Co-Pilot
Updated a month ago

cartographer

Kkingbootoshi
0.4k
kingbootoshi/cartographer
80
Agent Score

💡 Summary

Cartographer is a plugin that maps and documents codebases using parallel AI subagents.

🎯 Target Audience

Software developersTechnical project managersDevOps engineersCode reviewersDocumentation specialists

🤖 AI Roast:Powerful, but the setup might scare off the impatient.

Security AnalysisMedium Risk

Risk: Medium. Review: outbound network access (SSRF, data egress); API keys/tokens handling and storage; dependency pinning and supply-chain risk. Run with least privilege and audit before enabling in production.

Cartographer

A Claude Code plugin that maps and documents codebases of any size using parallel AI subagents.

Installation

Step 1: Add the marketplace to Claude Code:

/plugin marketplace add kingbootoshi/cartographer

Step 2: Install the plugin:

/plugin install cartographer

Step 3: Restart Claude Code (may be required for the skill to load)

Step 4: Use it:

/cartographer

Or just say "map this codebase" and it will trigger automatically.

What it Does

Cartographer orchestrates multiple Sonnet subagents to analyze your entire codebase in parallel, then synthesizes their findings into:

  • docs/CODEBASE_MAP.md - Detailed architecture map with file purposes, dependencies, data flows, and navigation guides
  • Updates CLAUDE.md with a summary pointing to the map

How it Works

  1. Runs a scanner script to get file tree with token counts (respects .gitignore)
  2. Plans how to split work across subagents based on token budgets
  3. Spawns Sonnet subagents in parallel - each analyzes a portion of the codebase
  4. Synthesizes all subagent reports into comprehensive documentation

Update Mode

If docs/CODEBASE_MAP.md already exists, Cartographer will:

  1. Check git history for changes since last mapping
  2. Only re-analyze changed modules
  3. Merge updates with existing documentation

Just run /cartographer again to update.

Token Usage

⚠️ NOTE: This skill spawns Sonnet subagents for accurate, reliable analysis. Depending on codebase size, this can use significant tokens. Be mindful of your usage.

You can ask Claude to use Haiku subagents instead for a cheaper run, but accuracy may suffer on complex codebases.

Requirements

  • tiktoken (for token counting): pip install tiktoken or uv pip install tiktoken

Full Documentation

See plugins/cartographer/README.md for detailed documentation.

License

MIT

5-Dim Analysis
Clarity8/10
Novelty8/10
Utility9/10
Completeness8/10
Maintainability7/10
Pros & Cons

Pros

  • Efficient parallel analysis of codebases
  • Generates comprehensive documentation
  • Updates existing documentation intelligently

Cons

  • High token usage for large codebases
  • Dependency on Sonnet subagents
  • May require manual restarts

Related Skills

ccmp

A
toolCo-Pilot
86/ 100

“Powerful, but the setup might scare off the impatient.”

claude-mods

A
toolCo-Pilot
86/ 100

“Powerful, but the setup might scare off the impatient.”

agentic-qe

A
toolCo-Pilot
86/ 100

“Powerful, but the setup might scare off the impatient.”

Disclaimer: This content is sourced from GitHub open source projects for display and rating purposes only.

Copyright belongs to the original author kingbootoshi.