refactor(skills): drop Why Order Matters narrative from test-driven-development

The section's five prose rebuttals each map to a Common Rationalizations
row (test-after, manual-tested, sunk-cost, dogmatic, spirit-not-ritual),
and every excuse phrasing also appears in the Red Flags list. This is the
highest-stakes cut on the branch: TDD is the most pressure-tested
discipline skill, and the bet that the table alone holds under pressure
is exactly what the eval pass must decide.

.agents/plugins/marketplace.json

@@ -0,0 +1,20 @@
+{
+  "name": "superpowers-dev",
+  "interface": {
+    "displayName": "Superpowers Dev"
+  },
+  "plugins": [
+    {
+      "name": "superpowers",
+      "source": {
+        "source": "url",
+        "url": "./"
+      },
+      "policy": {
+        "installation": "AVAILABLE",
+        "authentication": "ON_INSTALL"
+      },
+      "category": "Developer Tools"
+    }
+  ]
+}

.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": "6.0.3",
+      "version": "6.1.1",
       "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": "6.0.3",
+  "version": "6.1.1",
   "author": {
     "name": "Jesse Vincent",
     "email": "jesse@fsck.com"

.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.0.3",
+  "version": "6.1.1",
   "description": "An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.",
   "author": {
     "name": "Jesse Vincent",
@@ -21,13 +21,13 @@
     "workflow"
   ],
   "skills": "./skills/",
-  "hooks": "./hooks/hooks-codex.json",
+  "hooks": {},
   "interface": {
     "displayName": "Superpowers",
     "shortDescription": "Planning, TDD, debugging, and delivery workflows for coding agents",
     "longDescription": "Use Superpowers to guide agent work through brainstorming, implementation planning, test-driven development, systematic debugging, parallel execution, code review, and finish-the-branch workflows.",
     "developerName": "Jesse Vincent",
-    "category": "Coding",
+    "category": "Developer Tools",
     "capabilities": [
       "Interactive",
       "Read",

.cursor-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "superpowers",
   "displayName": "Superpowers",
   "description": "Core skills library: TDD, debugging, collaboration patterns, and proven techniques",
-  "version": "6.0.3",
+  "version": "6.1.1",
   "author": {
     "name": "Jesse Vincent",
     "email": "jesse@fsck.com"

.kimi-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.0.3",
+  "version": "6.1.1",
   "description": "An agentic skills framework and software development methodology.",
   "author": {
     "name": "Jesse Vincent",

CLAUDE.md

@@ -101,7 +101,7 @@ Skills are not prose — they are code that shapes agent behavior. If you modify
 
 ## Eval harness
 
-Skill-behavior evals live in [superpowers-evals](https://github.com/prime-radiant-inc/superpowers-evals/), cloned into `evals/` — see `evals/README.md` for setup. Drill (the harness) drives real tmux sessions of Claude Code / Codex / Gemini CLI and judges skill compliance with an LLM verifier. Plugin-infrastructure tests still live at `tests/`.
+Skill-behavior evals live in [superpowers-evals](https://github.com/prime-radiant-inc/superpowers-evals/), cloned into `evals/` — see `evals/README.md` for setup. The harness drives real tmux sessions of Claude Code / Codex and judges skill compliance with an LLM verifier. Plugin-infrastructure tests still live at `tests/`.
 
 ## Understand the Project Before Contributing
 

README.md

@@ -11,7 +11,7 @@ If this sounds like someone you know, definitely send them our way.
 
 ## 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).
+Give your agent Superpowers: [Claude Code](#claude-code), [Antigravity](#antigravity), [Codex App](#codex-app), [Codex CLI](#codex-cli), [Cursor](#cursor), [Factory Droid](#factory-droid), [GitHub Copilot CLI](#github-copilot-cli), [Kimi Code](#kimi-code), [OpenCode](#opencode), [Pi](#pi).
 
 ## How it works
 
@@ -122,20 +122,6 @@ Superpowers is available via the [official Codex plugin marketplace](https://git
   droid plugin install superpowers@superpowers
   ```
 
-### Gemini CLI
-
-- Install the extension:
-
-  ```bash
-  gemini extensions install https://github.com/obra/superpowers
-  ```
-
-- Update later:
-
-  ```bash
-  gemini extensions update superpowers
-  ```
-
 ### GitHub Copilot CLI
 
 - Register the marketplace:

RELEASE-NOTES.md

@@ -1,5 +1,34 @@
 # Superpowers Release Notes
 
+## v6.1.1 (2026-07-02)
+
+### Codex
+
+- **Codex no longer re-registers the Claude SessionStart hook.** v6.1.0 removed the Codex hook config and its manifest `hooks` pointer, meaning to stop Codex from installing a SessionStart hook — but with no `hooks` field, Codex fell back to auto-discovering `hooks/hooks.json`, the Claude Code SessionStart hook that the marketplace ships from the repo root, and re-registered it along with its install-time trust prompt. The Codex manifest now declares an explicit empty hooks object (`hooks: {}`), which Codex reads as "no hooks" instead of reaching the auto-discovery fallback. An absent field, `[]`, and an empty inline list all collapse back to the fallback, so the value has to be exactly `{}`.
+- **Removed orphaned Codex session-start dead code.** `hooks/session-start-codex` had no caller once the Codex hook config was deleted, so it and its redundant test cases are gone. The worked shell-hook example in `docs/porting-to-a-new-harness.md` moves from Codex — now native skill discovery with no session-start hook — to Cursor, a live shell-hook harness, and the stale `hooks-codex.json` pointer in `docs/windows/polyglot-hooks.md` is corrected. The Codex plugin category is also fixed to "Developer Tools".
+
+### Packaging
+
+- **New `package-codex-plugin.sh` for building the Codex portal package.** A maintainer script produces a deterministic Codex "portal" archive — `.zip` by default, `tar.gz` on request — that normalizes entry timestamps, preserves executable modes, verifies every packaged skill ships its OpenAI metadata, includes the app and composer icons, and refuses to run against a dirty worktree. The packaged manifest keeps the source `hooks: {}` object so a portal-installed plugin avoids the same SessionStart auto-discovery, and the script can rebuild a byte-identical archive from a saved metadata source. Covered by a new test suite.
+
+## v6.1.0 (2026-06-30)
+
+### Lower Per-Session Token Cost
+
+The `using-superpowers` bootstrap is injected into every session, so its size is paid for constantly. This release trims it and the per-harness references it points to, without dropping behavior-shaping content.
+
+- **Compressed the `using-superpowers` bootstrap.** Replaced the graphviz skill-flow diagram with the prose it encoded, folded the standalone Instruction-Priority section into User Instructions, dropped the per-platform "How to Access Skills" walkthrough, and trimmed the Platform Adaptation pointer to the harnesses that still ship a reference file. The full Red Flags rationalization table and the user-instruction precedence rules are unchanged.
+- **Pruned the per-harness tool-mapping references.** The verbose action-to-tool tables restated guidance modern agents already follow. Each reference file is trimmed to the harness-specific notes that still carry weight — subagent dispatch, task tracking, instructions-file paths — and `claude-code-tools.md` and `copilot-tools.md`, which had nothing harness-specific left, are deleted.
+
+### Codex
+
+- **Codex can install from the marketplace.** Codex marketplace sources expect a `.agents/plugins/marketplace.json` at the marketplace root; the repo only shipped the Claude marketplace file, so Codex could name the marketplace but found no installable plugin entries. A repo-local Codex marketplace manifest now points at the same repository root, so the plugin is installable from Codex.
+- **Codex no longer ships a SessionStart hook.** Codex reliably triggers skills on its own, and the bootstrap hook made the UX worse rather than better. The Codex hook config (`hooks-codex.json`) and its manifest registration are removed.
+
+### Harness Support
+
+- **Gemini CLI support removed.** Google EOLed the Gemini CLI on 2026-06-18; the extension can no longer be installed or updated. Gemini is gone from the install docs, the subagent-capable platform lists, and the eval-harness description, and its tool-mapping reference is deleted.
+
 ## v6.0.3 (2026-06-18)
 
 ### Subagent-Driven Development

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

@@ -90,7 +90,7 @@ every session, with no per-session opt-in by your human partner.** This is the
 one non-negotiable capability. It can take any form:
 
 - a **hook/event system** that runs a shell command at session start and reads
-  its stdout (Claude Code, Codex, Cursor, Copilot CLI), or
+  its stdout (Claude Code, Cursor, Copilot CLI), or
 - an **in-process plugin/extension** with a session-start or message lifecycle
   callback that can mutate the message array (OpenCode, pi), or
 - an **instructions-file** convention where the harness loads a context file that
@@ -227,18 +227,20 @@ you may **not** do is bridge a gap by editing the user's global config.
 The harness has a hook system that runs a shell command at session start and
 reads JSON from its stdout. The configured command runs `run-hook.cmd`, a
 polyglot wrapper that just locates bash and dispatches the named script; the
-script (`hooks/session-start`, or a harness-specific variant like
-`hooks/session-start-codex`) is what reads `using-superpowers/SKILL.md` and
-prints a JSON object whose **field name and nesting differ per harness**.
+script (`hooks/session-start`, or a harness-specific variant) is what reads
+`using-superpowers/SKILL.md` and prints a JSON object whose **field name and
+nesting differ per harness**.
 
-- Reference: `hooks/session-start` (and `hooks/session-start-codex`),
-  `hooks/run-hook.cmd`, and the per-harness hook config `hooks/hooks.json`
-  (Claude Code), `hooks/hooks-codex.json` (Codex), `hooks/hooks-cursor.json`
+- Reference: `hooks/session-start`, `hooks/run-hook.cmd`, and the per-harness
+  hook config `hooks/hooks.json` (Claude Code) and `hooks/hooks-cursor.json`
   (Cursor).
-- Manifests: `.codex-plugin/plugin.json`, `.cursor-plugin/plugin.json` point the
-  harness at `./skills/` and the right `hooks-*.json`. (Claude Code's
+- 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.)
+  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
@@ -287,7 +289,7 @@ part of the installed extension** — never substitute "edit the user's global
 
 | If the harness… | Use shape | Copy from |
 |---|---|---|
-| runs a shell command at session start and reads its stdout | A (shell-hook) | Codex (`hooks/session-start-codex` + `hooks/hooks-codex.json` + `.codex-plugin/`) |
+| runs a shell command at session start and reads its stdout | A (shell-hook) | Cursor (`hooks/session-start` + `hooks/hooks-cursor.json` + `.cursor-plugin/`) |
 | is a JS/TS plugin host with session/message lifecycle callbacks | B (in-process) | OpenCode (`.opencode/`) — or pi (`.pi/`) if it has no native skill tool |
 | ships an extension-declared context file it always loads | C (instructions-file) | Gemini (`gemini-extension.json` + `GEMINI.md` + `references/gemini-tools.md`) |
 | has a plugin install command and a manifest `contextFileName` (or equivalent) the installer keeps | C via the plugin installer | Antigravity (`.antigravity-plugin/` — `agy plugin install` ships a generated context file; verify the installer preserves it — Part 6) |
@@ -309,7 +311,7 @@ patterns below are summaries; the code is the spec.
 Create whatever the harness uses to recognize the plugin. Match the existing
 ones in spirit:
 
-- **Shape A:** a `*-plugin/plugin.json` (see `.codex-plugin/plugin.json`) with
+- **Shape A:** a `*-plugin/plugin.json` (see `.cursor-plugin/plugin.json`) with
   `name`, `version`, `description`, author/license/keywords, `"skills":
   "./skills/"`, and `"hooks": "./hooks/hooks-<harness>.json"`. Plus the
   `hooks-<harness>.json` itself, registering a session-start hook whose command
@@ -375,25 +377,24 @@ both double-injects). Find the
 exact field, nesting, and event-matcher values your harness expects. Then
 decide: add a fourth branch to `hooks/session-start`, or — if the harness needs
 a different bootstrap message or env contract — add a dedicated
-`hooks/session-start-<harness>` script, the way Codex did. If you add a branch
+`hooks/session-start-<harness>` script. If you add a branch
 and your harness *also* sets an env var an earlier branch keys on (some harnesses
 set `CLAUDE_PLUGIN_ROOT` too), order your branch before the one that would
 otherwise shadow it. Match the harness's
-own event-matcher strings (Claude Code uses `startup|clear|compact`, Codex
-`startup|resume|clear`, Cursor `sessionStart`); wrong matchers mean the hook
-silently never fires.
+own event-matcher strings (Claude Code uses `startup|clear|compact`, Cursor
+`sessionStart`); wrong matchers mean the hook silently never fires.
 
 The **hook-config schema itself varies per harness** — don't assume the
-Claude/Codex shape is universal. Compare `hooks/hooks.json`,
-`hooks/hooks-codex.json`, and `hooks/hooks-cursor.json`: Cursor's uses
+Claude Code shape is universal. Compare `hooks/hooks.json` and
+`hooks/hooks-cursor.json`: Cursor's uses
 `"version": 1`, a lowercase `sessionStart` key, a relative
-`./hooks/run-hook.cmd` command, and omits the `matcher`/`type`/`async` fields the
-others use. Match your `hooks-<harness>.json` to whichever existing file is
+`./hooks/run-hook.cmd` command, and omits the `matcher`/`type`/`async` fields
+Claude Code uses. Match your `hooks-<harness>.json` to whichever existing file is
 closest, not to a single canonical template.
 
 The hook **command string references a harness-provided plugin-root variable**,
 and its name differs per harness: `hooks.json` uses `${CLAUDE_PLUGIN_ROOT}`,
-`hooks-codex.json` uses `${PLUGIN_ROOT}`, Cursor uses a relative path. Use
+`hooks-cursor.json` uses a relative path. Use
 whatever your harness exports. (The `session-start` script re-derives the root
 itself via `dirname`, so the script body doesn't depend on this — but the
 command in the manifest does.)
@@ -784,7 +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; `references/claude-code-tools.md` | `tests/hooks/` | marketplace |
-| Codex | `.codex-plugin/plugin.json` + `hooks/hooks-codex.json` | shell hook → `hooks/session-start-codex` | `references/codex-tools.md` | `tests/codex-plugin-sync/`, `tests/hooks/` | 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`) | `references/claude-code-tools.md` | `tests/hooks/` | hand-authored |
 | Copilot CLI | (shares Claude Code hook path; `COPILOT_CLI` env) | shell hook → `hooks/session-start` (`additionalContext`) | `references/copilot-tools.md` | `tests/hooks/` | — |
 | Gemini CLI | `gemini-extension.json` + `GEMINI.md` | instructions file `@`-includes bootstrap + mapping | `references/gemini-tools.md` | — | `gemini extensions install` |
@@ -799,10 +800,10 @@ Use this as the live index; when in doubt, read the files, not this table.
 - **Wrong JSON field → silent failure or double injection.** Shape A only.
   Confirm the exact field/nesting; Claude Code reads two fields without dedup.
 - **Hook-config schema varies per harness.** Shape A. Cursor's `hooks-cursor.json`
-  looks nothing like the Claude/Codex one (`version`, lowercase `sessionStart`,
+  looks nothing like the Claude Code one (`version`, lowercase `sessionStart`,
   relative command, no `matcher`/`type`/`async`). Match the closest existing file.
 - **Plugin-root env var differs per harness.** Shape A. The hook command uses
-  `${CLAUDE_PLUGIN_ROOT}` (Claude), `${PLUGIN_ROOT}` (Codex), or a relative path
+  `${CLAUDE_PLUGIN_ROOT}` (Claude) or a relative path
   (Cursor). Use what your harness exports; the script re-derives the root itself.
 - **System-message injection.** Shape B injects a *user* message on purpose
   (#750, #894). Don't "fix" it to a system message.

docs/windows/polyglot-hooks.md

@@ -140,7 +140,7 @@ Check that the script filename is **extensionless** in `hooks.json`. A command l
 
 ### Hook doesn't fire at all
 
-Verify the `matcher` in `hooks.json` matches the event type your harness emits. Claude Code uses `startup|clear|compact`; Codex uses `startup|resume|clear`. Check `hooks-codex.json` for the Codex variant.
+Verify the `matcher` in `hooks.json` matches the event type your harness emits. Claude Code uses `startup|clear|compact`; Cursor uses `sessionStart`. Check `hooks-cursor.json` for the Cursor variant.
 
 ## Related Issues
 

gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
   "description": "Core skills library: TDD, debugging, collaboration patterns, and proven techniques",
-  "version": "6.0.3",
+  "version": "6.1.1",
   "contextFileName": "GEMINI.md"
 }

hooks/hooks-codex.json

@@ -1,16 +0,0 @@
-{
-  "hooks": {
-    "SessionStart": [
-      {
-        "matcher": "startup|resume|clear",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "\"${PLUGIN_ROOT}/hooks/run-hook.cmd\" session-start-codex",
-            "async": false
-          }
-        ]
-      }
-    ]
-  }
-}

hooks/session-start-codex

@@ -1,26 +0,0 @@
-#!/usr/bin/env bash
-# Codex SessionStart hook for superpowers plugin
-
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-PLUGIN_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
-
-using_superpowers_content=$(cat "${PLUGIN_ROOT}/skills/using-superpowers/SKILL.md" 2>&1 || echo "Error reading using-superpowers skill")
-
-escape_for_json() {
-    local s="$1"
-    s="${s//\\/\\\\}"
-    s="${s//\"/\\\"}"
-    s="${s//$'\n'/\\n}"
-    s="${s//$'\r'/\\r}"
-    s="${s//$'\t'/\\t}"
-    printf '%s' "$s"
-}
-
-using_superpowers_escaped=$(escape_for_json "$using_superpowers_content")
-session_context="<EXTREMELY_IMPORTANT>\nYou have superpowers.\n\n**Below is the full content of your 'superpowers:using-superpowers' skill - your introduction to using skills. For all other skills, follow the Codex skill-loading instructions in that skill:**\n\n${using_superpowers_escaped}\n</EXTREMELY_IMPORTANT>"
-
-printf '{\n  "hookSpecificOutput": {\n    "hookEventName": "SessionStart",\n    "additionalContext": "%s"\n  }\n}\n' "$session_context" | cat
-
-exit 0

package.json

@@ -1,6 +1,6 @@
 {
   "name": "superpowers",
-  "version": "6.0.3",
+  "version": "6.1.1",
   "description": "Superpowers skills and runtime bootstrap for coding agents",
   "type": "module",
   "main": ".opencode/plugins/superpowers.js",

scripts/package-codex-plugin.sh

@@ -0,0 +1,342 @@
+#!/usr/bin/env bash
+#
+# Package the Superpowers Codex plugin as a rootless archive for portal upload.
+#
+# The Codex portal artifact differs from the old openai/plugins sync flow:
+# it is a standalone archive, but it still needs the OpenAI-owned
+# skills/*/agents/openai.yaml metadata that used to be preserved from the
+# destination plugin repo. Seed that metadata from a prior official package.
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+REF="HEAD"
+OUTPUT=""
+FORMAT=""
+METADATA_SOURCE=""
+ALLOW_DIRTY=0
+KEEP_STAGE=0
+
+usage() {
+  cat <<'EOF'
+Usage:
+  scripts/package-codex-plugin.sh [options]
+
+Options:
+  --output PATH            Write archive to PATH.
+                           Default: ../_tmp/sup-codex-packaging/superpowers-VERSION.zip
+  --format FORMAT          Archive format: zip or tar.gz. Default: zip.
+                           If --output ends in .zip, .tar.gz, or .tgz, that
+                           extension is used when --format is omitted.
+  --metadata-source PATH   Prior official package directory, .zip, or .tar.gz used to
+                           seed skills/*/agents/openai.yaml.
+                           Default: ../_tmp/sup-codex-packaging/superpowers,
+                           falling back to superpowers.zip, then superpowers.tar.gz
+  --ref REF                Git ref to package. Default: HEAD.
+  --allow-dirty            Permit a dirty working tree. The archive still uses --ref.
+  --keep-stage             Print and keep the temporary staging directory.
+  -h, --help               Show this help.
+
+The archive is rootless: .codex-plugin/, assets/, skills/, README.md, LICENSE,
+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
+}
+
+die() {
+  echo "ERROR: $*" >&2
+  exit 1
+}
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --output)
+      [[ $# -ge 2 ]] || die "--output requires a path"
+      OUTPUT="$2"
+      shift 2
+      ;;
+    --format)
+      [[ $# -ge 2 ]] || die "--format requires a value"
+      case "$2" in
+        zip)
+          FORMAT="zip"
+          ;;
+        tar.gz|tgz)
+          FORMAT="tar.gz"
+          ;;
+        *)
+          die "--format must be zip or tar.gz"
+          ;;
+      esac
+      shift 2
+      ;;
+    --metadata-source)
+      [[ $# -ge 2 ]] || die "--metadata-source requires a path"
+      METADATA_SOURCE="$2"
+      shift 2
+      ;;
+    --ref)
+      [[ $# -ge 2 ]] || die "--ref requires a value"
+      REF="$2"
+      shift 2
+      ;;
+    --allow-dirty)
+      ALLOW_DIRTY=1
+      shift
+      ;;
+    --keep-stage)
+      KEEP_STAGE=1
+      shift
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      echo "Unknown arg: $1" >&2
+      usage >&2
+      exit 2
+      ;;
+  esac
+done
+
+infer_format_from_output() {
+  local output_path="$1"
+
+  case "$output_path" in
+    *.tar.gz|*.tgz)
+      printf '%s\n' "tar.gz"
+      ;;
+    *.zip)
+      printf '%s\n' "zip"
+      ;;
+    *)
+      return 1
+      ;;
+  esac
+}
+
+if [[ -z "$FORMAT" ]]; then
+  FORMAT="$(infer_format_from_output "$OUTPUT" || true)"
+  if [[ -z "$FORMAT" ]]; then
+    FORMAT="zip"
+  fi
+else
+  output_format="$(infer_format_from_output "$OUTPUT" || true)"
+  if [[ -n "$output_format" && "$output_format" != "$FORMAT" ]]; then
+    die "--output extension does not match --format $FORMAT: $OUTPUT"
+  fi
+fi
+
+command -v git >/dev/null || die "git not found in PATH"
+command -v jq >/dev/null || die "jq not found in PATH"
+command -v tar >/dev/null || die "tar not found in PATH"
+command -v gzip >/dev/null || die "gzip not found in PATH"
+command -v shasum >/dev/null || die "shasum not found in PATH"
+if [[ "$FORMAT" == "zip" ]]; then
+  command -v zip >/dev/null || die "zip not found in PATH"
+  command -v unzip >/dev/null || die "unzip not found in PATH"
+fi
+
+[[ -d "$REPO_ROOT/.git" ]] || die "repo root is not a git checkout: $REPO_ROOT"
+git -C "$REPO_ROOT" rev-parse --verify "$REF^{commit}" >/dev/null ||
+  die "git ref does not resolve to a commit: $REF"
+
+if [[ "$ALLOW_DIRTY" -ne 1 ]]; then
+  dirty_status="$(git -C "$REPO_ROOT" status --porcelain --untracked-files=all)"
+  if [[ -n "$dirty_status" ]]; then
+    echo "Working tree has uncommitted changes:" >&2
+    printf '%s\n' "$dirty_status" | sed 's/^/  /' >&2
+    die "commit or stash changes first, or pass --allow-dirty to package $REF anyway"
+  fi
+fi
+
+if [[ -z "$METADATA_SOURCE" ]]; then
+  if [[ -d "$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers" ]]; then
+    METADATA_SOURCE="$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers"
+  elif [[ -f "$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers.zip" ]]; then
+    METADATA_SOURCE="$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers.zip"
+  elif [[ -f "$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers.tar.gz" ]]; then
+    METADATA_SOURCE="$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers.tar.gz"
+  else
+    die "no metadata source found; pass --metadata-source <prior package dir, zip, or tar.gz>"
+  fi
+fi
+
+WORK_DIR="$(mktemp -d "${TMPDIR:-/tmp}/superpowers-codex-package.XXXXXX")"
+STAGE="$WORK_DIR/payload"
+METADATA_WORK="$WORK_DIR/metadata"
+ARCHIVE_LIST="$WORK_DIR/archive-list"
+
+cleanup() {
+  if [[ "$KEEP_STAGE" -eq 1 ]]; then
+    echo "Keeping staging directory: $WORK_DIR" >&2
+  else
+    rm -rf "$WORK_DIR"
+  fi
+}
+trap cleanup EXIT
+
+mkdir -p "$STAGE" "$METADATA_WORK"
+
+metadata_root_from_dir() {
+  local candidate="$1"
+  local nested
+
+  if [[ -d "$candidate/skills" ]]; then
+    printf '%s\n' "$candidate"
+    return 0
+  fi
+
+  nested="$(find "$candidate" -mindepth 2 -maxdepth 2 -type d -name skills -print -quit)"
+  if [[ -n "$nested" ]]; then
+    dirname "$nested"
+    return 0
+  fi
+
+  return 1
+}
+
+prepare_metadata_root() {
+  local source="$1"
+  local root
+
+  if [[ -d "$source" ]]; then
+    root="$(cd "$source" && pwd)"
+  elif [[ -f "$source" ]]; then
+    case "$source" in
+      *.tar.gz|*.tgz)
+        tar -xzf "$source" -C "$METADATA_WORK"
+        root="$METADATA_WORK"
+        ;;
+      *.zip)
+        command -v unzip >/dev/null || die "unzip not found in PATH"
+        unzip -q "$source" -d "$METADATA_WORK"
+        root="$METADATA_WORK"
+        ;;
+      *)
+        die "metadata source must be a directory, .zip, or .tar.gz: $source"
+        ;;
+    esac
+  else
+    die "metadata source does not exist: $source"
+  fi
+
+  metadata_root_from_dir "$root" ||
+    die "metadata source does not contain a skills/ directory: $source"
+}
+
+METADATA_ROOT="$(prepare_metadata_root "$METADATA_SOURCE")"
+
+git -C "$REPO_ROOT" archive --format=tar "$REF" -- \
+  .codex-plugin \
+  CODE_OF_CONDUCT.md \
+  LICENSE \
+  README.md \
+  assets \
+  skills \
+  | tar -xf - -C "$STAGE"
+
+VERSION="$(jq -r '.version // empty' "$STAGE/.codex-plugin/plugin.json")"
+[[ -n "$VERSION" ]] || die "could not read version from .codex-plugin/plugin.json"
+
+if [[ -z "$OUTPUT" ]]; then
+  case "$FORMAT" in
+    zip)
+      OUTPUT="$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers-$VERSION.zip"
+      ;;
+    tar.gz)
+      OUTPUT="$REPO_ROOT/../_tmp/sup-codex-packaging/superpowers-$VERSION.tar.gz"
+      ;;
+  esac
+fi
+mkdir -p "$(dirname "$OUTPUT")"
+OUTPUT="$(cd "$(dirname "$OUTPUT")" && pwd)/$(basename "$OUTPUT")"
+
+missing_metadata=0
+while IFS= read -r skill_dir; do
+  skill_name="${skill_dir##*/}"
+  metadata_file="$METADATA_ROOT/skills/$skill_name/agents/openai.yaml"
+
+  if [[ ! -f "$metadata_file" ]]; then
+    echo "Missing OpenAI agent metadata for skill: $skill_name" >&2
+    missing_metadata=1
+    continue
+  fi
+
+  mkdir -p "$skill_dir/agents"
+  cp "$metadata_file" "$skill_dir/agents/openai.yaml"
+done < <(find "$STAGE/skills" -mindepth 1 -maxdepth 1 -type d -print | sort)
+
+if [[ "$missing_metadata" -ne 0 ]]; then
+  die "metadata source is incomplete"
+fi
+
+skill_count="$(find "$STAGE/skills" -mindepth 1 -maxdepth 1 -type d | wc -l | tr -d ' ')"
+metadata_count="$(find "$STAGE/skills" -path '*/agents/openai.yaml' -type f | wc -l | tr -d ' ')"
+[[ "$skill_count" == "$metadata_count" ]] ||
+  die "metadata count mismatch: $metadata_count metadata files for $skill_count skills"
+
+(
+  cd "$STAGE"
+  {
+    find . -mindepth 1 -type d | sed 's#^\./##' | LC_ALL=C sort
+    find . -mindepth 1 -type f | sed 's#^\./##' | LC_ALL=C sort
+  } >"$ARCHIVE_LIST"
+)
+
+case "$FORMAT" in
+  zip)
+    # ZIP cannot represent dates earlier than 1980.
+    TZ=UTC find "$STAGE" -exec touch -t 198001010000 {} +
+    (
+      cd "$STAGE"
+      rm -f "$OUTPUT"
+      COPYFILE_DISABLE=1 zip -X -q - -@ <"$ARCHIVE_LIST" >"$OUTPUT"
+    )
+    ;;
+  tar.gz)
+    # Match the prior official archive's deterministic tar entry metadata.
+    TZ=UTC find "$STAGE" -exec touch -t 197001010000 {} +
+    (
+      cd "$STAGE"
+      rm -f "$OUTPUT"
+      COPYFILE_DISABLE=1 tar -cf - --no-recursion --format ustar --uid 0 --gid 0 --uname '' --gname '' -T "$ARCHIVE_LIST" |
+        gzip -9n >"$OUTPUT"
+    )
+    ;;
+esac
+
+if command -v xattr >/dev/null 2>&1; then
+  xattr -c "$OUTPUT" 2>/dev/null || true
+fi
+
+case "$FORMAT" in
+  zip)
+    archive_paths="$(unzip -Z1 "$OUTPUT" | sed 's#/$##')"
+    ;;
+  tar.gz)
+    archive_paths="$(tar -tzf "$OUTPUT")"
+    ;;
+esac
+
+unexpected_paths="$(
+  printf '%s\n' "$archive_paths" |
+    grep -E '(^superpowers/|^\.agents/|^hooks/|package\.json$|^\.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' "$unexpected_paths" | sed 's/^/  /' >&2
+  die "archive contains source-only paths"
+fi
+
+entry_count="$(printf '%s\n' "$archive_paths" | wc -l | tr -d ' ')"
+checksum="$(shasum -a 256 "$OUTPUT" | awk '{print $1}')"
+
+echo "Archive: $OUTPUT"
+echo "Format:  $FORMAT"
+echo "Version: $VERSION"
+echo "Entries: $entry_count"
+echo "Skills:  $skill_count"
+echo "SHA-256: $checksum"

skills/brainstorming/SKILL.md

@@ -77,6 +77,7 @@ digraph brainstorming {
 - Propose 2-3 different approaches with trade-offs
 - Present options conversationally with your recommendation and reasoning
 - Lead with your recommended option and explain why
+- YAGNI ruthlessly - remove unnecessary features from every approach and design
 
 **Presenting the design:**
 
@@ -130,15 +131,6 @@ Wait for the user's response. If they request changes, make them and re-run the
 - Invoke the writing-plans skill to create a detailed implementation plan
 - Do NOT invoke any other skill. writing-plans is the next step.
 
-## Key Principles
-
-- **One question at a time** - Don't overwhelm with multiple questions
-- **Multiple choice preferred** - Easier to answer than open-ended when possible
-- **YAGNI ruthlessly** - Remove unnecessary features from all designs
-- **Explore alternatives** - Always propose 2-3 approaches before settling
-- **Incremental validation** - Present design, get approval before moving on
-- **Be flexible** - Go back and clarify when something doesn't make sense
-
 ## Visual Companion
 
 A browser-based companion for showing mockups, diagrams, and visual options during brainstorming. Available as a tool — not a mode. Accepting the companion means it's available for questions that benefit from visual treatment; it does NOT mean every question goes through the browser.

skills/brainstorming/visual-companion.md

@@ -74,13 +74,6 @@ On Windows, the script auto-detects and switches to foreground mode (which block
 scripts/start-server.sh --project-dir /path/to/project --open
 ```
 
-**Gemini CLI:**
-```bash
-# Use --foreground and set is_background: true on your shell tool call
-# so the process survives across turns
-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"

skills/dispatching-parallel-agents/SKILL.md

@@ -158,15 +158,6 @@ Agent 3 → Fix tool-approval-race-conditions.test.ts
 
 **Integration:** All fixes independent, no conflicts, full suite green
 
-**Time saved:** 3 problems solved in parallel vs sequentially
-
-## Key Benefits
-
-1. **Parallelization** - Multiple investigations happen simultaneously
-2. **Focus** - Each agent has narrow scope, less context to track
-3. **Independence** - Agents don't interfere with each other
-4. **Speed** - 3 problems solved in time of 1
-
 ## Verification
 
 After agents return:
@@ -174,12 +165,3 @@ After agents return:
 2. **Check for conflicts** - Did agents edit same code?
 3. **Run full suite** - Verify all fixes work together
 4. **Spot check** - Agents can make systematic errors
-
-## Real-World Impact
-
-From debugging session (2025-10-03):
-- 6 failures across 3 files
-- 3 agents dispatched in parallel
-- All investigations completed concurrently
-- All fixes integrated successfully
-- Zero conflicts between agent changes

skills/executing-plans/SKILL.md

@@ -11,7 +11,7 @@ Load plan, review critically, execute all tasks, report when complete.
 
 **Announce at start:** "I'm using the executing-plans skill to implement this plan."
 
-**Note:** Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (Claude Code, Codex CLI, Codex App, Copilot CLI, and Gemini CLI all qualify; see the per-platform tool refs in `../using-superpowers/references/`). If subagents are available, use superpowers:subagent-driven-development instead of this skill.
+**Note:** Tell your human partner that Superpowers works much better with access to subagents (Claude Code, Codex CLI, Codex App, and Copilot CLI all qualify; see the per-platform tool refs in `../using-superpowers/references/`). If subagents are available, use superpowers:subagent-driven-development instead of this skill.
 
 ## The Process
 

skills/receiving-code-review/SKILL.md

@@ -203,11 +203,3 @@ You understand 1,2,3,6. Unclear on 4,5.
 ## GitHub Thread Replies
 
 When replying to inline review comments on GitHub, reply in the comment thread (`gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies`), not as a top-level PR comment.
-
-## The Bottom Line
-
-**External feedback = suggestions to evaluate, not orders to follow.**
-
-Verify. Question. Then implement.
-
-No performative agreement. Technical rigor always.

skills/requesting-code-review/SKILL.md

@@ -5,7 +5,7 @@ description: Use when completing tasks, implementing major features, or before m
 
 # Requesting Code Review
 
-Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history. This keeps the reviewer focused on the work product, not your thought process, and preserves your own context for continued work.
+Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history.
 
 **Core principle:** Review early, review often.
 
@@ -72,21 +72,6 @@ You: [Fix progress indicators]
 [Continue to Task 3]
 ```
 
-## Integration with Workflows
-
-**Subagent-Driven Development:**
-- Review after EACH task
-- Catch issues before they compound
-- Fix before moving to next task
-
-**Executing Plans:**
-- Review after each task or at natural checkpoints
-- Get feedback, apply, continue
-
-**Ad-Hoc Development:**
-- Review before merge
-- Review when stuck
-
 ## Red Flags
 
 **Never:**

skills/subagent-driven-development/SKILL.md

@@ -332,38 +332,6 @@ Final reviewer: All requirements met, ready to merge
 Done!
 ```
 
-## Advantages
-
-**vs. Manual execution:**
-- Subagents follow TDD naturally
-- Fresh context per task (no confusion)
-- Parallel-safe (subagents don't interfere)
-- Subagent can ask questions (before AND during work)
-
-**vs. Executing Plans:**
-- Same session (no handoff)
-- Continuous progress (no waiting)
-- Review checkpoints automatic
-
-**Efficiency gains:**
-- Controller curates exactly what context is needed; bulk artifacts move
-  as files, not pasted text
-- Subagent gets complete information upfront
-- Questions surfaced before work begins (not after)
-
-**Quality gates:**
-- Self-review catches issues before handoff
-- Task review carries two verdicts: spec compliance and code quality
-- Review loops ensure fixes actually work
-- Spec compliance prevents over/under-building
-- Code quality ensures implementation is well-built
-
-**Cost:**
-- More subagent invocations (implementer + reviewer per task)
-- Controller does more prep work (extracting all tasks upfront)
-- Review loops add iterations
-- But catches issues early (cheaper than debugging later)
-
 ## Red Flags
 
 **Never:**

skills/systematic-debugging/SKILL.md

@@ -7,8 +7,6 @@ description: Use when encountering any bug, test failure, or unexpected behavior
 
 ## Overview
 
-Random fixes waste time and create new bugs. Quick patches mask underlying issues.
-
 **Core principle:** ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
 
 **Violating the letter of this process is violating the spirit of debugging.**
@@ -286,11 +284,3 @@ These techniques are part of systematic debugging and available in this director
 **Related skills:**
 - **superpowers:test-driven-development** - For creating failing test case (Phase 4, Step 1)
 - **superpowers:verification-before-completion** - Verify fix worked before claiming success
-
-## Real-World Impact
-
-From debugging sessions:
-- Systematic approach: 15-30 minutes to fix
-- Random fixes approach: 2-3 hours of thrashing
-- First-time fix rate: 95% vs 40%
-- New bugs introduced: Near zero vs common

skills/test-driven-development/SKILL.md

@@ -203,56 +203,6 @@ Next failing test for next feature.
 | **Clear** | Name describes behavior | `test('test1')` |
 | **Shows intent** | Demonstrates desired API | Obscures what code should do |
 
-## Why Order Matters
-
-**"I'll write tests after to verify it works"**
-
-Tests written after code pass immediately. Passing immediately proves nothing:
-- Might test wrong thing
-- Might test implementation, not behavior
-- Might miss edge cases you forgot
-- You never saw it catch the bug
-
-Test-first forces you to see the test fail, proving it actually tests something.
-
-**"I already manually tested all the edge cases"**
-
-Manual testing is ad-hoc. You think you tested everything but:
-- No record of what you tested
-- Can't re-run when code changes
-- Easy to forget cases under pressure
-- "It worked when I tried it" ≠ comprehensive
-
-Automated tests are systematic. They run the same way every time.
-
-**"Deleting X hours of work is wasteful"**
-
-Sunk cost fallacy. The time is already gone. Your choice now:
-- Delete and rewrite with TDD (X more hours, high confidence)
-- Keep it and add tests after (30 min, low confidence, likely bugs)
-
-The "waste" is keeping code you can't trust. Working code without real tests is technical debt.
-
-**"TDD is dogmatic, being pragmatic means adapting"**
-
-TDD IS pragmatic:
-- Finds bugs before commit (faster than debugging after)
-- Prevents regressions (tests catch breaks immediately)
-- Documents behavior (tests show how to use code)
-- Enables refactoring (change freely, tests catch breaks)
-
-"Pragmatic" shortcuts = debugging in production = slower.
-
-**"Tests after achieve the same goals - it's spirit not ritual"**
-
-No. Tests-after answer "What does this do?" Tests-first answer "What should this do?"
-
-Tests-after are biased by your implementation. You test what you built, not what's required. You verify remembered edge cases, not discovered ones.
-
-Tests-first force edge case discovery before implementing. Tests-after verify you remembered everything (you didn't).
-
-30 minutes of tests after ≠ TDD. You get coverage, lose proof tests work.
-
 ## Common Rationalizations
 
 | Excuse | Reality |

skills/using-git-worktrees/SKILL.md

@@ -156,47 +156,12 @@ Ready to implement <feature-name>
 | Tests fail during baseline | Report failures + ask |
 | No package.json/Cargo.toml | Skip dependency install |
 
-## Common Mistakes
+## Common Rationalizations
 
-### Fighting the harness
-
-- **Problem:** Using `git worktree add` when the platform already provides isolation
-- **Fix:** Step 0 detects existing isolation. Step 1a defers to native tools.
-
-### Skipping detection
-
-- **Problem:** Creating a nested worktree inside an existing one
-- **Fix:** Always run Step 0 before creating anything
-
-### Skipping ignore verification
-
-- **Problem:** Worktree contents get tracked, pollute git status
-- **Fix:** Always use `git check-ignore` before creating project-local worktree
-
-### Assuming directory location
-
-- **Problem:** Creates inconsistency, violates project conventions
-- **Fix:** Follow priority: explicit instructions > existing project-local directory > default
-
-### Proceeding with failing tests
-
-- **Problem:** Can't distinguish new bugs from pre-existing issues
-- **Fix:** Report failures, get explicit permission to proceed
-
-## Red Flags
-
-**Never:**
-- Create a worktree when Step 0 detects existing isolation
-- Use `git worktree add` when you have a native worktree tool (e.g., `EnterWorktree`). This is the #1 mistake — if you have it, use it.
-- Skip Step 1a by jumping straight to Step 1b's git commands
-- Create worktree without verifying it's ignored (project-local)
-- Skip baseline test verification
-- Proceed with failing tests without asking
-
-**Always:**
-- Run Step 0 detection first
-- Prefer native tools over git fallback
-- Follow directory priority: explicit instructions > existing project-local directory > default
-- Verify directory is ignored for project-local
-- Auto-detect and run project setup
-- Verify clean test baseline
+| Excuse | Reality |
+|--------|---------|
+| "I'm obviously not in a worktree — no need to check" | Run Step 0. Harness-created isolation and submodules both fool eyeballing; the detection commands settle it. |
+| "`git worktree add` is quicker than hunting for a native tool" | A native tool (e.g. `EnterWorktree`) owns placement, branching, and cleanup. Bypassing it is the #1 mistake — it creates phantom state your harness can't see or manage. |
+| "The worktree directory is surely ignored already" | Run `git check-ignore`. An unignored worktree directory commits the whole tree into the repo. |
+| "Any directory name works" | Explicit instructions beat an existing project-local directory, which beats the `.worktrees/` default. |
+| "The workspace is fresh — baseline tests can wait" | A dirty baseline makes every later failure ambiguous. Run the tests now; proceeding past failures is your human partner's call. |

skills/using-superpowers/SKILL.md

@@ -4,7 +4,7 @@ description: Use when starting any conversation - establishes how to find and us
 ---
 
 <SUBAGENT-STOP>
-If you were dispatched as a subagent to execute a specific task, skip this skill.
+If you were dispatched as a subagent to execute a specific task, ignore this skill.
 </SUBAGENT-STOP>
 
 <EXTREMELY-IMPORTANT>
@@ -12,72 +12,23 @@ If you think there is even a 1% chance a skill might apply to what you are doing
 
 IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
 
-This is not negotiable. This is not optional. You cannot rationalize your way out of this.
+This is not negotiable. You cannot rationalize your way out of this.
 </EXTREMELY-IMPORTANT>
 
-## Instruction Priority
-
-Superpowers skills override default system prompt behavior, but **user instructions always take precedence**:
-
-1. **User's explicit instructions** (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — highest priority
-2. **Superpowers skills** — override default system behavior where they conflict
-3. **Default system prompt** — lowest priority
-
-If CLAUDE.md, GEMINI.md, or AGENTS.md says "don't use TDD" and a skill says "always use TDD," follow the user's instructions. The user is in control.
-
-## How to Access Skills
-
-**Never read skill files manually with file tools** — always use your platform's skill-loading mechanism so the skill is properly activated.
-
-**In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you — follow it directly.
-
-**In Codex:** Skills load natively. Follow the instructions presented when a skill activates.
-
-**In Copilot CLI:** Use the `skill` tool. Skills are auto-discovered from installed plugins.
-
-**In Gemini CLI:** Skills activate via the `activate_skill` tool. Gemini loads skill metadata at session start and activates the full content on demand.
-
-**In other environments:** Check your platform's documentation for how skills are loaded.
-
-## Platform Adaptation
-
-Skills speak in actions ("dispatch a subagent", "create a todo", "read a file") rather than naming any one runtime's tools. For per-platform tool equivalents and instructions-file conventions, see [claude-code-tools.md](references/claude-code-tools.md), [codex-tools.md](references/codex-tools.md), [copilot-tools.md](references/copilot-tools.md), [gemini-tools.md](references/gemini-tools.md), [pi-tools.md](references/pi-tools.md), and [antigravity-tools.md](references/antigravity-tools.md). Gemini CLI users get the tool mapping loaded automatically via GEMINI.md.
-
-# Using Skills
-
 ## The Rule
 
-**Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.
+**Invoke relevant or requested skills BEFORE any response or action** — including clarifying questions, exploring the codebase, or checking files. If it turns out wrong for the situation, you don't have to use it.
 
-```dot
-digraph skill_flow {
-    "User message received" [shape=doublecircle];
-    "About to enter plan mode?" [shape=doublecircle];
-    "Already brainstormed?" [shape=diamond];
-    "Invoke brainstorming skill" [shape=box];
-    "Might any skill apply?" [shape=diamond];
-    "Invoke the skill" [shape=box];
-    "Announce: 'Using [skill] to [purpose]'" [shape=box];
-    "Has checklist?" [shape=diamond];
-    "Create a todo per item" [shape=box];
-    "Follow skill exactly" [shape=box];
-    "Respond (including clarifications)" [shape=doublecircle];
+**Before entering plan mode:** if you haven't already brainstormed, invoke the brainstorming skill first.
 
-    "About to enter plan mode?" -> "Already brainstormed?";
-    "Already brainstormed?" -> "Invoke brainstorming skill" [label="no"];
-    "Already brainstormed?" -> "Might any skill apply?" [label="yes"];
-    "Invoke brainstorming skill" -> "Might any skill apply?";
+Then announce "Using [skill] to [purpose]" and follow the skill exactly. If it has a checklist, create a todo per item.
 
-    "User message received" -> "Might any skill apply?";
-    "Might any skill apply?" -> "Invoke the skill" [label="yes, even 1%"];
-    "Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
-    "Invoke the skill" -> "Announce: 'Using [skill] to [purpose]'";
-    "Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
-    "Has checklist?" -> "Create a todo per item" [label="yes"];
-    "Has checklist?" -> "Follow skill exactly" [label="no"];
-    "Create a todo per item" -> "Follow skill exactly";
-}
-```
+## Skill Priority
+
+When multiple skills apply, process skills come first — they set the approach, then implementation skills (frontend-design, etc.) carry it out. Brainstorming and systematic-debugging are Superpowers' most common process skills, but the rule holds for any of them.
+
+- "Let's build X" → superpowers:brainstorming first, then implementation skills.
+- "Fix this bug" → superpowers:systematic-debugging first, then domain skills.
 
 ## Red Flags
 
@@ -98,24 +49,14 @@ These thoughts mean STOP—you're rationalizing:
 | "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
 | "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. |
 
-## Skill Priority
+## Platform Adaptation
 
-When multiple skills could apply, use this order:
+If your harness appears here, read its reference file for special instructions:
 
-1. **Process skills first** (brainstorming, systematic-debugging) - these determine HOW to approach the task
-2. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution
-
-"Let's build X" → brainstorming first, then implementation skills.
-"Fix this bug" → systematic-debugging first, then domain-specific skills.
-
-## Skill Types
-
-**Rigid** (TDD, systematic-debugging): Follow exactly. Don't adapt away discipline.
-
-**Flexible** (patterns): Adapt principles to context.
-
-The skill itself tells you which.
+- Codex: `references/codex-tools.md`
+- Pi: `references/pi-tools.md`
+- Antigravity: `references/antigravity-tools.md`
 
 ## User Instructions
 
-Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.
+User instructions (CLAUDE.md, AGENTS.md, GEMINI.md, etc, direct requests) take precedence over skills, which in turn override default behavior. Only skip skill workflows or instructions when your human partner has explicitly told you to.

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

@@ -4,85 +4,12 @@ Skills speak in actions ("dispatch a subagent", "create a todo", "read a file").
 
 | Action skills request | Antigravity CLI equivalent |
 |----------------------|----------------------|
-| Read a file | `view_file` |
-| Create a new file | `write_to_file` |
-| Edit a file | `replace_file_content` |
-| Edit a file in several places at once | `multi_replace_file_content` |
-| Run a shell command | `run_command` |
-| Search file contents | `grep_search` |
-| Find files by name / list a directory | `list_dir` (no dedicated glob tool — combine `list_dir` with `grep_search`) |
-| Fetch a URL | `read_url_content` |
-| Search the web | `search_web` |
-| Pose a structured question to your human partner | `ask_question` |
 | Dispatch a subagent (`Subagent (general-purpose):` template) | `invoke_subagent` with a built-in `TypeName` — `self` for full-capability work, `research` for read-only (see [Subagent support](#subagent-support)) |
-| Multiple parallel dispatches | Multiple entries in one `invoke_subagent` call's `Subagents` array |
 | Task tracking ("create a todo", "mark complete") | a **task artifact** — `write_to_file` with `IsArtifact: true` and `ArtifactType: "task"` (see [Task tracking](#task-tracking)). **Not** `manage_task`, which manages background processes. |
 
-## Invoking a skill — read its `SKILL.md`
-
-Antigravity surfaces every installed skill's `name` + `description` to you at the
-start of each session, but it has **no `Skill`/`activate_skill` tool**. To load a
-skill, **read its `SKILL.md` with `view_file`, setting `IsSkillFile: true`** when
-the skill applies — e.g. `view_file` on
-`.../plugins/superpowers/skills/<skill-name>/SKILL.md` with `IsSkillFile: true`.
-(`IsSkillFile` is agy's own signal that you're reading a file to *execute its
-instructions*, not to edit or preview it — set it whenever you load a skill.)
-
-This is the blessed skill-loading mechanism on this harness. The general rule
-"never read skill files manually" means "don't bypass your platform's
-skill-loading mechanism" — and on Antigravity, reading `SKILL.md` *is* that
-mechanism. Reading it honors the rule rather than breaking it.
-
-You already know which skills exist and what they're for: their names and
-descriptions are in front of you at session start. When a description matches
-what you're about to do, read that skill's `SKILL.md` before acting.
-
-## Subagent support
-
-Antigravity dispatches subagents with `invoke_subagent`, passing each one a
-`TypeName` in the `Subagents` array. Two `TypeName`s are **built in** — use them
-directly, no `define_subagent` needed:
-
-- **`self`** — a full clone of you, with every tool you have (including
-  `write_to_file`/`replace_file_content`/`run_command`). The safe default for
-  general-purpose work: implementing, fixing, anything that edits files or runs
-  commands.
-- **`research`** — read-only (file reading, `grep_search`, web/URL fetch; no write
-  or command access). Use it when you specifically want a subagent that can't make
-  changes — investigation and read-only review.
-
-Call `define_subagent` only for a custom system prompt or capability mix: set
-`enable_write_tools: true` to grant file edits **and** `run_command`,
-`enable_subagent_tools` for nested dispatch, `enable_mcp_tools` for MCP. Then
-invoke it by the name you gave it. (`manage_subagents` lists/kills running
-subagents.)
-
-Skills dispatch with `Subagent (general-purpose):` and either reference a
-prompt-template file (e.g. `superpowers:subagent-driven-development`'s
-`./implementer-prompt.md`) or supply an inline prompt. On Antigravity:
-
-| Skill dispatch form | Antigravity equivalent |
-|---------------------|----------------------|
-| An implementer-style `*-prompt.md` template (writes code, runs tests) | Fill the template, then `invoke_subagent` with `TypeName: "self"` and the filled prompt |
-| A read-only reviewer template (`task-reviewer`, `code-reviewer`, `requesting-code-review`'s `./code-reviewer.md`) | `invoke_subagent` with `TypeName: "research"` and the filled review template |
-| Inline prompt (no template referenced) | `invoke_subagent` with `TypeName: "self"` (or `"research"` if the task only reads) and your inline prompt |
-
-### Prompt filling
-
-Skills provide prompt templates with placeholders like `{WHAT_WAS_IMPLEMENTED}` or
-`[FULL TEXT of task]`. Fill all placeholders before passing the complete prompt to
-`invoke_subagent`. The prompt template itself contains the agent's role, review
-criteria, and expected output format — the subagent will follow it.
-
-### Parallel dispatch
-
-Put multiple entries in a single `invoke_subagent` call's `Subagents` array to run
-independent subagent work in parallel. Keep dependent tasks sequential, but do not
-serialize independent subagent tasks just to preserve a simpler history.
-
 ## Task tracking
 
-Antigravity has **no todo / `TodoWrite` tool** (`manage_task` manages background
+Antigravity has **no todo tool** (`manage_task` manages background
 processes — `list`/`kill`/`status`/`send_input` — it is *not* a checklist). When a
 skill says to create a todo list or track tasks, maintain a **task artifact**: a
 markdown checklist saved with `write_to_file` (`IsArtifact: true`,

skills/using-superpowers/references/claude-code-tools.md

@@ -1,50 +0,0 @@
-# Claude Code Tool Mapping
-
-Skills speak in actions ("dispatch a subagent", "create a todo", "read a file"). On Claude Code these resolve to the tools below.
-
-## Tools
-
-| Action skills request | Claude Code tool |
-|----------------------|------------------|
-| Read a file | `Read` |
-| Create a new file | `Write` |
-| Edit a file | `Edit` |
-| Run a shell command | `Bash` |
-| Search file contents | `Grep` |
-| Find files by name | `Glob` |
-| Fetch a URL | `WebFetch` |
-| Search the web | `WebSearch` |
-| Invoke a skill | `Skill` |
-| Dispatch a subagent (`Subagent (general-purpose):` template) | `Agent` (older releases named this `Task`) |
-| Multiple parallel dispatches | Multiple `Agent` calls in one response |
-| Task tracking ("create a todo", "mark complete") | `TaskCreate`, `TaskUpdate`, `TaskList`, `TaskGet`; `TodoWrite` in `claude -p` / Agent SDK unless `CLAUDE_CODE_ENABLE_TASKS=1` is set |
-| Background-process / subagent lifecycle (read output, cancel) | `TaskOutput`, `TaskStop` — these are distinct from the todo tools above and apply to running shells, agents, and remote sessions |
-
-## Instructions file
-
-When a skill mentions "your instructions file", on Claude Code this is **`CLAUDE.md`**. Claude Code walks up the directory tree from the current working directory and concatenates every `CLAUDE.md` and `CLAUDE.local.md` it finds along the way. Standard locations:
-
-| Scope | Location |
-|-------|----------|
-| Project (team-shared) | `./CLAUDE.md` or `./.claude/CLAUDE.md` |
-| User global | `~/.claude/CLAUDE.md` |
-| Local-private (gitignored) | `./CLAUDE.local.md` |
-| Managed policy (org-wide) | `/Library/Application Support/ClaudeCode/CLAUDE.md` (macOS), `/etc/claude-code/CLAUDE.md` (Linux/WSL), `C:\Program Files\ClaudeCode\CLAUDE.md` (Windows) |
-
-CLAUDE.md files can pull in additional content with `@path/to/file` imports (relative or absolute, max five hops deep). Subdirectory `CLAUDE.md` files are also discovered automatically and loaded on-demand when Claude Code reads files in those subdirectories.
-
-Claude Code does **not** read `AGENTS.md` directly. If a project already maintains `AGENTS.md` for other agents, import it from `CLAUDE.md` so both runtimes share the same instructions:
-
-```markdown
-@AGENTS.md
-
-## Claude Code
-
-(Claude-Code-specific instructions go here.)
-```
-
-For path-scoped rules and larger-project organization, see `.claude/rules/` (rules can be scoped to specific files via `paths` frontmatter and load on demand).
-
-## Personal skills directory
-
-User-level skills live at **`~/.claude/skills/`**. Each skill is a subdirectory containing a `SKILL.md` (with `name` and `description` frontmatter) plus any supporting files. Claude Code does not currently recognize the cross-runtime `~/.agents/skills/` path that Codex, Copilot CLI, and Gemini CLI read; if you're relying on cross-runtime support in the future, verify against the [official skills docs](https://code.claude.com/docs/en/skills).

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

@@ -1,31 +1,3 @@
-# Codex Tool Mapping
-
-Skills speak in actions ("dispatch a subagent", "create a todo", "read a file"). On Codex these resolve to the tools below.
-
-| Action skills request | Codex equivalent |
-|----------------------|------------------|
-| Read a file | `shell` (e.g., `cat`, `head`, `tail`) — Codex reads files via shell |
-| Create / edit / delete a file | `apply_patch` (structured diff for create, update, delete) |
-| Run a shell command | `shell` |
-| Search file contents | `shell` (e.g., `grep`, `rg`) |
-| Find files by name | `shell` (e.g., `find`, `ls`) |
-| Fetch a URL | `shell` with `curl` / `wget` — Codex has no native fetch tool |
-| Search the web | `web_search` (enabled by default; configurable in `config.toml` via the top-level `web_search` setting — `live`, `cached`, or `disabled`) |
-| Invoke a skill | Skills load natively — just follow the instructions |
-| Dispatch a subagent (`Subagent (general-purpose):` template) | `spawn_agent` (see [Subagent dispatch requires multi-agent support](#subagent-dispatch-requires-multi-agent-support)) |
-| Multiple parallel dispatches | Multiple `spawn_agent` calls in one response |
-| Wait for subagent result | `wait_agent` |
-| Free up subagent slot when done | `close_agent` |
-| Task tracking ("create a todo", "mark complete") | `update_plan` |
-
-## Instructions file
-
-When a skill mentions "your instructions file", on Codex this is **`AGENTS.md`** at the project root. Codex also reads `~/.codex/AGENTS.md` for global context, and an `AGENTS.override.md` (in the project tree or `~/.codex/`) takes precedence when present. Codex walks from the project root down to the current working directory, concatenating `AGENTS.md` files it finds along the way, up to `project_doc_max_bytes` (32 KiB by default).
-
-## Personal skills directory
-
-User-level skills live at **`$CODEX_HOME/skills/`** (default `~/.codex/skills/`). Codex also reads the cross-runtime path **`~/.agents/skills/`** (shared with Copilot CLI and Gemini CLI). When both directories exist at the same scope, Codex loads them both as separate skill catalogs — Codex's docs don't currently document a precedence between them. Each skill is a subdirectory containing a `SKILL.md` (with `name` and `description` frontmatter).
-
 ## Subagent dispatch requires multi-agent support
 
 Add to your Codex config (`~/.codex/config.toml`):
@@ -35,12 +7,7 @@ Add to your Codex config (`~/.codex/config.toml`):
 multi_agent = true
 ```
 
-This enables `spawn_agent`, `wait_agent`, and `close_agent` for skills like `dispatching-parallel-agents` and `subagent-driven-development`.
-
-Legacy note: Codex builds before `rust-v0.115.0` exposed spawned-agent
-waiting as `wait`. Current Codex uses `wait_agent` for spawned agents. The
-`wait` name now belongs to code-mode `exec/wait`, which resumes a yielded exec
-cell by `cell_id`; it is not the spawned-agent result tool.
+This enables `spawn_agent`, `wait_agent`, and `close_agent` for skills like `dispatching-parallel-agents` and `subagent-driven-development`. When using subagent-driven-development, you should always close implementer and reviewer subagents when they have finished all their work.
 
 ## Environment Detection
 

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

@@ -1,49 +0,0 @@
-# Copilot CLI Tool Mapping
-
-Skills speak in actions ("dispatch a subagent", "create a todo", "read a file"). On Copilot CLI these resolve to the tools below.
-
-| Action skills request | Copilot CLI equivalent |
-|----------------------|----------------------|
-| Read a file | `view` |
-| Create / edit / delete a file | `apply_patch` (Copilot CLI has no separate create/edit/write tools) |
-| Run a shell command | `bash` |
-| Search file contents | `rg` (ripgrep; Copilot CLI does not expose a `grep` tool) |
-| Find files by name | `glob` |
-| Fetch a URL | `web_fetch` |
-| Search the web | `web_search` |
-| Invoke a skill | `skill` |
-| Dispatch a subagent (`Subagent (general-purpose):` template) | `task` with `agent_type: "general-purpose"` (other accepted types: `explore`, `task`, `code-review`, `research`, `configure-copilot`) |
-| Multiple parallel dispatches | Multiple `task` calls in one response |
-| Subagent status/output/control | `read_agent`, `list_agents`, `write_agent` |
-| Task tracking ("create a todo", "mark complete") | `update_todo` |
-| Enter / exit plan mode | No equivalent — stay in the main session |
-
-## Instructions file
-
-When a skill mentions "your instructions file", on Copilot CLI this is **`AGENTS.md`** at the repository root. If both `AGENTS.md` and `.github/copilot-instructions.md` are present, Copilot reads both.
-
-## Personal skills directory
-
-User-level skills live at **`~/.copilot/skills/`**. Copilot CLI also recognizes the cross-runtime alias **`~/.agents/skills/`**, which is shared with Codex and Gemini CLI. Each skill is a subdirectory containing a `SKILL.md` (with `name` and `description` frontmatter).
-
-## Async shell sessions
-
-Copilot CLI supports persistent async shell sessions:
-
-| Tool | Purpose |
-|------|---------|
-| `bash` with `mode: "async"` (and optionally `detach: true`) | Start a long-running command in the background; returns a `shellId` |
-| `write_bash` | Send input to a running async session |
-| `read_bash` | Read output from an async session |
-| `stop_bash` | Terminate an async session |
-| `list_bash` | List all active shell sessions |
-
-## Additional Copilot CLI tools
-
-| Tool | Purpose |
-|------|---------|
-| `store_memory` | Persist facts about the codebase for future sessions |
-| `report_intent` | Update the UI status line with current intent |
-| `sql` | Query the session's SQLite database (todos, metadata) |
-| `fetch_copilot_cli_documentation` | Look up Copilot CLI documentation |
-| GitHub MCP tools (`github-mcp-server-*`) | Native GitHub API access (issues, PRs, code search) |

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

@@ -1,63 +0,0 @@
-# Gemini CLI Tool Mapping
-
-Skills speak in actions ("dispatch a subagent", "create a todo", "read a file"). On Gemini CLI these resolve to the tools below.
-
-| Action skills request | Gemini CLI equivalent |
-|----------------------|----------------------|
-| Read a file | `read_file` |
-| Read multiple files at once | `read_many_files` |
-| Create a new file | `write_file` |
-| Edit a file | `replace` |
-| Run a shell command | `run_shell_command` |
-| Search file contents | `grep_search` |
-| Find files by name | `glob` |
-| List files and subdirectories | `list_directory` |
-| Fetch a URL | `web_fetch` |
-| Search the web | `google_web_search` |
-| Invoke a skill | `activate_skill` |
-| Dispatch a subagent (`Subagent (general-purpose):` template) | `invoke_agent` with `agent_name: "generalist"` (invocable via `@generalist` chat syntax — see [Subagent support](#subagent-support)) |
-| Multiple parallel dispatches | Multiple `invoke_agent` calls in the same response |
-| Task tracking ("create a todo", "mark complete") | `write_todos` (statuses: pending, in_progress, completed, cancelled, blocked) |
-
-## Instructions file
-
-When a skill mentions "your instructions file", on Gemini CLI this is **`GEMINI.md`**. Gemini CLI loads `GEMINI.md` hierarchically: global at `~/.gemini/GEMINI.md`, project-level files in workspace directories and their ancestors, and sub-directory `GEMINI.md` files when a tool accesses files in those directories.
-
-## Personal skills directory
-
-User-level skills live at **`~/.gemini/skills/`**, with **`~/.agents/skills/`** as a cross-runtime alias (shared with Codex and Copilot CLI). When both directories exist at the same scope, `.agents/skills/` takes precedence. Each skill is a subdirectory containing a `SKILL.md` (with `name` and `description` frontmatter).
-
-## Subagent support
-
-Gemini CLI dispatches subagents through the `invoke_agent` tool, which takes `agent_name` and `prompt` parameters. The same dispatch is also surfaced as a chat-syntax shortcut: typing `@generalist <prompt>` is equivalent to calling `invoke_agent` with `agent_name: "generalist"`. Built-in agent names include `generalist`, `cli_help`, `codebase_investigator`, and (with browser tooling enabled) `browser_agent`.
-
-Skills dispatch with `Subagent (general-purpose):` and either reference a prompt-template file (e.g., `superpowers:subagent-driven-development`'s `./implementer-prompt.md`) or supply an inline prompt. On Gemini CLI:
-
-| Skill dispatch form | Gemini CLI equivalent |
-|---------------------|----------------------|
-| References a `*-prompt.md` template (implementer, task-reviewer, code-reviewer, etc.) | Fill the template, then `invoke_agent` with `agent_name: "generalist"` and the filled prompt |
-| References `superpowers:requesting-code-review`'s `./code-reviewer.md` | `invoke_agent` with `agent_name: "generalist"` and the filled review template |
-| Inline prompt (no template referenced) | `invoke_agent` with `agent_name: "generalist"` and your inline prompt |
-
-### Prompt filling
-
-Skills provide prompt templates with placeholders like `{WHAT_WAS_IMPLEMENTED}` or `[FULL TEXT of task]`. Fill all placeholders before passing the complete prompt to `invoke_agent`. The prompt template itself contains the agent's role, review criteria, and expected output format — the subagent will follow it.
-
-### Parallel dispatch
-
-Gemini CLI supports parallel subagent dispatch. Issue multiple `invoke_agent` calls in the same response (or multiple `@generalist` invocations in one prompt) to run independent subagent work in parallel. Keep dependent tasks sequential, but do not serialize independent subagent tasks just to preserve a simpler history.
-
-## Additional Gemini CLI tools
-
-These tools are unique to Gemini CLI:
-
-| Tool | Purpose |
-|------|---------|
-| `save_memory` (legacy) | Persist facts across sessions when `experimental.memoryV2 = false` |
-| `get_internal_docs` | Look up Gemini CLI's bundled documentation |
-| `ask_user` | Pose structured questions to the user (text / single-select / multi-select) |
-| `enter_plan_mode` / `exit_plan_mode` | Switch into and out of read-only plan mode |
-| `update_topic` | Update the current conversation's topic / strategic-intent metadata |
-| `complete_task` | Signal that a Gemini subagent has completed and return its result to the parent agent |
-| `tracker_create_task`, `tracker_update_task`, `tracker_get_task`, `tracker_list_tasks`, `tracker_add_dependency`, `tracker_visualize` | Rich task tracker with dependency and visualization support |
-| `read_mcp_resource`, `list_mcp_resources` | MCP resource access |

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

@@ -4,21 +4,9 @@ Skills speak in actions ("dispatch a subagent", "create a todo", "read a file").
 
 | Action skills request | Pi equivalent |
 | --- | --- |
-| Invoke a skill | Pi native skills: load the relevant `SKILL.md` with `read`, or let the human use `/skill:name` |
-| Read a file | `read` |
-| Create a file | `write` |
-| Edit a file | `edit` |
-| Run a shell command | `bash` |
-| Search file contents | `grep` when active; otherwise `bash` with `rg`/`grep` |
-| Find files by name | `find` or `bash` with shell globs |
-| List files and subdirectories | `ls` when active; otherwise `bash` with `ls` |
 | Dispatch a subagent (`Subagent (general-purpose):` template) | Use an installed subagent tool such as `subagent` from `pi-subagents` if available |
 | Task tracking ("create a todo", "mark complete") | Use an installed todo/task tool if available, otherwise track tasks in the plan or `TODO.md` |
 
-## Skills
-
-Pi discovers skills from configured skill directories and installed Pi packages. A Superpowers Pi package should expose `skills/` through its `pi.skills` manifest entry. Pi does not expose Claude Code's `Skill` tool, but the agent should still follow the Superpowers rule: when a skill applies, load and follow it before responding.
-
 ## Subagents
 
 Pi core does not ship a standard subagent tool. The `pi-subagents` package is a strong optional companion and provides a `subagent` tool with single-agent, chain, parallel, async, forked-context, and resume/status workflows. If no subagent tool is available, do not fabricate `Task` calls; execute sequentially in the current session or explain that the optional subagent capability is not installed.

skills/verification-before-completion/SKILL.md

@@ -7,8 +7,6 @@ description: Use when about to claim work is complete, fixed, or passing, before
 
 ## Overview
 
-Claiming work is complete without verification is dishonesty, not efficiency.
-
 **Core principle:** Evidence before claims, always.
 
 **Violating the letter of this rule is violating the spirit of this rule.**
@@ -105,15 +103,6 @@ Skip any step = lying, not verifying
 ❌ Trust agent report
 ```
 
-## Why This Matters
-
-From 24 failure memories:
-- your human partner said "I don't believe you" - trust broken
-- Undefined functions shipped - would crash
-- Missing requirements shipped - incomplete features
-- Time wasted on false completion → redirect → rework
-- Violates: "Honesty is a core value. If you lie, you'll be replaced."
-
 ## When To Apply
 
 **ALWAYS before:**
@@ -129,11 +118,3 @@ From 24 failure memories:
 - Paraphrases and synonyms
 - Implications of success
 - ANY communication suggesting completion/correctness
-
-## The Bottom Line
-
-**No shortcuts for verification.**
-
-Run the command. Read the output. THEN claim the result.
-
-This is non-negotiable.

skills/writing-plans/SKILL.md

@@ -135,12 +135,6 @@ Every step must contain the actual content an engineer needs. These are **plan f
 - Steps that describe what to do without showing how (code blocks required for code steps)
 - References to types, functions, or methods not defined in any task
 
-## Remember
-- Exact file paths always
-- Complete code in every step — if a step changes code, show the code
-- Exact commands with expected output
-- DRY, YAGNI, TDD, frequent commits
-
 ## Self-Review
 
 After writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch.

skills/writing-skills/SKILL.md

@@ -9,7 +9,7 @@ description: Use when creating new skills, editing existing skills, or verifying
 
 **Writing skills IS Test-Driven Development applied to process documentation.**
 
-**Personal skills live in your runtime's skills directory** — see [claude-code-tools.md](../using-superpowers/references/claude-code-tools.md), [codex-tools.md](../using-superpowers/references/codex-tools.md), [copilot-tools.md](../using-superpowers/references/copilot-tools.md), or [gemini-tools.md](../using-superpowers/references/gemini-tools.md) for the path on your runtime. Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.
+**Personal skills live in your runtime's skills directory** 
 
 You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).
 
@@ -677,13 +677,3 @@ How future agents find your skill:
 6. **Loads example** (only when implementing)
 
 **Optimize for this flow** - put searchable terms early and often.
-
-## The Bottom Line
-
-**Creating skills IS TDD for process documentation.**
-
-Same Iron Law: No skill without failing test first.
-Same cycle: RED (baseline) → GREEN (write skill) → REFACTOR (close loopholes).
-Same benefits: Better quality, fewer surprises, bulletproof results.
-
-If you follow TDD for code, follow it for skills. It's the same discipline applied to documentation.

tests/codex/test-marketplace-manifest.sh

@@ -0,0 +1,76 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+MARKETPLACE="$REPO_ROOT/.agents/plugins/marketplace.json"
+
+python3 - "$MARKETPLACE" "$REPO_ROOT" <<'PY'
+import json
+import sys
+from pathlib import Path
+
+marketplace_path = Path(sys.argv[1])
+repo_root = Path(sys.argv[2])
+
+if not marketplace_path.exists():
+    raise AssertionError(".agents/plugins/marketplace.json must exist")
+
+marketplace = json.loads(marketplace_path.read_text(encoding="utf-8"))
+
+def assert_equal(actual, expected, label):
+    if actual != expected:
+        raise AssertionError(f"{label}: expected {expected!r}, got {actual!r}")
+
+assert_equal(marketplace.get("name"), "superpowers-dev", "marketplace name")
+assert_equal(
+    marketplace.get("interface", {}).get("displayName"),
+    "Superpowers Dev",
+    "marketplace display name",
+)
+
+plugins = marketplace.get("plugins")
+if not isinstance(plugins, list):
+    raise AssertionError("plugins must be a list")
+
+matching_plugins = [plugin for plugin in plugins if plugin.get("name") == "superpowers"]
+assert_equal(len(matching_plugins), 1, "superpowers plugin entry count")
+
+plugin = matching_plugins[0]
+assert_equal(plugin.get("source"), {"source": "url", "url": "./"}, "plugin source")
+assert_equal(
+    plugin.get("policy"),
+    {"installation": "AVAILABLE", "authentication": "ON_INSTALL"},
+    "plugin policy",
+)
+assert_equal(plugin.get("category"), "Developer Tools", "plugin category")
+
+plugin_manifest = repo_root / ".codex-plugin" / "plugin.json"
+if not plugin_manifest.exists():
+    raise AssertionError(".codex-plugin/plugin.json must exist")
+
+manifest = json.loads(plugin_manifest.read_text(encoding="utf-8"))
+assert_equal(manifest.get("name"), plugin.get("name"), "plugin manifest name")
+
+# 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"),
+    {},
+    "Codex manifest must declare empty hooks {} to suppress hooks/hooks.json auto-discovery",
+)
+
+print("Codex marketplace manifest looks good")
+PY

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

@@ -0,0 +1,292 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+SCRIPT_UNDER_TEST="$REPO_ROOT/scripts/package-codex-plugin.sh"
+
+FAILURES=0
+TEST_ROOT="$(mktemp -d)"
+
+cleanup() {
+  rm -rf "$TEST_ROOT"
+}
+trap cleanup EXIT
+
+pass() {
+  echo "  [PASS] $1"
+}
+
+fail() {
+  echo "  [FAIL] $1"
+  FAILURES=$((FAILURES + 1))
+}
+
+assert_equals() {
+  local actual="$1"
+  local expected="$2"
+  local description="$3"
+
+  if [[ "$actual" == "$expected" ]]; then
+    pass "$description"
+  else
+    fail "$description"
+    echo "    expected: $expected"
+    echo "    actual:   $actual"
+  fi
+}
+
+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_matches() {
+  local haystack="$1"
+  local pattern="$2"
+  local description="$3"
+
+  if printf '%s' "$haystack" | grep -Eq -- "$pattern"; then
+    fail "$description"
+    echo "    did not expect to match: $pattern"
+  else
+    pass "$description"
+  fi
+}
+
+list_archive() {
+  local archive_path="$1"
+
+  case "$archive_path" in
+    *.tar.gz|*.tgz)
+      tar -tzf "$archive_path"
+      ;;
+    *.zip)
+      unzip -Z1 "$archive_path"
+      ;;
+    *)
+      unzip -Z1 "$archive_path"
+      ;;
+  esac
+}
+
+normalize_archive_paths() {
+  sed 's#/$##' | LC_ALL=C sort
+}
+
+extract_archive() {
+  local archive_path="$1"
+  local destination="$2"
+
+  mkdir -p "$destination"
+  case "$archive_path" in
+    *.tar.gz|*.tgz)
+      tar -xzf "$archive_path" -C "$destination"
+      ;;
+    *.zip)
+      unzip -q "$archive_path" -d "$destination"
+      ;;
+    *)
+      unzip -q "$archive_path" -d "$destination"
+      ;;
+  esac
+}
+
+read_archive_file() {
+  local archive_path="$1"
+  local file_path="$2"
+
+  case "$archive_path" in
+    *.tar.gz|*.tgz)
+      tar -xOf "$archive_path" "$file_path"
+      ;;
+    *.zip)
+      unzip -p "$archive_path" "$file_path"
+      ;;
+    *)
+      unzip -p "$archive_path" "$file_path"
+      ;;
+  esac
+}
+
+write_metadata_fixture() {
+  local destination="$1"
+  local skill
+
+  while IFS= read -r skill; do
+    mkdir -p "$destination/skills/$skill/agents"
+    cat >"$destination/skills/$skill/agents/openai.yaml" <<EOF
+interface:
+  display_name: "$skill"
+  short_description: "Fixture metadata for $skill"
+EOF
+  done < <(find "$REPO_ROOT/skills" -mindepth 1 -maxdepth 1 -type d -print | sed 's#.*/##' | sort)
+}
+
+echo "Codex package archive tests"
+
+metadata_source="$TEST_ROOT/metadata-source"
+archive="$TEST_ROOT/superpowers"
+tar_archive="$TEST_ROOT/superpowers.tar.gz"
+extracted="$TEST_ROOT/extracted"
+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 "$source_hooks" "{}" "source Codex manifest suppresses local hook auto-discovery"
+
+if output="$("$SCRIPT_UNDER_TEST" --allow-dirty --metadata-source "$metadata_source" --output "$archive" 2>&1)"; then
+  pass "package script exits successfully"
+else
+  fail "package script exits successfully"
+  printf '%s\n' "$output" | sed 's/^/      /'
+fi
+
+if [[ -f "$archive" ]]; then
+  pass "package script writes archive"
+else
+  fail "package script writes archive"
+fi
+
+assert_contains "$output" "Archive:" "reports archive path"
+assert_contains "$output" "Format:  zip" "reports default zip format"
+assert_contains "$output" "SHA-256:" "reports archive checksum"
+
+extract_archive "$archive" "$extracted"
+
+archive_paths="$(list_archive "$archive" | normalize_archive_paths)"
+unexpected_pattern='(^superpowers/|^\.agents/|^hooks/|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 "$archive_paths" "skills/brainstorming/agents/openai.yaml" "archive includes OpenAI skill metadata"
+assert_contains "$archive_paths" "assets/app-icon.png" "archive includes app icon"
+assert_contains "$archive_paths" "assets/superpowers-small.svg" "archive includes composer icon"
+
+manifest_summary="$(read_archive_file "$archive" .codex-plugin/plugin.json | python3 -c 'import json,sys; data=json.load(sys.stdin); print("\t".join([data["name"], data["version"], data["skills"], str(data.get("hooks"))]))')"
+expected_version="$(python3 -c 'import json; print(json.load(open("'"$REPO_ROOT"'/.codex-plugin/plugin.json"))["version"])')"
+assert_equals "$manifest_summary" "superpowers	$expected_version	./skills/	$source_hooks" "archive manifest preserves source hooks"
+
+skill_count="$(find "$extracted/skills" -mindepth 1 -maxdepth 1 -type d | wc -l | tr -d ' ')"
+metadata_count="$(find "$extracted/skills" -path '*/agents/openai.yaml' -type f | wc -l | tr -d ' ')"
+assert_equals "$metadata_count" "$skill_count" "every packaged skill has OpenAI metadata"
+
+if [[ -x "$extracted/skills/subagent-driven-development/scripts/task-brief" ]]; then
+  pass "archive preserves executable script mode"
+else
+  fail "archive preserves executable script mode"
+fi
+
+zip_times="$(python3 - "$archive" <<'PY'
+import sys
+import zipfile
+
+with zipfile.ZipFile(sys.argv[1]) as archive:
+    print("\n".join(sorted({str(info.date_time) for info in archive.infolist()})))
+PY
+)"
+assert_equals "$zip_times" "(1980, 1, 1, 0, 0, 0)" "zip archive normalizes entry timestamps"
+
+if tar_output="$("$SCRIPT_UNDER_TEST" --allow-dirty --metadata-source "$metadata_source" --format tar.gz --output "$tar_archive" 2>&1)"; then
+  pass "package script writes explicit tar.gz archive"
+else
+  fail "package script writes explicit tar.gz archive"
+  printf '%s\n' "$tar_output" | sed 's/^/      /'
+fi
+assert_contains "$tar_output" "Format:  tar.gz" "reports explicit tar.gz format"
+
+extract_archive "$tar_archive" "$tar_extracted"
+tar_archive_paths="$(list_archive "$tar_archive" | normalize_archive_paths)"
+assert_equals "$tar_archive_paths" "$archive_paths" "zip and tar.gz archives contain the same paths"
+
+tar_task_brief_mode="$(tar -tzvf "$tar_archive" skills/subagent-driven-development/scripts/task-brief | awk '{print $1}')"
+assert_equals "$tar_task_brief_mode" "-rwxr-xr-x" "tar.gz archive preserves executable script mode"
+
+tar_metadata_times="$(tar -tzvf "$tar_archive" | awk '{print $6, $7, $8}' | sort -u)"
+assert_equals "$tar_metadata_times" "Dec 31 1969" "tar.gz archive normalizes entry timestamps"
+
+metadata_archive="$TEST_ROOT/metadata-source.tar.gz"
+metadata_zip="$TEST_ROOT/metadata-source.zip"
+archive_from_tar_source="$TEST_ROOT/superpowers-from-tar-source.zip"
+archive_from_zip_source="$TEST_ROOT/superpowers-from-zip-source.zip"
+(
+  cd "$metadata_source"
+  tar -czf "$metadata_archive" .
+  zip -X -q -r "$metadata_zip" .
+)
+
+if output="$("$SCRIPT_UNDER_TEST" --allow-dirty --metadata-source "$metadata_archive" --output "$archive_from_tar_source" 2>&1)"; then
+  pass "package script accepts tarball metadata source"
+else
+  fail "package script accepts tarball metadata source"
+  printf '%s\n' "$output" | sed 's/^/      /'
+fi
+
+if cmp -s "$archive" "$archive_from_tar_source"; then
+  pass "tarball metadata source produces identical archive"
+else
+  fail "tarball metadata source produces identical archive"
+fi
+
+if output="$("$SCRIPT_UNDER_TEST" --allow-dirty --metadata-source "$metadata_zip" --output "$archive_from_zip_source" 2>&1)"; then
+  pass "package script accepts zip metadata source"
+else
+  fail "package script accepts zip metadata source"
+  printf '%s\n' "$output" | sed 's/^/      /'
+fi
+
+if cmp -s "$archive" "$archive_from_zip_source"; then
+  pass "zip metadata source produces identical archive"
+else
+  fail "zip metadata source produces identical archive"
+fi
+
+incomplete_metadata="$TEST_ROOT/incomplete-metadata"
+mkdir -p "$incomplete_metadata/skills/brainstorming/agents"
+cp "$metadata_source/skills/brainstorming/agents/openai.yaml" \
+  "$incomplete_metadata/skills/brainstorming/agents/openai.yaml"
+
+set +e
+missing_output="$("$SCRIPT_UNDER_TEST" --allow-dirty --metadata-source "$incomplete_metadata" --output "$TEST_ROOT/missing.tar.gz" 2>&1)"
+missing_status=$?
+set -e
+if [[ "$missing_status" -ne 0 ]]; then
+  pass "package script rejects incomplete metadata source"
+else
+  fail "package script rejects incomplete metadata source"
+fi
+assert_contains "$missing_output" "ERROR: metadata source is incomplete" "incomplete metadata reports clear error"
+
+dirty_repo="$TEST_ROOT/dirty-repo"
+git clone -q --no-local "$REPO_ROOT" "$dirty_repo"
+printf '\n# dirty fixture\n' >>"$dirty_repo/README.md"
+set +e
+dirty_output="$(
+  cd "$dirty_repo"
+  scripts/package-codex-plugin.sh \
+    --metadata-source "$metadata_source" \
+    --output "$TEST_ROOT/dirty.zip" 2>&1
+)"
+dirty_status=$?
+set -e
+if [[ "$dirty_status" -ne 0 ]]; then
+  pass "package script rejects dirty worktree by default"
+else
+  fail "package script rejects dirty worktree by default"
+fi
+assert_contains "$dirty_output" "Working tree has uncommitted changes:" "dirty worktree reports changed files"
+
+if [[ "$FAILURES" -eq 0 ]]; then
+  echo "All Codex package archive tests passed"
+else
+  echo "$FAILURES Codex package archive test(s) failed"
+  exit 1
+fi

tests/hooks/test-session-start.sh

@@ -4,7 +4,6 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
 REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
 HOOK_UNDER_TEST="$REPO_ROOT/hooks/session-start"
-CODEX_HOOK_UNDER_TEST="$REPO_ROOT/hooks/session-start-codex"
 WRAPPER_UNDER_TEST="$REPO_ROOT/hooks/run-hook.cmd"
 
 FAILURES=0
@@ -154,35 +153,15 @@ assert_command_output \
     CLAUDE_PLUGIN_ROOT="$REPO_ROOT" \
     bash "$HOOK_UNDER_TEST"
 
-codex_home="$(make_home codex-plugin-hooks)"
-codex_data="$TEST_ROOT/codex-plugin-hooks/data"
-mkdir -p "$codex_data"
+wrapper_home="$(make_home run-hook-wrapper)"
 assert_command_output \
-    "Codex plugin hooks use dedicated script and emit nested SessionStart additionalContext" \
+    "run-hook.cmd wrapper dispatches to the named session-start script" \
     "nested" \
     "" \
     "" \
-    "$codex_home" \
-    PLUGIN_DATA="$codex_data" \
-    CLAUDE_PLUGIN_DATA="$codex_data" \
-    PLUGIN_ROOT="$REPO_ROOT" \
+    "$wrapper_home" \
     CLAUDE_PLUGIN_ROOT="$REPO_ROOT" \
-    bash "$CODEX_HOOK_UNDER_TEST"
-
-codex_wrapper_home="$(make_home codex-wrapper)"
-codex_wrapper_data="$TEST_ROOT/codex-wrapper/data"
-mkdir -p "$codex_wrapper_data"
-assert_command_output \
-    "Codex wrapper path dispatches to dedicated script" \
-    "nested" \
-    "" \
-    "" \
-    "$codex_wrapper_home" \
-    PLUGIN_DATA="$codex_wrapper_data" \
-    CLAUDE_PLUGIN_DATA="$codex_wrapper_data" \
-    PLUGIN_ROOT="$REPO_ROOT" \
-    CLAUDE_PLUGIN_ROOT="$REPO_ROOT" \
-    bash "$WRAPPER_UNDER_TEST" session-start-codex
+    bash "$WRAPPER_UNDER_TEST" session-start
 
 cursor_home="$(make_home cursor)"
 assert_command_output \
@@ -217,21 +196,6 @@ assert_command_output \
     CLAUDE_PLUGIN_ROOT="$REPO_ROOT" \
     bash "$HOOK_UNDER_TEST"
 
-codex_legacy_home="$(make_home codex-legacy-warning-removed)"
-codex_legacy_data="$TEST_ROOT/codex-legacy-warning-removed/data"
-mkdir -p "$codex_legacy_home/.config/superpowers/skills" "$codex_legacy_data"
-assert_command_output \
-    "Codex SessionStart omits obsolete legacy custom-skill warning" \
-    "nested" \
-    "" \
-    "Superpowers now uses"$'\037'"~/.config/superpowers/skills"$'\037'"~/.claude/skills"$'\037'"legacy" \
-    "$codex_legacy_home" \
-    PLUGIN_DATA="$codex_legacy_data" \
-    CLAUDE_PLUGIN_DATA="$codex_legacy_data" \
-    PLUGIN_ROOT="$REPO_ROOT" \
-    CLAUDE_PLUGIN_ROOT="$REPO_ROOT" \
-    bash "$CODEX_HOOK_UNDER_TEST"
-
 if [[ "$FAILURES" -gt 0 ]]; then
     echo "STATUS: FAILED ($FAILURES failure(s))"
     exit 1