rpg-fan/cline-recursive-chain-of-thought-system-crct-/crct-documentation
Claude Code and agent skill by rpg-fan/cline-recursive-chain-of-thought-system-crct-
- community
Checking that the SKILL.md file is still in the repository.
Install
npx vskill@latest install rpg-fan/cline-recursive-chain-of-thought-system-crct-/crct-documentationSKILL.md
CRCT Comment-Skill: Automated Dependency Annotation
CRCT v8.4 introduces the Comment-Skill system, an automated utility for injecting architectural metadata directly into your source code. This system enhances agent navigability and ensures that documentation remains synchronized with the project's dependency graph.
Core Concepts
Station Headers
A Station Header is a block of metadata injected at the top of a source file. It provides immediate context about the file's role and its position in the dependency hierarchy.
- [AUTO]: Fields marked with this tag are managed by CRCT and will be refreshed automatically.
- [FILL: ...]: These are prose fields intended for agents to complete. CRCT will preserve any text you write here during updates.
Connection Maps
A Connection Map is a single-line comment injected before each function or class definition. it summarizes the symbol's outbound dependencies using the tracker's "dependency rail" format.
- Dependency Rail: Shows target keys and their relationship character (e.g.,
>for outbound,xfor bi-directional). - Filtering: Connection maps are filtered to show only dependencies relevant to the specific symbol, based on AST and runtime analysis.
Usage
The comment system is integrated into the CRCT TrackerBatchCollector and triggers automatically after tracker updates (e.g., during resolve-placeholders or analyze-project).
Manual Trigger
You can also manually refresh comments using the populate_comments.py utility:
Benefits for Agents
- Local Context: Agents can understand a file's dependencies without opening the full tracker.
- Navigational Pointers:
TRACKER_REFandCRCT_KEYprovide clear "goto" pointers for deeper investigation. - Stable Metadata: Architectural shifts are reflected in the code immediately, reducing the risk of working with stale context.
Best Practices
- Always use [FILL]: When an agent initializes a file, it should fill in the
ROLEandLAYERfields to provide long-term context. - Commit with Comments: Include the [AUTO] comment blocks in your version control to share architectural context with other agents or developers.
- Audit Regularly: Use the
code_analysisreporting tools to find files with missing or incomplete headers.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcline_docs/CRCT_Documentation/COMMENT_SKILL.md
Popularity
- Repository stars
- 765
- Repository forks
- 80
- 7-day trend score
- 33
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/rpg-fan/cline-recursive-chain-of-thought-system-crct-/crct-documentation)