zhanj/claude-code
1
0
Fork 0
mirror of https://github.com/anthropics/claude-code.git synced 2026-05-09 16:42:43 +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

9
plugins/hookify/agents/conversation-analyzer.md
View File

@@ -1,6 +1,13 @@
---
name: conversation-analyzer
description: Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments\nuser: "/hookify"\nassistant: "I'll analyze the conversation to find behaviors you want to prevent"\n<commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations\nuser: "Can you look back at this conversation and help me create hooks for the mistakes you made?"\nassistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks."\n<commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>
description: |-
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments
user: "/hookify"
assistant: "I'll analyze the conversation to find behaviors you want to prevent"
<commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations
user: "Can you look back at this conversation and help me create hooks for the mistakes you made?"
assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks."
<commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>
model: inherit
color: yellow
tools: ["Read", "Grep"]