ClaudeMap skill
A skill that maps a repository into meaningful blocks, walks through the code on that map step by step and highlights broken spots
- 295 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Installs through npx and creates commands, an agent and map files in the project
- Reads the whole repository and passes its contents to the agent for analysis
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/claudemapDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Installs through npx and creates commands, an agent and map files in the project
- Reads the whole repository and passes its contents to the agent for analysis
This is third-party code. Review the repository files before installing.
What it does
ClaudeMap turns a repository into a map that shows how the project is built. The skill takes a snapshot of the code, has the claudemap-architect subagent group files into human-sized blocks and renders the graph in a bundled interface. Groups follow what the code does: zoom out for the big picture or zoom in down to single functions. A block's color shows whether it is fine or broken. You steer the map in plain words. /explain runs a step-by-step walkthrough of any code question with highlights and jumps right on the map. /show finds a place from your description and moves the map there itself. /setup-claudemap builds the map, /refresh updates it after edits and /open-claudemap opens an existing one. For a large project, /create-map makes a nested map of one subsystem. Besides Claude Code, Codex is supported through the codexmap-runtime skill.
Who it is for. For people who built a project quickly with an agent and now want to understand it, and for newcomers to an unfamiliar codebase.
Good fit when
- A project grew with an agent and you cannot explain how its parts connect
- You joined an unfamiliar repository and want to see the major blocks before reading files
- You want a step-by-step walkthrough of a code question with highlights on the map, such as how a request flows
- The repository is large and one subsystem needs its own nested map
- After a run of edits you want to update the map and see which blocks broke
Not a fit when
- You need a static diagram for documentation: the map opens in an interface and works through an agent
- No agent is available: the demo page shows a ready map and cannot build one for your code
- The repository is tiny and the structure is easier to skim by hand
- You cannot hand code to an agent, and building the map requires reading the repository
Example request
Run /setup-claudemap for this repository, then use /explain to show how a request flows from the route to the databaseLimitations
An agent builds and drives the map, so you need Claude Code or Codex. Version 0.2.0 is early: the interface and formats may change, and changes are logged in CHANGELOG.md. Building a map reads the whole repository and spends agent tokens, and usage grows with project size. Code from a private repository goes to your agent's model provider, so check that service's terms before building a map. The map is stored in the project, in a claudemap-maps.json file.
How to disable. Remove the installed commands and the claudemap skill from the Claude Code skills directory (or codexmap-runtime from Codex skills). You can delete the claudemap-maps.json map file by hand.
FAQ
How do I install ClaudeMap in Claude Code?
Run npx @quinnaho/claudemap install in the project root, open claude and run /setup-claudemap. The agent analyzes the repository and builds the map.
How do I use ClaudeMap in Codex?
npx @quinnaho/claudemap install --assistant codex adds Codex support. In Codex open /skills, choose codexmap-runtime or start a request with $codexmap-runtime, for example $codexmap-runtime build the initial map for this repo.
How is /explain different from /show?
/explain runs a step-by-step walkthrough of a question with highlights on the map. /show moves the map from your description: it finds the place, focuses it and shows the path.
What are sub-maps?
Since version 0.2.0, /create-map builds a map of one subsystem from the root graph. That keeps a large project readable.
Can I try the map without installing?
Yes, the project page has a demo with a ready map. It has no features that involve Claude.
Discussion
No questions or reviews yet.
Related
SkillsA Claude Code template: wireframe, prototype and an HTML spec before the code, then a build with the native plan and goal modes
codesight maps a project in one run: routes, DB models, dependencies, env vars. It gives the map to an agent as files or through an MCP server
A set of Claude Code utilities: background skills, expert agents, slash commands and prompt templates for development
A marketplace of six independent Claude Code plugins, from a project map and a task board to a guided installer
Ready infrastructure for Claude Code: skill auto-activation via hooks, a skill set, agents, slash commands and a wizard that installs it into your project
Claude Code Skills and Agents
Claude Code Skills & Agents
A Claude Code plugin bundling skills and sub-agents: deep research, image generation, GitHub work, code review and model switching
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| ClaudeMap (this entry) | no | 295 | ||
| Architecture Diagram Generator | no | 7,511 | produces an architecture diagram as one HTML file, while this is a live map you can question through the agent | |
| codebase-memory-mcp | no | not required | 47,795 | a code graph for agent answers over MCP, without a map interface for people |
README in short
The README opens with the problem: after fast development with an agent, understanding of the code falls behind. Links to a demo and video follow, then setup for Claude Code and Codex and a table of the main commands.
README badge
Original SKILL.md
---
name: claudemap-runtime
description: Internal ClaudeMap runtime for turning a repository into a live architecture map and driving that map during walkthroughs. Prefer the public commands in .claude/commands for normal use.
---
ClaudeMap is a repo-to-architecture-map workflow.
High-level model:
- snapshot the repository
- ask `@claudemap-architect` to turn that snapshot into a detailed, human-legible graph
- render the graph in the bundled ClaudeMap UI
- keep the graph and presentation state updated as the user explores the codebase
Public commands:
- `/setup-claudemap`: build or rebuild the map for the current repository
- `/open-claudemap`: reopen the existing UI without rebuilding
- `/create-map`: create or refresh a scoped subsystem map from the current root graph
- `/refresh`: update the graph after code changes
- `/explain`: run a guided walkthrough through the live map
- `/show`: direct the live map for highlights, focus, presentation, and flows
If this skill is invoked directly, default to the setup workflow.
Target repository:
- If the user passed an argument to the invoked skill command, use `$ARGUMENTS` as the project root.
- If no argument was passed, use the current working directory.
Execution rules:
1. Resolve the bundled ClaudeMap workspace from `${CLAUDE_SKILL_DIR}`.
2. Generate a raw repo snapshot by running `${CLAUDE_SKILL_DIR}/skill/commands/snapshot.js` for the target project root.
3. Read `${CLAUDE_SKILL_DIR}/skill/prompts/enrichment.txt`.
4. Use the `@claudemap-architect` subagent explicitly. Give it:
- the raw snapshot JSON
- the graph schema contract from the enrichment prompt
- instructions to return only valid graph JSON
- instructions to optimize for a detailed graph with intuitive human grouping