill
+
+Hermes Agent has a `skills` toolset with `skill_view` and `skills_list` tools.
+To invoke a superpowers skill, use:
+
+```
+skill_view("brainstorming")
+skill_view("test-driven-development")
+```
+
+If `skill_view` cannot find a superpowers skill (it may not appear in the catalog
+until the plugin fully registers it), fall back to reading the SKILL.md directly:
+
+```
+read_file(path="~/.hermes/plugins/superpowers/skills/<skill-name>/SKILL.md")
+```
+
+This fallback is the same mechanism used by other harnesses without native skill loading.
+
+## Subagent dispatch
+
+Use `delegate_task` to spawn isolated subagents for parallel or sequential workstreams:
+
+```
+delegate_task(goal="...", context="...", toolsets=[...], role="leaf")
+```
+
+If `delegate_task` is unavailable, do the work inline rather than inventing tool calls.
+
+## Task tracking
+
+Use the `todo` tool for task tracking within a session. For multi-agent task boards, use `hermes kanban` CLI if available. Treat older `TodoWrite` references as the task-tracking action.

skills/writing-plans/SKILL.md

@@ -22,6 +22,30 @@ Assume they are a skilled developer, but know almost nothing about our toolset o
 
 If the spec covers multiple independent subsystems, it should have been broken into sub-project specs during brainstorming. If it wasn't, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.
 
+## Two Plan Shapes
+
+Before mapping files, classify the plan's shape and say the
+classification out loud — "this composes three subsystems, so I'll plan
+it skeleton-first" — so your human partner can override it:
+
+- **Task-by-task (default)** — tasks build the feature a component at a
+  time, each step carrying the actual content the engineer needs. Use it
+  for changes to code that already exists, for a spec that touches one
+  subsystem, and whenever the alternative's conditions do not clearly
+  hold. The rest of this skill describes this shape.
+- **Skeleton-first (alternative)** — Task 1 is the thinnest end-to-end
+  slice through every subsystem the spec composes; later tasks widen it
+  one component at a time, each from a contract rather than written-out
+  code. Use it when the spec composes more than one subsystem AND a
+  running end-to-end slice early is worth a longer total build. Read
+  [skeleton-first-plans.md](skeleton-first-plans.md) before writing one
+  — it adds one line to the plan header and replaces this skill's task
+  granularity, task template, and plan-failure list.
+
+When in doubt, plan task-by-task. Skeleton-first buys an earlier running
+system and pays for it in total wall clock; it is a trade, not an
+upgrade.
+
 ## File Structure
 
 Before defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.
@@ -66,6 +90,9 @@ independently testable deliverable.
 
 **Tech Stack:** [Key technologies/libraries]
 
+**Spec:** [path to the spec/design doc this plan implements — the plan
+argues from the spec, so the spec travels with it; executors read both]
+
 ## Global Constraints
 
 [The spec's project-wide requirements — version floors, dependency limits,

skills/writing-plans/skeleton-first-plans.md

@@ -0,0 +1,131 @@
+# Skeleton-First Plans
+
+The alternative plan shape from writing-plans' Two Plan Shapes router.
+Each section below replaces the same-named section of
+[SKILL.md](SKILL.md); everything SKILL.md says that is not named here
+still binds — Scope Check, File Structure, Task Right-Sizing, the plan
+header, Self-Review, and the Execution Handoff.
+
+## Overview
+
+Write a plan that carries the decisions, not the keystrokes:
+decomposition, file structure, interfaces, constraints, and a precise
+contract per task. Assume the engineer is skilled and designs their own
+code and tests from a precise contract, but knows nothing about our
+codebase, toolset, or problem domain — every name, path, constraint, and
+behavior they must match is stated explicitly. DRY. YAGNI. TDD.
+Frequent commits.
+
+## When This Shape Fits
+
+Use it when the spec composes more than one subsystem and a running
+end-to-end slice early is worth a longer total build: the value arrives
+as soon as real input reaches real output, and every later task widens
+something that already runs.
+
+Do not use it for a change to one subsystem, or when the whole point is
+to land the finished thing as fast as possible. This shape spends its
+first task on a slice that does almost nothing, and it spends planning
+effort on contracts and interfaces the task-by-task shape gets for free
+by writing the code out.
+
+## Plan Document Header
+
+The header is SKILL.md's, plus one line directly under the **Goal:**
+line, which is how executors know which shape they are running:
+
+```markdown
+**Plan shape:** skeleton-first
+```
+
+## Walking Skeleton First
+
+Task 1 builds the thinnest end-to-end slice through every subsystem the
+spec composes — real input to real output — before any task deepens a
+single layer; later tasks widen the skeleton.
+
+The test of a skeleton is that it runs. A first task that builds the
+data loader, the schema, or the config layer is a foundation, not a
+skeleton: nothing runs until something above it exists. A skeleton
+reaches the output — thinly, with one real case — through every
+subsystem the spec names.
+
+## Task Contracts, Not Task Scripts
+
+A task states WHAT must exist when it is done, precisely enough that a
+skilled engineer can build it without asking you anything, without
+prescribing HOW:
+
+- **Goal:** one short paragraph naming the deliverable and its role in
+  the feature.
+- **Success criteria:** concrete, checkable behaviors — exact commands
+  to run and what they must show, the cases tests must cover (including
+  failure cases), constraints that bind the implementation.
+- **Notes:** what the engineer needs and cannot discover alone — spec
+  sections to read, files worth reading first, known pitfalls.
+
+The Interfaces block carries the exact names, signatures, and types;
+the success criteria carry the behaviors; the engineer supplies the
+code and the test design. TDD and frequent commits remain required.
+
+## Task Structure
+
+````markdown
+### Task N: [Component Name]
+
+**Files:**
+- Create: `exact/path/to/file.py`
+- Modify: `exact/path/to/existing.py:123-145`
+- Test: `tests/exact/path/to/test.py`
+
+**Interfaces:**
+- Consumes: [what this task uses from earlier tasks — exact signatures]
+- Produces: [what later tasks rely on — exact function names, parameter
+  and return types. A task's implementer sees only their own task; this
+  block is how they learn the names and types neighboring tasks use.]
+
+**Goal:** [one paragraph — the deliverable and its role in the feature]
+
+**Success criteria:**
+- Run: `pytest tests/exact/path/to/test.py -v` — all tests pass; tests
+  cover [the specific behaviors and failure cases, named concretely]
+- [observable behavior the deliverable must exhibit, with the exact
+  command or input/output that demonstrates it]
+- [constraint that binds the implementation, copied from the spec]
+
+**Notes:** [spec sections to read; files to read first; known pitfalls]
+
+**Tier:** mechanical | judgment. Mechanical = the deliverable is fully
+specified by Files + Interfaces + success criteria above (most tasks in
+a well-specified plan are mechanical); judgment = multi-file
+coordination, debugging, or real design latitude remains. The
+implementer's model follows this field — mark it deliberately.
+
+**Commit:** one commit ending the task; message named here.
+````
+
+## No Vague Contracts
+
+Every contract must be checkable by someone who did not write it. These
+are **plan failures** — never write them:
+- "TBD", "TODO", "implement later", "fill in details"
+- Goals naming activity instead of a deliverable ("improve error handling")
+- Success criteria with no observable check ("works correctly", "handles edge cases")
+- Interfaces blocks omitting a name, signature, or type another task consumes
+- "Similar to Task N" (state this task's own contract in full — the engineer may be reading tasks out of order)
+- References to types, functions, or methods not defined in any task's Interfaces block
+
+## Self-Review
+
+Run SKILL.md's Self-Review checklist, reading step 2 against "No Vague
+Contracts" above rather than "No Placeholders".
+
+## Red Flags
+
+| Thought | Reality |
+|---------|---------|
+| "Task 1 is the data loader — that's the foundation" | A foundation is a layer. The skeleton runs real input to real output through every subsystem the spec names, thinly. |
+| "The skeleton can return a hardcoded value for now" | It may be thin, but the path must be real: real input, real wiring, real output. A hardcoded response tests nothing end to end. |
+| "A contract without the code is vague" | Vague is an uncheckable success criterion. Exact names, exact commands, exact expected output — no code. |
+| "I'll write the test code into the task to be safe" | The success criteria name the cases; the implementer designs the tests. Written-out tests are the task-by-task shape. |
+| "Skeleton-first is the better shape, so I'll use it here" | It costs total wall clock. Without more than one subsystem and a reason to want an early running slice, plan task-by-task. |

skills/writing-skills/render-graphs.js

@@ -13,9 +13,9 @@
  * Requires: graphviz (dot) installed on system
  */
 
-const fs = require('fs');
-const path = require('path');
-const { execSync } = require('child_process');
+import * as fs from 'fs';
+import * as path from 'path';
+import { execFileSync } from 'child_process';
 
 function extractDotBlocks(markdown) {
   const blocks = [];
@@ -69,7 +69,7 @@ ${bodies.join('\n\n')}
 
 function renderToSvg(dotContent) {
   try {
-    return execSync('dot -Tsvg', {
+    return execFileSync('dot', ['-Tsvg'], {
       input: dotContent,
       encoding: 'utf-8',
       maxBuffer: 10 * 1024 * 1024
@@ -107,9 +107,10 @@ function main() {
     process.exit(1);
   }
 
-  // Check if dot is available
+  // Check if dot is available. Run the binary directly rather than probing
+  // with `which`, which is not a command on Windows.
   try {
-    execSync('which dot', { encoding: 'utf-8' });
+    execFileSync('dot', ['-V'], { stdio: 'ignore' });
   } catch {
     console.error('Error: graphviz (dot) not found. Install with:');
     console.error('  brew install graphviz    # macOS');

tests/codex/test-marketplace-manifest.sh

@@ -52,37 +52,25 @@ if not plugin_manifest.exists():
 manifest = json.loads(plugin_manifest.read_text(encoding="utf-8"))
 assert_equal(manifest.get("name"), plugin.get("name"), "plugin manifest name")
 
-# The Codex manifest must declare its hooks explicitly. An absent field makes
-# load_plugin_hooks fall back to a hardcoded DEFAULT_HOOKS_CONFIG_FILE =
-# "hooks/hooks.json" — the Claude Code SessionStart hook, which injects the
-# bootstrap at startup and must not run on Codex. The explicit pointer both
-# registers the Codex compaction re-injection hook and overrides that fallback.
+# Codex auto-discovers a plugin's hooks/hooks.json whenever the Codex manifest
+# has no `hooks` field: load_plugin_hooks falls back to a hardcoded
+# DEFAULT_HOOKS_CONFIG_FILE = "hooks/hooks.json" and registers it. That file is
+# the Claude Code SessionStart hook, it is tracked in this repo, and this
+# marketplace installs the whole repo root (source url "./"), so on Codex the
+# fallback re-registers the SessionStart hook and its install-time trust prompt.
+# Declaring an empty inline hooks object ({}) parses as an empty inline hook set
+# and suppresses the auto-discovery. An absent field, an empty array ([]), and
+# an empty inline list all collapse back to the fallback, so the value must be
+# exactly an empty object.
 hooks_config = repo_root / "hooks" / "hooks.json"
 if not hooks_config.exists():
     raise AssertionError("hooks/hooks.json must exist (Claude Code SessionStart hook)")
 
 assert_equal(
     manifest.get("hooks"),
-    "./hooks/hooks-codex.json",
-    "Codex manifest must point hooks at the Codex hook config (an absent field "
-    "falls back to auto-discovering the Claude Code hooks/hooks.json)",
+    {},
+    "Codex manifest must declare empty hooks {} to suppress hooks/hooks.json auto-discovery",
 )
 
-codex_hooks_path = repo_root / "hooks" / "hooks-codex.json"
-if not codex_hooks_path.exists():
-    raise AssertionError("hooks/hooks-codex.json must exist (Codex manifest points at it)")
-
-codex_hooks = json.loads(codex_hooks_path.read_text(encoding="utf-8"))
-session_start = codex_hooks["hooks"]["SessionStart"]
-assert_equal(len(session_start), 1, "Codex SessionStart hook group count")
-assert_equal(session_start[0].get("matcher"), "compact", "Codex hook matcher")
-entry = session_start[0]["hooks"][0]
-assert_equal(entry.get("type"), "command", "Codex hook type")
-command = entry.get("command", "")
-if "${PLUGIN_ROOT}" not in command or not command.endswith("session-start-codex"):
-    raise AssertionError(
-        f"Codex hook command must run session-start-codex via ${{PLUGIN_ROOT}}: {command!r}"
-    )
-
 print("Codex marketplace manifest looks good")
 PY

tests/codex/test-package-codex-plugin.sh

@@ -141,7 +141,7 @@ tar_extracted="$TEST_ROOT/tar-extracted"
 write_metadata_fixture "$metadata_source"
 
 source_hooks="$(python3 -c 'import json; print(json.load(open("'"$REPO_ROOT"'/.codex-plugin/plugin.json")).get("hooks"))')"
-assert_equals "$source_hooks" "./hooks/hooks-codex.json" "source Codex manifest declares the Codex hook config"
+assert_equals "$source_hooks" "{}" "source Codex manifest suppresses local hook auto-discovery"
 
 if output="$("$SCRIPT_UNDER_TEST" --allow-dirty --metadata-source "$metadata_source" --output "$archive" 2>&1)"; then
   pass "package script exits successfully"
@@ -163,13 +163,10 @@ assert_contains "$output" "SHA-256:" "reports archive checksum"
 extract_archive "$archive" "$extracted"
 
 archive_paths="$(list_archive "$archive" | normalize_archive_paths)"
-unexpected_pattern='(^superpowers/|^\.agents/|^hooks/hooks\.json$|^hooks/hooks-cursor\.json$|^hooks/session-start$|package\.json$|^\.git|^\.pytest_cache|^\.ruff_cache|^scripts/|^tests/|^docs/|^evals/|^lib/|^\.claude|^\.cursor|^\.kimi|^\.opencode|^\.pi|^AGENTS\.md$|^CLAUDE\.md$|^GEMINI\.md$|^RELEASE-NOTES\.md$|^CHANGELOG\.md$)'
+unexpected_pattern='(^superpowers/|^\.agents/|^hooks/|package\.json$|^\.git|^\.pytest_cache|^\.ruff_cache|^scripts/|^tests/|^docs/|^evals/|^lib/|^\.claude|^\.cursor|^\.kimi|^\.opencode|^\.pi|^AGENTS\.md$|^CLAUDE\.md$|^GEMINI\.md$|^RELEASE-NOTES\.md$|^CHANGELOG\.md$)'
 assert_not_matches "$archive_paths" "$unexpected_pattern" "archive excludes source-only paths"
 assert_contains "$archive_paths" ".codex-plugin/plugin.json" "archive includes Codex manifest"
 assert_contains "$archive_paths" "skills/brainstorming/SKILL.md" "archive includes skills"
-assert_contains "$archive_paths" "hooks/hooks-codex.json" "archive includes Codex hook config"
-assert_contains "$archive_paths" "hooks/session-start-codex" "archive includes Codex hook script"
-assert_contains "$archive_paths" "hooks/run-hook.cmd" "archive includes hook runner"
 assert_contains "$archive_paths" "skills/brainstorming/agents/openai.yaml" "archive includes OpenAI skill metadata"
 assert_contains "$archive_paths" "assets/app-icon.png" "archive includes app icon"
 assert_contains "$archive_paths" "assets/superpowers-small.svg" "archive includes composer icon"

tests/devin/test-devin-plugin.sh

@@ -0,0 +1,63 @@
+#!/usr/bin/env bash
+# Validate the Devin CLI integration. `devin plugins install obra/superpowers`
+# reads `.devin-plugin/plugin.json` and auto-discovers the co-located `skills/`
+# directory; Devin CLI surfaces every installed skill's name + description in
+# the system prompt at session start and invokes them via its native `skill`
+# tool, and its system prompt already documents its own tools (subagent
+# profiles, todo tracking, question prompts), so there is no hook, injector,
+# or tool-mapping scaffold to test. What IS Devin-specific is the manifest.
+#
+# Mirrors tests/kimi/test-plugin-manifest.sh. CI-safe: does not require
+# `devin` installed.
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+MANIFEST="$REPO_ROOT/.devin-plugin/plugin.json"
+
+fail() { echo "FAIL: $*" >&2; exit 1; }
+
+echo "test-devin-plugin: checking Devin CLI manifest"
+
+# --- Manifest is valid and matches the repo version -------------------------
+[ -f "$MANIFEST" ] || fail "manifest missing at $MANIFEST"
+
+python3 - "$MANIFEST" <<'PY'
+import json
+import sys
+from pathlib import Path
+
+manifest_path = Path(sys.argv[1])
+manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
+repo_root = manifest_path.parents[1]
+
+if manifest.get("name") != "superpowers":
+    raise AssertionError(f"plugin name: expected 'superpowers', got {manifest.get('name')!r}")
+
+package = json.loads((repo_root / "package.json").read_text(encoding="utf-8"))
+if manifest.get("version") != package.get("version"):
+    raise AssertionError(
+        f"manifest version {manifest.get('version')!r} != package.json version {package.get('version')!r}"
+    )
+
+# Devin CLI plugins carry skills only (auto-discovered from ./skills/); the
+# manifest supports metadata + dependency lists, nothing executable.
+unsupported = ["skills", "hooks", "commands", "sessionStart", "contextFileName", "inject"]
+present = sorted(field for field in unsupported if field in manifest)
+if present:
+    raise AssertionError("unsupported Devin manifest fields present: " + ", ".join(present))
+
+version_config = json.loads((repo_root / ".version-bump.json").read_text(encoding="utf-8"))
+entries = version_config.get("files")
+if not isinstance(entries, list) or not any(
+    entry.get("path") == ".devin-plugin/plugin.json" and entry.get("field") == "version"
+    for entry in entries
+    if isinstance(entry, dict)
+):
+    raise AssertionError(".version-bump.json must update .devin-plugin/plugin.json version")
+
+print("Devin plugin manifest looks good")
+PY
+
+echo "PASS: Devin CLI plugin valid (manifest)"

tests/hermes/conftest.py

@@ -0,0 +1,30 @@
+from pathlib import Path
+
+import pytest
+from unittest.mock import MagicMock
+
+
+@pytest.fixture
+def mock_ctx():
+    ctx = MagicMock()
+    ctx._hooks = {}
+    ctx._skills = {}
+
+    def register_hook(event, fn):
+        ctx._hooks[event] = fn
+
+    def register_skill(name, path):
+        # Mimic hermes' real register_skill, which calls path.exists() and
+        # therefore breaks on a str (the bug that silently disabled the whole
+        # plugin, found 2026-07-23). Keeping that fidelity here means a
+        # regression to str paths fails these tests instead of failing
+        # silently inside hermes.
+        if not isinstance(path, Path):
+            raise AttributeError(
+                f"register_skill requires a pathlib.Path, got {type(path).__name__}"
+            )
+        ctx._skills[name] = path
+
+    ctx.register_hook.side_effect = register_hook
+    ctx.register_skill.side_effect = register_skill
+    return ctx

tests/hermes/test_bootstrap.py

@@ -0,0 +1,98 @@
+import importlib
+import os
+import sys
+
+import pytest
+
+sys.path.insert(0, os.path.abspath(
+    os.path.join(os.path.dirname(__file__), "../../.hermes-plugin")
+))
+
+BOOTSTRAP_MARKER = "superpowers:using-superpowers bootstrap for hermes"
+
+# Hermes spills injected context over 10,000 chars to a file, which breaks
+# inline injection semantics. The bootstrap must stay under it with margin.
+HERMES_CONTEXT_SPILL_LIMIT = 10_000
+
+
+def _load():
+    if "__init__" in sys.modules:
+        del sys.modules["__init__"]
+    return importlib.import_module("__init__")
+
+
+def _bootstrap():
+    m = _load()
+    return m._build_bootstrap(m._skills_dir())
+
+
+class TestStripFrontmatter:
+    def test_strips_yaml_block(self):
+        m = _load()
+        content = "---\nname: foo\ndescription: bar\n---\n# Body\nContent here"
+        assert m._strip_frontmatter(content) == "# Body\nContent here"
+
+    def test_no_frontmatter_returns_trimmed_content(self):
+        m = _load()
+        content = "# No frontmatter\nJust content"
+        assert m._strip_frontmatter(content) == "# No frontmatter\nJust content"
+
+    def test_strips_surrounding_whitespace_from_body(self):
+        m = _load()
+        content = "---\nname: foo\n---\n\n\n# Body\n\n"
+        assert m._strip_frontmatter(content) == "# Body"
+
+
+class TestSkillsDirResolution:
+    def test_repo_layout_resolves(self):
+        # The repo checkout IS the git-clone layout: .hermes-plugin/ and
+        # skills/ are siblings, so resolution must succeed from here.
+        m = _load()
+        skills = m._skills_dir()
+        assert os.path.isfile(
+            os.path.join(skills, "using-superpowers", "SKILL.md")
+        )
+
+
+class TestBootstrapContent:
+    def test_marker_and_wrapper(self):
+        content = _bootstrap()
+        assert BOOTSTRAP_MARKER in content
+        assert content.startswith("<EXTREMELY_IMPORTANT>")
+        assert content.rstrip().endswith("</EXTREMELY_IMPORTANT>")
+
+    def test_contains_using_superpowers_body(self):
+        content = _bootstrap()
+        # A distinctive line from the skill body proves the real SKILL.md was
+        # embedded, not a stub.
+        assert "You have superpowers" in content
+        assert "## The Rule" in content
+
+    def test_frontmatter_stripped(self):
+        content = _bootstrap()
+        assert "---\nname:" not in content
+
+    def test_tool_mapping_sourced_from_reference_file(self):
+        m = _load()
+        content = _bootstrap()
+        ref = os.path.join(
+            m._skills_dir(), "using-superpowers", "references", "hermes-tools.md"
+        )
+        with open(ref, encoding="utf-8") as f:
+            ref_text = f.read().strip()
+        # The mapping is included verbatim from the reference file — the
+        # single source, not a drift-prone inline copy.
+        assert ref_text in content
+        assert "read_file" in content
+
+    def test_skill_view_guidance_present(self):
+        content = _bootstrap()
+        assert 'skill_view("superpowers:brainstorming")' in content
+
+    def test_under_hermes_context_spill_limit(self):
+        content = _bootstrap()
+        assert len(content) < HERMES_CONTEXT_SPILL_LIMIT, (
+            f"bootstrap is {len(content)} chars; hermes spills injected "
+            f"context over {HERMES_CONTEXT_SPILL_LIMIT} to a file, which "
+            "breaks inline injection"
+        )

tests/hermes/test_plugin.py

@@ -0,0 +1,142 @@
+import importlib
+import importlib.util
+import os
+import shutil
+import sys
+from pathlib import Path
+
+import pytest
+
+# Point at the plugin directory
+_PLUGIN_DIR = os.path.abspath(
+    os.path.join(os.path.dirname(__file__), "../../.hermes-plugin")
+)
+sys.path.insert(0, _PLUGIN_DIR)
+
+BOOTSTRAP_MARKER = "superpowers:using-superpowers bootstrap for hermes"
+
+
+def _load_plugin():
+    """Re-import plugin module fresh."""
+    if "__init__" in sys.modules:
+        del sys.modules["__init__"]
+    return importlib.import_module("__init__")
+
+
+def _fire_pre_llm(ctx, **kwargs):
+    hook = ctx._hooks["pre_llm_call"]
+    defaults = {
+        "session_id": "s1",
+        "user_message": "hi",
+        "conversation_history": [],
+        "is_first_turn": False,
+        "model": "test-model",
+        "platform": "cli",
+    }
+    defaults.update(kwargs)
+    return hook(**defaults)
+
+
+class TestPluginRegistration:
+    def test_register_attaches_only_pre_llm_call_hook(self, mock_ctx):
+        plugin = _load_plugin()
+        plugin.register(mock_ctx)
+        assert list(mock_ctx._hooks.keys()) == ["pre_llm_call"]
+
+    def test_register_registers_every_stock_skill_as_path(self, mock_ctx):
+        plugin = _load_plugin()
+        plugin.register(mock_ctx)
+        # The conftest mock raises on non-Path (mirroring hermes' real
+        # register_skill), so reaching these asserts proves every
+        # registration passed a pathlib.Path.
+        assert "using-superpowers" in mock_ctx._skills
+        assert "brainstorming" in mock_ctx._skills
+        for name, path in mock_ctx._skills.items():
+            assert isinstance(path, Path)
+            assert path.name == "SKILL.md"
+            assert path.parent.name == name
+            assert path.is_file()
+
+    def test_registered_skills_match_skill_directories(self, mock_ctx):
+        plugin = _load_plugin()
+        plugin.register(mock_ctx)
+        skills_root = plugin._skills_dir()
+        expected = {
+            entry
+            for entry in os.listdir(skills_root)
+            if os.path.isfile(os.path.join(skills_root, entry, "SKILL.md"))
+        }
+        assert set(mock_ctx._skills.keys()) == expected
+
+
+class TestBootstrapInjection:
+    def test_first_turn_returns_bootstrap_context(self, mock_ctx):
+        plugin = _load_plugin()
+        plugin.register(mock_ctx)
+        result = _fire_pre_llm(mock_ctx, is_first_turn=True)
+        assert isinstance(result, dict)
+        content = result["context"]
+        assert BOOTSTRAP_MARKER in content
+        assert content.startswith("<EXTREMELY_IMPORTANT>")
+        assert content.rstrip().endswith("</EXTREMELY_IMPORTANT>")
+
+    def test_later_turns_return_none(self, mock_ctx):
+        plugin = _load_plugin()
+        plugin.register(mock_ctx)
+        assert _fire_pre_llm(mock_ctx, is_first_turn=False) is None
+        assert _fire_pre_llm(mock_ctx, is_first_turn=None) is None
+
+    def test_hook_tolerates_future_kwargs(self, mock_ctx):
+        plugin = _load_plugin()
+        plugin.register(mock_ctx)
+        result = _fire_pre_llm(
+            mock_ctx, is_first_turn=True, telemetry_schema_version=3
+        )
+        assert BOOTSTRAP_MARKER in result["context"]
+
+
+class TestLayoutResolution:
+    def _stage(self, tmp_path, layout):
+        """Copy the plugin module + a minimal skills tree in the given layout."""
+        src_skills = Path(_PLUGIN_DIR).parent / "skills"
+        if layout == "clone":
+            plugdir = tmp_path / "superpowers" / ".hermes-plugin"
+        else:  # flat: module at the plugin dir root, skills nested inside it
+            plugdir = tmp_path / "superpowers"
+        skills = tmp_path / "superpowers" / "skills"
+        plugdir.mkdir(parents=True, exist_ok=True)
+        shutil.copy(Path(_PLUGIN_DIR) / "__init__.py", plugdir / "__init__.py")
+        for skill in ("using-superpowers", "brainstorming"):
+            shutil.copytree(src_skills / skill, skills / skill)
+        return plugdir
+
+    def _load_from(self, plugdir):
+        spec = importlib.util.spec_from_file_location(
+            f"hermes_plugin_test_{plugdir.parent.name}_{plugdir.name}",
+            plugdir / "__init__.py",
+        )
+        mod = importlib.util.module_from_spec(spec)
+        spec.loader.exec_module(mod)
+        return mod
+
+    def test_clone_layout_resolves_sibling_skills(self, tmp_path, mock_ctx):
+        # git-clone install: .hermes-plugin/ and skills/ are siblings.
+        plugdir = self._stage(tmp_path, "clone")
+        mod = self._load_from(plugdir)
+        mod.register(mock_ctx)
+        assert "using-superpowers" in mock_ctx._skills
+
+    def test_flat_layout_resolves_nested_skills(self, tmp_path, mock_ctx):
+        # flattened install: module at the plugin dir root, skills/ inside it.
+        plugdir = self._stage(tmp_path, "flat")
+        mod = self._load_from(plugdir)
+        mod.register(mock_ctx)
+        assert "using-superpowers" in mock_ctx._skills
+
+    def test_missing_skills_raises_loudly(self, tmp_path, mock_ctx):
+        plugdir = tmp_path / "superpowers"
+        plugdir.mkdir(parents=True)
+        shutil.copy(Path(_PLUGIN_DIR) / "__init__.py", plugdir / "__init__.py")
+        mod = self._load_from(plugdir)
+        with pytest.raises(RuntimeError, match="cannot find the skills"):
+            mod.register(mock_ctx)

tests/hooks/test-session-start-codex.sh

@@ -1,115 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
-HOOK_UNDER_TEST="$REPO_ROOT/hooks/session-start-codex"
-CONFIG_UNDER_TEST="$REPO_ROOT/hooks/hooks-codex.json"
-
-FAILURES=0
-
-pass() {
-    echo "  [PASS] $1"
-}
-
-fail() {
-    echo "  [FAIL] $1"
-    FAILURES=$((FAILURES + 1))
-}
-
-# run_hook <stdin-payload> — echoes hook stdout; fails the calling test on
-# non-zero exit. env -i mirrors the codex hook executor's clean environment.
-run_hook() {
-    printf '%s' "$1" | env -i PATH="${PATH:-}" bash "$HOOK_UNDER_TEST"
-}
-
-echo "Codex SessionStart hook tests"
-
-startup_payload='{"session_id":"s","hook_event_name":"SessionStart","model":"gpt-5.6-terra","source":"startup"}'
-if output="$(run_hook "$startup_payload")" && [ -z "$output" ]; then
-    pass "source=startup emits nothing and exits 0"
-else
-    fail "source=startup emits nothing and exits 0"
-    printf '%s\n' "$output" | head -3 | sed 's/^/    /'
-fi
-
-compact_payload='{"session_id":"s","hook_event_name":"SessionStart","model":"gpt-5.6-terra","source":"compact"}'
-if output="$(run_hook "$compact_payload")"; then
-    ok=1
-    for needle in \
-        "<EXTREMELY_IMPORTANT>" \
-        "You have superpowers." \
-        "name: using-superpowers" \
-        "<CONTEXT_RESTORED>" \
-        "subagent-driven-development/SKILL.md" \
-        "references/codex-tools.md"; do
-        if [[ "$output" != *"$needle"* ]]; then
-            ok=0
-            echo "    missing: $needle"
-        fi
-    done
-    if [ "$ok" -eq 1 ]; then
-        pass "source=compact emits bootstrap plus re-read addendum"
-    else
-        fail "source=compact emits bootstrap plus re-read addendum"
-    fi
-else
-    fail "source=compact emits bootstrap plus re-read addendum (hook exited non-zero)"
-fi
-
-# Whitespace-tolerant source matching (serializers vary).
-spaced_payload='{"hook_event_name":"SessionStart", "source" : "compact"}'
-if output="$(run_hook "$spaced_payload")" && [[ "$output" == *"<CONTEXT_RESTORED>"* ]]; then
-    pass "whitespace around the source key still triggers injection"
-else
-    fail "whitespace around the source key still triggers injection"
-fi
-
-if output="$(printf '' | env -i PATH="${PATH:-}" bash "$HOOK_UNDER_TEST")" && [ -z "$output" ]; then
-    pass "empty stdin fails open to no output, exit 0"
-else
-    fail "empty stdin fails open to no output, exit 0"
-fi
-
-if output="$(run_hook 'not json at all {{{')" && [ -z "$output" ]; then
-    pass "garbage stdin fails open to no output, exit 0"
-else
-    fail "garbage stdin fails open to no output, exit 0"
-fi
-
-# A compact mention inside some other field must not trigger injection.
-decoy_payload='{"hook_event_name":"SessionStart","source":"startup","cwd":"/tmp/compact"}'
-if output="$(run_hook "$decoy_payload")" && [ -z "$output" ]; then
-    pass "compact appearing outside the source field does not trigger"
-else
-    fail "compact appearing outside the source field does not trigger"
-fi
-
-if node -e '
-const config = JSON.parse(require("fs").readFileSync(process.argv[1], "utf8"));
-const group = config.hooks.SessionStart[0];
-if (group.matcher !== "compact") {
-  console.error(`hook matcher is ${JSON.stringify(group.matcher)}, expected "compact"`);
-  process.exit(1);
-}
-const entry = group.hooks[0];
-if (entry.type !== "command") {
-  console.error(`hook type is ${JSON.stringify(entry.type)}, expected "command"`);
-  process.exit(1);
-}
-if (!entry.command.includes("${PLUGIN_ROOT}") || !/run-hook\.cmd" session-start-codex$/.test(entry.command)) {
-  console.error(`unexpected command shape: ${entry.command}`);
-  process.exit(1);
-}
-' "$CONFIG_UNDER_TEST"; then
-    pass "hooks-codex.json runs session-start-codex via \${PLUGIN_ROOT} on compact"
-else
-    fail "hooks-codex.json runs session-start-codex via \${PLUGIN_ROOT} on compact"
-fi
-
-if [[ "$FAILURES" -gt 0 ]]; then
-    echo "STATUS: FAILED ($FAILURES failure(s))"
-    exit 1
-fi
-
-echo "STATUS: PASSED"

tests/version-bump/test-bump-version.sh

@@ -0,0 +1,76 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+SCRIPT_SOURCE="$REPO_ROOT/scripts/bump-version.sh"
+TEST_ROOT="$(mktemp -d)"
+
+cleanup() {
+  rm -rf "$TEST_ROOT"
+}
+trap cleanup EXIT
+
+fail() {
+  echo "FAIL: $*" >&2
+  exit 1
+}
+
+make_fixture() {
+  local repo="$1"
+  local yaml_body="$2"
+
+  mkdir -p "$repo/scripts" "$repo/.hermes-plugin"
+  cp "$SCRIPT_SOURCE" "$repo/scripts/bump-version.sh"
+  cat >"$repo/.version-bump.json" <<'JSON'
+{
+  "files": [
+    { "path": "package.json", "field": "version" },
+    { "path": ".hermes-plugin/plugin.yaml", "field": "version" }
+  ],
+  "audit": { "exclude": [] }
+}
+JSON
+  cat >"$repo/package.json" <<'JSON'
+{
+  "name": "fixture",
+  "version": "1.2.3"
+}
+JSON
+  printf '%s\n' "$yaml_body" >"$repo/.hermes-plugin/plugin.yaml"
+}
+
+happy_repo="$TEST_ROOT/happy"
+make_fixture "$happy_repo" $'name: superpowers\nversion: 1.2.3'
+
+/bin/bash "$happy_repo/scripts/bump-version.sh" --check >"$TEST_ROOT/check.out"
+/bin/bash "$happy_repo/scripts/bump-version.sh" --audit >"$TEST_ROOT/audit.out"
+/bin/bash "$happy_repo/scripts/bump-version.sh" 2.3.4 >"$TEST_ROOT/bump.out"
+
+[[ "$(jq -r '.version' "$happy_repo/package.json")" == "2.3.4" ]] \
+  || fail "JSON manifest was not bumped"
+[[ "$(yq -r '.version' "$happy_repo/.hermes-plugin/plugin.yaml")" == "2.3.4" ]] \
+  || fail "YAML manifest was not bumped"
+
+jq -e '
+  any(.files[];
+    .path == ".hermes-plugin/plugin.yaml" and .field == "version")
+' "$REPO_ROOT/.version-bump.json" >/dev/null \
+  || fail "Hermes manifest is not registered"
+
+invalid_repo="$TEST_ROOT/invalid"
+make_fixture "$invalid_repo" $'name: superpowers\nversion: 123'
+cp "$invalid_repo/package.json" "$TEST_ROOT/package.before"
+cp "$invalid_repo/.hermes-plugin/plugin.yaml" "$TEST_ROOT/plugin.before"
+
+if /bin/bash "$invalid_repo/scripts/bump-version.sh" 2.3.4 \
+  >"$TEST_ROOT/invalid.out" 2>&1; then
+  fail "bump accepted a non-string YAML version"
+fi
+
+cmp -s "$TEST_ROOT/package.before" "$invalid_repo/package.json" \
+  || fail "JSON manifest changed before YAML validation failed"
+cmp -s "$TEST_ROOT/plugin.before" "$invalid_repo/.hermes-plugin/plugin.yaml" \
+  || fail "invalid YAML manifest changed"
+
+echo "Version-bump tests passed"

tests/writing-skills/test-render-graphs.sh

@@ -0,0 +1,113 @@
+#!/usr/bin/env bash
+set -u
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+SCRIPT_UNDER_TEST="$REPO_ROOT/skills/writing-skills/render-graphs.js"
+NODE_BIN="$(command -v node)"
+
+PASSES=0
+FAILURES=0
+TEST_ROOT="$(mktemp -d)"
+
+cleanup() {
+  rm -rf "$TEST_ROOT"
+}
+trap cleanup EXIT
+
+pass() {
+  echo "  [PASS] $1"
+  PASSES=$((PASSES + 1))
+}
+
+fail() {
+  echo "  [FAIL] $1"
+  FAILURES=$((FAILURES + 1))
+}
+
+assert_contains() {
+  local haystack="$1"
+  local needle="$2"
+  local description="$3"
+
+  if printf '%s' "$haystack" | grep -Fq -- "$needle"; then
+    pass "$description"
+  else
+    fail "$description"
+    echo "    expected to find: $needle"
+  fi
+}
+
+assert_not_contains() {
+  local haystack="$1"
+  local needle="$2"
+  local description="$3"
+
+  if printf '%s' "$haystack" | grep -Fq -- "$needle"; then
+    fail "$description"
+    echo "    did not expect to find: $needle"
+  else
+    pass "$description"
+  fi
+}
+
+fixture="$TEST_ROOT/fixture-skill"
+mkdir -p "$fixture" "$TEST_ROOT/empty-path"
+cat >"$fixture/SKILL.md" <<'EOF'
+---
+name: fixture-skill
+---
+
+# Fixture Skill
+
+```dot
+digraph fixture_graph {
+  start -> end;
+}
+```
+EOF
+
+echo "Writing-skills render-graphs tests"
+
+missing_dot_output="$(PATH="$TEST_ROOT/empty-path" "$NODE_BIN" "$SCRIPT_UNDER_TEST" "$fixture" 2>&1)"
+missing_dot_status=$?
+
+if [[ "$missing_dot_status" -ne 0 ]]; then
+  pass "missing Graphviz exits non-zero"
+else
+  fail "missing Graphviz exits non-zero"
+fi
+assert_contains "$missing_dot_output" "Error: graphviz (dot) not found." "missing Graphviz reports install guidance"
+assert_not_contains "$missing_dot_output" "ReferenceError: require is not defined" "script runs as an ES module"
+
+render_output="$("$NODE_BIN" "$SCRIPT_UNDER_TEST" "$fixture" 2>&1)"
+render_status=$?
+
+if [[ "$render_status" -eq 0 ]]; then
+  pass "fixture diagram renders"
+else
+  fail "fixture diagram renders"
+  printf '%s\n' "$render_output"
+fi
+
+assert_contains "$render_output" "Found 1 diagram(s)" "reports discovered diagram"
+assert_contains "$render_output" "Rendered: fixture_graph.svg" "reports rendered SVG"
+
+if [[ -f "$fixture/diagrams/fixture_graph.svg" ]]; then
+  pass "writes SVG output"
+else
+  fail "writes SVG output"
+fi
+
+if [[ -f "$fixture/diagrams/fixture_graph.svg" ]] && grep -Fq "<svg" "$fixture/diagrams/fixture_graph.svg"; then
+  pass "SVG output has SVG markup"
+else
+  fail "SVG output has SVG markup"
+fi
+
+echo
+echo "Results: $PASSES passed, $FAILURES failed"
+
+if [[ "$FAILURES" -gt 0 ]]; then
+  exit 1
+fi