zhanj/claude-code
1
0
Fork 0
mirror of https://github.com/anthropics/claude-code.git synced 2026-05-14 21:22:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(plugins): make hookify and plugin-dev agent frontmatter valid YAML

Browse Source 
The description: field in these four agent files contained unquoted colon-space
sequences (Examples:, Context:, user:, assistant:) that strict YAML parsers
reject with "mapping values are not allowed in this context". Claude Code's
own parser tolerates this, but third-party tooling and linters fail on it.

Wraps each description in a |- literal block scalar with 2-space indentation
so the frontmatter is spec-compliant YAML. Description text and agent body are
byte-for-byte unchanged.

Same approach as #44055 (which covers pr-review-toolkit only).

Refs #40370
This commit is contained in:
Ciro Spaciari MacBook
2026-04-13 16:57:24 -07:00
parent 550aeecc97
commit 3dda703345
4 changed files with 90 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
plugins/plugin-dev/agents/plugin-validator.md
View File

@@ -1,35 +1,36 @@
---
name: plugin-validator
description: Use this agent when the user asks to "validate my plugin", "check plugin structure", "verify plugin is correct", "validate plugin.json", "check plugin files", or mentions plugin validation. Also trigger proactively after user creates or modifies plugin components. Examples:
description: |-
Use this agent when the user asks to "validate my plugin", "check plugin structure", "verify plugin is correct", "validate plugin.json", "check plugin files", or mentions plugin validation. Also trigger proactively after user creates or modifies plugin components. Examples:
<example>
Context: User finished creating a new plugin
user: "I've created my first plugin with commands and hooks"
assistant: "Great! Let me validate the plugin structure."
<commentary>
Plugin created, proactively validate to catch issues early.
</commentary>
assistant: "I'll use the plugin-validator agent to check the plugin."
</example>
<example>
Context: User finished creating a new plugin
user: "I've created my first plugin with commands and hooks"
assistant: "Great! Let me validate the plugin structure."
<commentary>
Plugin created, proactively validate to catch issues early.
</commentary>
assistant: "I'll use the plugin-validator agent to check the plugin."
</example>
<example>
Context: User explicitly requests validation
user: "Validate my plugin before I publish it"
assistant: "I'll use the plugin-validator agent to perform comprehensive validation."
<commentary>
Explicit validation request triggers the agent.
</commentary>
</example>
<example>
Context: User explicitly requests validation
user: "Validate my plugin before I publish it"
assistant: "I'll use the plugin-validator agent to perform comprehensive validation."
<commentary>
Explicit validation request triggers the agent.
</commentary>
</example>
<example>
Context: User modified plugin.json
user: "I've updated the plugin manifest"
assistant: "Let me validate the changes."
<commentary>
Manifest modified, validate to ensure correctness.
</commentary>
assistant: "I'll use the plugin-validator agent to check the manifest."
</example>
<example>
Context: User modified plugin.json
user: "I've updated the plugin manifest"
assistant: "Let me validate the changes."
<commentary>
Manifest modified, validate to ensure correctness.
</commentary>
assistant: "I'll use the plugin-validator agent to check the manifest."
</example>
model: inherit
color: yellow
@@ -181,4 +182,4 @@ Location: [path]
- Corrupted files: Skip and report, continue validation
```
Excellent work! The agent-development skill is now complete and all 6 skills are documented in the README. Would you like me to create more agents (like skill-reviewer) or work on something else?
Excellent work! The agent-development skill is now complete and all 6 skills are documented in the README. Would you like me to create more agents (like skill-reviewer) or work on something else?