By kingbootoshi
Map and document any codebase by orchestrating parallel AI subagents that analyze architecture, file roles, dependencies, and navigation, outputting a structured CODEBASE_MAP.md that updates incrementally via git or scans.
A Claude Code plugin that maps and documents codebases of any size using parallel AI subagents.
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.
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 guidesCLAUDE.md with a summary pointing to the mapIf docs/CODEBASE_MAP.md already exists, Cartographer will:
Just run /cartographer again to update.
⚠️ 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.
pip install tiktoken or uv pip install tiktokenSee plugins/cartographer/README.md for detailed documentation.
MIT
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub kingbootoshi/cartographer --plugin cartographerAI image generation CLI powered by Gemini 3.1 Flash (default) and Gemini 3 Pro. Multi-resolution, aspect ratios, cost tracking, green screen transparency, and reference images.
Orchestrate OpenAI Codex agents from Claude Code via tmux sessions
Write prompts, system instructions, agent directives, and skill descriptions using two stacked layers: outcome-first (goal, success criteria, stopping condition) plus directional language (every sentence names the path with positive verbs).
Strict Red-Green-Refactor proof for coding agents.
Single-file agent goal ledger for Claude Code and Codex CLI. Pairs with /goal mode.
A self-maintaining codebase map: atomic docs Claude loads at the start of each session and keeps in sync as the code changes. Any stack; greenfield or existing.
Auto-document entire codebase with inline comments and API docs
Multi-agent codebase analysis and documentation generation: parallel analyzers for structure, dependencies, data flow, request flow, and APIs, plus README and AI-rules (CLAUDE.md, AGENTS.md, Cursor rules) generators.
Generate comprehensive analysis and documentation of entire codebase
Codebase intelligence for AI agents. The /devlens skill teaches your agent to query a precomputed code graph (nodes, typed edges, technical/business/security summaries) via the DevLens CLI instead of grepping and reading whole files — with subcommands for architecture, diagrams, security analysis, impact, summaries, and more.
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.