Agent skill

Codemap

by jellydn in jellydn/my-ai-tools

Create a seven-document architecture map when the user asks to map a codebase.

MITAuto-check: notes

Install Codemap

skills CLI
$ npx skills add jellydn/my-ai-tools --skill codemap -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jellydn/my-ai-tools codemap --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jellydn/my-ai-tools.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codemap .claude/skills/codemap && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
codemap
GitHub stars
123
Token cost
~2.8k tokens
SKILL.md length
813 words
Files
8
Skills in repo
33
Repo updated
First seen
Licence
MIT

At a glance

Create a seven-document architecture map when the user asks to map a codebase.

  • Works in 6 steps: Check Existing Map → Create Structure → Run the Four Focus Passes → …
  • Asks to map a codebase
  • SKILL.md covers What I do, When to use me, How it works and Process, plus 3 more sections
  • Calls rg and git

What it does

Codemap is an agent skill from jellydn/my-ai-tools. Create a seven-document architecture map when the user asks to map a codebase.

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files. Compatibility notes: cline, opencode, claude, amp, codex, gemini, cursor, pi

The repository describes itself as: Comprehensive configuration management for AI coding tools - Replicate my complete setup for Claude Code, OpenCode, Amp, Li, Codex and Claude Code Switch with custom… The licence is MIT.

When your agent uses it

  • Asks to map a codebase

Example prompts

  • “/codemap”

Requirements

  • Compatibility (from SKILL.md): cline, opencode, claude, amp, codex, gemini, cursor, pi

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Check Existing Map
  2. Create Structure
  3. Run the Four Focus Passes
  4. Verify Output
  5. Secret Check and Optional Commit
  6. Summary

What it can do on your machine

Read from SKILL.md and the folder at commit 7a06584. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • rg
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    cline, opencode, claude, amp, codex, gemini, cursor, pi

    From compatibility in the SKILL.md frontmatter.

Context cost

Codemap loads about 2.8k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 813 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:179
    e names, not secret values. Do not read `.env` contents or credential files for the map. Use the repository's secret sca

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jellydn/my-ai-tools at commit 7a06584, republished under its MIT licence (© jellydn). 813 words, ~2,838 tokens.

Download SKILL.mdSave it as .claude/skills/codemap/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
codemap
description
Create a seven-document architecture map when the user asks to map a codebase.
compatibility
cline, opencode, claude, amp, codex, gemini, cursor, pi
license
MIT
hint
Use when mapping codebase structure, documenting architecture, or onboarding to a project
user-invocable
true
metadata.audience
all
metadata.workflow
codebase-mapping
metadata.source
glittercowboy/get-shit-done@bdcaab2c752d9a33a1a1ca9acf3a3c81fb991815
metadata.source_path
get-shit-done/workflows/map-codebase.md

Codemap

What I do

Analyze your entire codebase and create 7 comprehensive documentation files in .planning/codebase/:

  • STACK.md - Technologies, dependencies, configuration
  • INTEGRATIONS.md - 3rd party providers, APIs, databases, auth providers
  • ARCHITECTURE.md - System patterns, layers, data flow
  • STRUCTURE.md - Directory layout, key locations, naming conventions
  • CONVENTIONS.md - Code style, patterns, error handling
  • TESTING.md - Framework, structure, mocking, coverage
  • CONCERNS.md - Tech debt, bugs, security, performance issues

When to use me

Use this skill when you need to:

  • Onboard new developers to understand the codebase quickly
  • Plan new features with full context of existing patterns
  • Understand code conventions before making changes
  • Identify technical debt and areas of concern
  • Document the current state of the project

How it works

This skill runs four focus passes. Use parallel file-reading and file-writing workers when the runtime provides them. If suitable workers are unavailable, perform the same passes sequentially in the current context:

  1. Tech → Analyzes stack and integrations → STACK.md, INTEGRATIONS.md
  2. Architecture → Analyzes patterns and structure → ARCHITECTURE.md, STRUCTURE.md
  3. Quality → Analyzes conventions and testing → CONVENTIONS.md, TESTING.md
  4. Concerns → Identifies tech debt and issues → CONCERNS.md

Each pass:

  • Explores the codebase for its focus
  • Uses templates from $SKILL_PATH/templates/
  • Writes documents directly to .planning/codebase/
  • Returns only confirmation (not document contents)

The orchestrator:

  • Creates .planning/codebase/ directory
  • Runs the four passes in parallel only when suitable workers are available
  • Otherwise runs those passes sequentially in the current context
  • Collects confirmations
  • Verifies all documents created
  • Commits the codebase map (if configured)

Process

Scope and Runtime

Accept an optional --paths <p1,p2,...> for an incremental map. Validate repository-relative prefixes before use: reject absolute paths, .. components, and shell metacharacters (;, backticks, $, &, |, <, >). If no supplied path is valid, stop and ask for a corrected scope; do not silently expand to the whole repository. Pass the same normalized scope to every mapper and every sequential pass. Do not interpolate unchecked input into shell commands.

Use the actual current date for all analysis-date placeholders. For scoped refreshes, retain documented information outside the scope and state which prefixes were rechecked.

Use parallel agents only when the runtime supports file-reading and file-writing workers. Do not assume an explore agent can write files or use a browser agent as a code mapper. If suitable workers are unavailable, perform the four focus passes sequentially in the current context, using the same scope and templates. Do not require GSD-specific SDK commands or agent types.

Step 1: Check Existing Map

If .planning/codebase/ already exists, prompt:

.planning/codebase/ already exists. What's next?
1. Refresh - Delete existing and remap codebase
2. Update - Keep existing, only update specific documents
3. Skip - Use existing codebase map as-is
Step 2: Create Structure

Create the output directory:

bash
mkdir -p .planning/codebase
Step 3: Run the Four Focus Passes

Run the passes in parallel only when the runtime supports file-reading and file-writing workers. Otherwise perform them sequentially in the current context. Parallel workers are optional, not required. Each pass must receive the validated scope, current date, and the appropriate template paths from $SKILL_PATH/templates/. The examples below describe assignments, not mandatory API parameter names. While a parallel worker is active, do not duplicate its exploration or write its documents.

Tech Agent:

agent_type: explore
description: Map codebase tech stack
prompt: |
	Focus: tech

	Analyze this codebase for technology stack and external integrations.

	Write these documents to .planning/codebase/:
	- STACK.md - Languages, runtime, frameworks, dependencies, configuration
	- INTEGRATIONS.md - External APIs, databases, auth providers, webhooks

	Use the templates from map-codebase skill. Explore thoroughly.
	Write documents directly. Return confirmation only.

Architecture Agent:

agent_type: explore
description: Map codebase architecture
prompt: |
	Focus: arch

	Analyze this codebase architecture and directory structure.

	Write these documents to .planning/codebase/:
	- ARCHITECTURE.md - Pattern, layers, data flow, abstractions, entry points
	- STRUCTURE.md - Directory layout, key locations, naming conventions

	Use the templates from map-codebase skill. Explore thoroughly.
	Write documents directly. Return confirmation only.

Quality Agent:

agent_type: explore
description: Map codebase conventions
prompt: |
	Focus: quality

	Analyze this codebase for coding conventions and testing patterns.

	Write these documents to .planning/codebase/:
	- CONVENTIONS.md - Code style, naming, patterns, error handling
	- TESTING.md - Framework, structure, mocking, coverage

	Use the templates from map-codebase skill. Explore thoroughly.
	Write documents directly. Return confirmation only.

Concerns Agent:

agent_type: explore
description: Map codebase concerns
prompt: |
	Focus: concerns

	Analyze this codebase for technical debt, known issues, and areas of concern.

	Write this document to .planning/codebase/:
	- CONCERNS.md - Tech debt, bugs, security, performance, fragile areas

	Use the templates from map-codebase skill. Explore thoroughly.
	Write document directly. Return confirmation only.
Show full SKILL.md (326 more words)Show less
Step 4: Verify Output

Wait for every mapper to finish. Check that all seven expected documents exist and each has more than 20 lines; a filename alone is not success. Report missing, short, or failed outputs and repair them before declaring completion. Check that dates are current and scoped output retains unaffected information.

bash
ls -la .planning/codebase/
wc -l .planning/codebase/*.md
Step 5: Secret Check and Optional Commit

Before showing or committing documents, scan for accidentally copied credentials. List configuration paths and environment-variable names, not secret values. Do not read .env contents or credential files for the map. Use the repository's secret scanner when available. A minimal supplementary check is:

bash
rg -l '(sk-[A-Za-z0-9]{20,}|gh[pousr]_[A-Za-z0-9]{36,}|AKIA[A-Z0-9]{16}|xox[baprs]-[A-Za-z0-9-]+|-----BEGIN.*PRIVATE KEY)' .planning/codebase/*.md

This prints filenames only, not matching secret values. A no-match exit status is normal; a scanner error is not a clean scan. If a match is found, stop, redact the content, and recheck before proceeding. Pattern matching is not proof that all secrets are absent; also review excerpts copied from logs and configuration.

If the checks pass, .planning/ is not gitignored, and the user wants to commit:

bash
git add .planning/codebase/*.md
git commit -m "docs: map existing codebase

- STACK.md - Technologies and dependencies
- ARCHITECTURE.md - System design and patterns
- STRUCTURE.md - Directory layout
- CONVENTIONS.md - Code style and patterns
- TESTING.md - Test structure
- INTEGRATIONS.md - External services
- CONCERNS.md - Technical debt and issues"
Step 6: Summary

Present completion summary:

Codebase mapping complete.

Created .planning/codebase/:
- STACK.md ([N] lines) - Technologies and dependencies
- ARCHITECTURE.md ([N] lines) - System design and patterns
- STRUCTURE.md ([N] lines) - Directory layout and organization
- CONVENTIONS.md ([N] lines) - Code style and patterns
- TESTING.md ([N] lines) - Test structure and practices
- INTEGRATIONS.md ([N] lines) - External services and APIs
- CONCERNS.md ([N] lines) - Technical debt and issues

Next steps:
- Review documents: cat .planning/codebase/STACK.md
- Use these as reference when planning features
- Update as codebase evolves

Templates

Templates are located in $SKILL_PATH/templates/:

  • STACK.md.template - Technology stack
  • INTEGRATIONS.md.template - External integrations
  • ARCHITECTURE.md.template - System architecture
  • STRUCTURE.md.template - Directory structure
  • CONVENTIONS.md.template - Coding conventions
  • TESTING.md.template - Testing patterns
  • CONCERNS.md.template - Technical concerns

Each agent reads the appropriate template and fills it in based on codebase exploration.

Agent Guidelines

When spawned as a mapper agent:

Exploration Commands

Helper: Use fd if available, fall back to find

bash
# Define finder helper (fd if available, otherwise find)
_finder() { command -v fd >/dev/null 2>&1 && fd "$@" || find "$@"; }
_rg() { command -v rg >/dev/null 2>&1 && rg "$@" || grep -r "$@"; }

Tech Focus:

bash
# Package manifests
cat package.json pyproject.toml Cargo.toml go.mod 2>/dev/null

# Config files
ls -la *.config.* tsconfig.json 2>/dev/null

# Find SDK/API imports
_rg "import.*stripe|import.*supabase|import.*aws" src/ 2>/dev/null | head -50

Architecture Focus:

bash
# Directory structure (fd is faster and ignores node_modules/.git by default)
_finder -t d . | head -50

# Entry points
_finder -t f "index.*" "main.*" "app.*" src/ app/ 2>/dev/null | head -20

# Import patterns
_rg "^import" src/ 2>/dev/null | head -100

Quality Focus:

bash
# Linting/formatting config
cat .eslintrc* .prettierrc* biome.json 2>/dev/null

# Test files
_finder -t f "\.test\." "\.spec\." 2>/dev/null | head -30

Concerns Focus:

bash
# TODO/FIXME comments
_rg "TODO|FIXME|HACK|XXX" src/ 2>/dev/null | head -50

# Large files (potential complexity)
_finder -t f "\.ts$" -e "\.tsx$" src/ 2>/dev/null | xargs wc -l 2>/dev/null | sort -rn | head -20
Critical Rules
  1. Write documents directly - Use the Write tool, don't return contents
  2. Always include file paths - Every finding needs a file path in backticks
  3. Use the templates - Fill in the template structure exactly
  4. Be thorough - Read actual files, don't guess
  5. Return only confirmation - Response should be ~10 lines with file paths and line counts
  6. Skip commits — orchestrator handles git operations

Inspiration

This skill is inspired by and adapted from glittercowboy/get-shit-done, specifically their map-codebase workflow and gsd-codebase-mapper agent.

© jellydn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files in skills/codemap of jellydn/my-ai-tools.

  • SKILL.md
  • templates/ARCHITECTURE.md.template
  • templates/CONCERNS.md.template
  • templates/CONVENTIONS.md.template
  • templates/INTEGRATIONS.md.template
  • templates/STACK.md.template
  • templates/STRUCTURE.md.template
  • templates/TESTING.md.template

Open the folder on GitHubat commit 7a06584

Compare with similar skills

Codemap next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codemap compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codemap this skilljellydn/my-ai-tools123—~2.8kAutomated safety check: NotesMIT
Token Mapnexu-io/open-design100k—~1.4kAutomated safety check: PassApache-2.0
Maps Geographyasgeirtj/system_prompts_leaks69k—~717Automated safety check: PassCC0-1.0
Feature Maponyx-dot-app/onyx32k—~459Automated safety check: PassCustom licence
Source Mapsthedaviddias/Front-End-Checklist74k—~445Automated safety check: PassMIT
Customer Journey Mapphuryn/pm-skills27k—~816Automated safety check: PassMIT

Similar skills

  • Token Map

    nexu-io/open-design

    Map an extracted Figma / source-code token bag onto the active OD design system, producing a deterministic mapping the generate stage can consume.

    100k GitHub stars~1.4k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Maps Geography

    asgeirtj/system_prompts_leaks

    Accurate maps from real geo data — use for any map, or whenever geography would make a good graphic for a deliverable

    69k GitHub stars~717 tokensUpdated today
    Auto-check passed
  • Feature Map

    onyx-dot-app/onyx

    Use the Onyx feature map (.agents/feature-map/) to learn what a product surface does, the code behind it, and what a change can break.

    32k GitHub stars~459 tokensUpdated today
    Auto-check passed
  • Source Maps

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Provide source maps for production debugging.

    74k GitHub stars~445 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Customer Journey Map

    phuryn/pm-skills

    Create an end-to-end customer journey map with stages, touchpoints, emotions, pain points, and opportunities.

    27k GitHub stars~816 tokensUpdated 23 days ago
    Product & Project ManagementAuto-check passed
  • Context Map

    github/awesome-copilot

    Official

    Generate a map of all files relevant to a task before making changes

    40k GitHub starsUsed in 1 repo~287 tokens
    Auto-check passed

More from jellydn/my-ai-tools

All 33 skills in this repo
  • Babysit PR

    jellydn/my-ai-tools

    A skill your agent uses when monitoring an open GitHub PR for CI failures, review feedback, mergeability, and safe retries or fixes.

    123 GitHub stars~4.1k tokensUpdated today
    Auto-check passed
  • Visual PR

    jellydn/my-ai-tools

    Posts a concise visual outline as a GitHub pull request comment.

    123 GitHub stars~764 tokensUpdated today
    Auto-check passed
  • Qmd Knowledge

    jellydn/my-ai-tools

    Manage project knowledge with qmd — captures learnings, decisions, and conventions

    123 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Prd

    jellydn/my-ai-tools

    Generate Product Requirements Documents from feature ideas — plans specs and requirements

    123 GitHub starsUsed in 4 repos~1.8k tokens
    Auto-check passed
  • Capability Experiments

    jellydn/my-ai-tools

    Build an interactive report or experiment when the user asks to explore model capabilities.

    123 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • PR Review

    jellydn/my-ai-tools

    Fix PR review comments by implementing requested changes. An agent skill from jellydn/my-ai-tools.

    123 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Questions about Codemap

What does Codemap do?

Create a seven-document architecture map when the user asks to map a codebase. Codemap is an agent skill from jellydn/my-ai-tools. Create a seven-document architecture map when the user asks to map a codebase.

When should I use Codemap?

Codemap fits situations like: asks to map a codebase.

How do I install Codemap in Claude Code?

Run `npx skills add jellydn/my-ai-tools --skill codemap -a claude-code`. Or copy the skill folder (skills/codemap in jellydn/my-ai-tools) into .claude/skills/codemap in your project. Claude Code loads it when a task matches its description.

How do I install Codemap in Codex?

Run `npx skills add jellydn/my-ai-tools --skill codemap -a codex`. Or copy the skill folder (skills/codemap in jellydn/my-ai-tools) into .agents/skills/codemap in your project. Codex loads it when a task matches its description.

Can I use Codemap in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jellydn/my-ai-tools --skill codemap -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codemap, .gemini/skills/codemap, .github/skills/codemap and .opencode/skills/codemap in your project.

What does Codemap need to run?

Going by SKILL.md and its folder, Codemap needs the command-line tools its instructions call (rg and git). Compatibility (from SKILL.md): cline, opencode, claude, amp, codex, gemini, cursor, pi.

Does Codemap access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Codemap safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Codemap use?

Codemap is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codemap use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Codemap?

Skills that share tags, products or a category with Codemap: Token Map (nexu-io/open-design, 100k stars), Maps Geography (asgeirtj/system_prompts_leaks, 69k stars), Feature Map (onyx-dot-app/onyx, 32k stars) and Source Maps (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codemap?

jellydn (a GitHub user) maintains it in jellydn/my-ai-tools, which has 123 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 8, 2026.

Source: jellydn/my-ai-tools on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.