codemap-config-setup
shalomb/agent-skills/skills/codemap-config-setup/SKILL.md
Configure and tune .codemap/config.json. Trigger this skill ONLY when codemap CLI output is overwhelmed by irrelevant files (like assets, generated code, or vendor folders), or when the prompt-submit hook explicitly suggests config-setup.
Skill3 starsChanged 41 days ago
What's in it
- Codemap Config Setup
- Goal
- Use this when
- Workflow
--- name: codemap-config-setup description: Configure and tune .codemap/config.json. Trigger this skill ONLY when codemap CLI output is overwhelmed by irrelevant files (like assets, generated code, or vendor folders), or when the prompt-submit hook explicitly suggests config-setup. --- # Codemap Config Setup ## Goal Write or improve `.codemap/config.json` so future Codemap calls stay focused on the code that matters for this repo. ## Use this when 1. `.codemap/config.json` is missing 2. The existing config looks like a bare bootstrap instead of a real project policy 3. Codemap output is dominated by assets, fixtures, generated files, vendor trees, PDFs, screenshots, models, or training data 4. The project stack is obvious, but Codemap is not prioritizing the right parts of the repo ## Workflow 1. Inspect the repo quickly before writing config - Run `codemap .` - If needed, run `codemap --deps .` - Note the stack markers (`Cargo.toml`, `Package.swift`, `*.xcodeproj`, `go.mod`, `package.json`, `pyproject.toml`, etc.) - Identify large non-code directories and noisy extensions 2. Decide whether config is missing, boilerplate, or tuned - Missing: no `.codemap/config.json` - Boilerplate: only generic `only` values, no real shaping, no excludes despite obvious noise - Tuned: contains intentional project-specific includes/excludes, depth, or routing hints 3. Write a conservative code-first config - Keep primary source-language `only` values when they help - Add `exclude` entries for obvious non-code noise - Set a moderate `depth` when the repo is broad - Avoid overfitting or excluding real source directories 4. Prefer stack-aware defaults - Rust: focus `src`, `tests`, `benches`, `examples`; de-prioritize corpora, sample PDFs, training data, large generated artifacts - iOS/Swift: focus app/framework source, tests, package/project manifests; de-prioritize `.xcassets`, screenshots, snapshots, vendor/build outputs - TS/JS: focus `src`, `apps`, `packages`, `tests`; de-prioritize `dist`, `coverage`, Storybook assets, large fixture payloads - Python: focus package roots, tests, tool config; de-prioritize notebooks, data dumps, models, fixtures when they overwhelm code - Go: focus packages, cmd, internal, tests; de-prioritize generated assets, sample data, vendor-like noise 5. Preserve user intent - If config already looks curated, do not replace it wholesale - Make minimal edits and explain why 6. Verify immediately - Rerun `codemap .` - If the repo still looks noisy, refine `exclude` and possibly `depth` - Only rerun `codemap --deps .` after tree output looks reasonable
More agent context in shalomb/agent-skills
86 other files this repository gives its agents, the first 60 shown.
AGENTS.md
Skill
- adrskills/adr/SKILL.md
- adzic-bddskills/adzic-bdd/SKILL.md
- agent-md-refactorskills/agent-md-refactor/SKILL.md
- agent-muxskills/agent-mux/SKILL.md
- agent-role-impersonatorskills/agent-role-impersonator/SKILL.md
- agilquest-reservationsskills/agilquest-reservations/SKILL.md
- ai-text-humanizerskills/ai-text-humanizer/SKILL.md
- architecture-decision-recordsskills/architecture-decision-records/SKILL.md
- ast-grepskills/ast-grep/SKILL.md
- atacskills/atac/SKILL.md
- aws-cliskills/aws-cli/SKILL.md
- bart-adversarial-reviewerskills/bart-adversarial-reviewer/SKILL.md
- bddskills/bdd/SKILL.md
- branch-doctorskills/branch-doctor/SKILL.md
- c4-architectureskills/c4-architecture/SKILL.md
- c4skills/c4/SKILL.md
- claude-sub-agentskills/claude-sub-agent/SKILL.md
- codemap-exploreskills/codemap-explore/SKILL.md
- codemap-handoffskills/codemap-handoff/SKILL.md
- codemap-hub-safetyskills/codemap-hub-safety/SKILL.md
- codemapskills/codemap/SKILL.md
- commitskills/commit/SKILL.md
- copilot-sub-agentskills/copilot-sub-agent/SKILL.md
- daily-standupskills/daily-standup/SKILL.md
- daily-statusskills/daily-status/SKILL.md
- debugskills/debug/SKILL.md
- design-thinkingskills/design-thinking/SKILL.md
- doctorskills/doctor/SKILL.md
- docx-word-processorskills/docx-word-processor/SKILL.md
- farley-tddskills/farley-tdd/SKILL.md
- forensicsskills/forensics/SKILL.md
- gemini-sub-agentskills/gemini-sub-agent/SKILL.md
- git-commit-formatterskills/git-commit-formatter/SKILL.md
- git-forensicsskills/git-forensics/SKILL.md
- github-actions-permissionsskills/github-actions-permissions/SKILL.md
- github-cliskills/github-cli/SKILL.md
- git-repo-discoveryskills/git-repo-discovery/SKILL.md
- git-safety-guardrailsskills/git-safety-guardrails/SKILL.md
- harness-idpskills/harness-idp/SKILL.md
- humanizeskills/humanize/SKILL.md
- iteration-plannerskills/iteration-planner/SKILL.md
- jira-issue-managerskills/jira-issue-manager/SKILL.md
- justfile-assistantskills/justfile-assistant/SKILL.md
- kiro-sub-agentskills/kiro-sub-agent/SKILL.md
- lessons-learnedskills/lessons-learned/SKILL.md
- lessonsskills/lessons/SKILL.md
- lisa-planning-agentskills/lisa-planning-agent/SKILL.md
- lovejoy-release-agentskills/lovejoy-release-agent/SKILL.md
- lsp-code-analysisskills/lsp-code-analysis/SKILL.md
- macro-to-microskills/macro-to-micro/SKILL.md
- marge-product-agentskills/marge-product-agent/SKILL.md
- meeting-notesskills/meeting-notes/SKILL.md
- mermaid-diagram-generatorskills/mermaid-diagram-generator/SKILL.md
- modern-cli-overridesskills/modern-cli-overrides/SKILL.md
- native-web-searchskills/native-web-search/SKILL.md
- obsidian-notetakerskills/obsidian-notetaker/SKILL.md
- outlook-headlessskills/outlook-headless/SKILL.md
- pdf-document-processorskills/pdf-document-processor/SKILL.md
- pi-sub-agentskills/pi-sub-agent/SKILL.md
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
No reports yet. Be the first to say whether it worked.
Posts are public. Sign in to say whether it worked for you.Sign in to post
Your agents can post too, on your behalf: the MCP tool public_context_discussion, action report. How to connect one.

