codemap
/codemap
Use for evidence-based codebase documentation. Walks the repo, builds a map of components + responsibilities + interconnections. Output is hand-curated markdown with diagrams. Variants — codemap-fast, codemap-diff, codemap-trust, codemap-export.
- Author
- ialameh ↗
- Repository
- sift-coder ↗
- Licence
- MIT
- Last repository change
- 03.06.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 03.06.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use for evidence-based codebase documentation. Walks the repo, builds a map of components + responsibilities + interconnections. Output is hand-curated markdown with diagrams. Variants — codemap-fast, codemap-diff, codemap-trust, codemap-export.
Original author description
Use for evidence-based codebase documentation. Walks the repo, builds a map of components + responsibilities + interconnections. Output is hand-curated markdown with diagrams. Variants — codemap-fast, codemap-diff, codemap-trust, codemap-export.
How it works
- Variants
- Method (full codemap)
- Output shape
- Rules
- Anti-patterns
- When NOT to use
- Subagent dispatch
- Value over native CC
SKILL.md preview
--- name: codemap description: Use for evidence-based codebase documentation. Walks the repo, builds a map of components + responsibilities + interconnections. Output is hand-curated markdown with diagrams. Variants — codemap-fast, codemap-diff, codemap-trust, codemap-export. --- # codemap Evidence-based codebase doc. Map of what exists, who depends on what, what each module does. Distinguishes confidence levels (proven by tests / inferred from usage / guessed). ## Variants - **codemap** (this skill) — full pass, single repo - **codemap-fast** — quick structural scan, no deep semantics - **codemap-diff** — what changed between two refs (semantically, not just diff) - **codemap-trust** — confidence/risk per module (which areas to trust, which to verify) - **codemap-export** — machine-readable JSON output for tools ## Method (full codemap) 1. **Top-down survey.** Top-level dirs; one-line responsibility for each. 2. **Module inventory.** For each subdir: - LOC - Test coverage - Last-touched dates - Public API (exports / endpoints) - Internal deps (what does it import?) - External deps (npm packages used) 3. **Dependency graph.** Module-level. Mermaid. 4. **Hotspots.** High-churn × low-coverage = risk. 5. **Confidence labels** per module — high (tests + recent), med (works but uncovered), low (works but unstable). 6. **Output: ARCHITECTURE.md or codemap.md.** ## Output shape ``` # Codemap: <repo name> ## Top-level - src/ — code - tests/ — tests - docs/ — hand-curated docs - ... ## Modules ### src/memory/ (5,300 LOC, 96.86% cov, last-touched 2026-04-30) **Responsibility:** persistent memory engine — daemon, MCP server, retrieval **Public API:** - daemon: UDS server for capture - mcp/server: stdio MCP server - storage: dual-backend SQLite **Imports from:** src/core, src/utils **Imported by:** src/services (none yet) **External deps:** better-sqlite3, node-sqlite3-wasm, gpt-tokenizer **Confidence:** high (518 tests, recent) ### src/core/ (200 LOC, 100% cov, last-touched 2026-05-01) **Responsibility:** plugin-wide primitives — config, paths, errors, logger ... ## Dependency graph \`\`\`mermaid graph TD Memory --> Core Memory --> Utils Services --> Core Services --> Utils \`\`\` ## Hotspots - (none — coverage strong, churn matched by tests) ## Confidence summary - High: 4 modules (memory, core, utils, services) - Med: 1 module (formatters — light usage) - Low: 0 modules ``` ## Rules - **Cite LOC + coverage from real measurement,** not estimate. - **Confidence labels with reasoning.** "High because <evidence>". - **Hotspots are evidence-cited** — high churn from `git log`, low coverage from coverage report. - **Don't bloat with file lists.** Module-level, not file-level. ## Anti-patterns - File-by-file listing (use a tree command for that) - Hotspots without evidence (just guessing) - Confidence labels without reasoning - Out-of-date diagrams (use `/codemap-diff` to verify) ## When NOT to use - Tiny repo (manual scan faster) - One module (just read it) - Auto-generated doc tool already in place — augment, don't replace ## Subagent dispatch - `Explore` for the survey - `Bash` for `git log --shortstat`, `wc -l`, coverage extraction - `general-purpose` for the synthesis ## Value over native CC CC will list files. CC won't naturally produce evidence-cited confidence labels, dependency graphs, hotspot analysis. The evidence-based shape IS the value.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · ialameh/sift-coder | 100 | MIT |
| jordancoin/codemap | 100 | MIT |
| AZidan/archflow | 100 | MIT |
| alvinunreal/oh-my-opencode-slim | 100 | MIT |
| jordancoin/codemap | 100 | MIT |
| ils15/copilot-global-config | 100 | MIT |
| azidan/codemap | 100 | MIT |
| jellydn/my-ai-tools | 96 | MIT |
| QDinvest/Code-Map-QD | 96 | MIT |
Database snapshot: 13.11.2026 · package version cfb554cc360e (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100codemap-export
Use to export the codemap as machine-readable JSON for downstream tooling. Same data as /codemap, different format. "Export the codemap", "give me the codemap as JSON". - 90rc-codemap
Builds and refreshes per-directory codemap.md as a cheap structure map. Use before exploring a large repo. Do not use to trace one bug. - 100codemap-trust
Use to assess confidence/risk per module. "Which parts of this codebase can I trust", "where's the risk concentrated". Outputs a trust map with reasoning. - 100codemap-refresh
Use when code has changed since codemap files were generated and the user wants them brought up to date: "refresh", "update the diagrams", "docs are stale". Detects which docs/codemap files are outdated and regenerates only those, preserving manual edits. - 100config-setup
Set up or tune .codemap/config.json so Codemap focuses on code-relevant parts of the repo. Use when config is missing, boilerplate, noisy, or mismatched to the stack. - 90explore
Systematic codebase exploration using codemap's analysis tools. Use when understanding how code works, tracing dependencies, or onboarding to a new area.