agentleFS
Sign inStart free
cmdr-characmdr-chara/codex-toolkit/skills/repository-intelligence/SKILL.md

repository-intelligence

Skill2 starsChanged 11 days agoMITView on GitHub

Map repository architecture, ownership, dependencies, change impact, and edit conflicts. Use when the task needs evidence about what exists or what a proposed change can affect. Not for implementing changes or diagnosing a runtime failure.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Use this skill for architecture/ownership mapping, dependency boundaries, blast radius, hotspots, change impact, or likely edit conflicts.

    line 12
  2. Distinctive:

    Do not trigger to delegate work, implement the change, diagnose a specific runtime failure, or approve a release.

    line 14
  3. Distinctive:

    Treat scanner output as evidence leads, not ownership truth.

    line 26
  4. Distinctive:

    Do not edit generated/vendor content during mapping.

    line 31
  5. Distinctive:

    Prefer repository-native manifests, imports, registrations, schemas, tests, and build/deploy configuration over naming guesses.

    line 33
  6. Very specific:

    Determine ownership: Use code/config/history/docs evidence.

    line 40
  7. Very specific:

    Report: Use references/evidence-model.md and references/output-schema.md for the evidence/confidence contract.

    line 43
  8. Distinctive:

    If the repository is too large, state a bounded slice and expand breadth-first.

    line 51
  9. Distinctive:

    Stop when the requested boundary, affected surfaces, confidence, and unresolved ambiguity are explicit enough for the next specialist to …

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Repository Intelligence

Build an evidence-backed map of the repository without turning discovery into implementation.

Trigger boundary

Use this skill for architecture/ownership mapping, dependency boundaries, blast radius, hotspots, change impact, or likely edit conflicts.

Do not trigger to delegate work, implement the change, diagnose a specific runtime failure, or approve a release.

Required inputs

Resolve repository root, task/change hypothesis, candidate/base ref when relevant, working-tree state, generated/vendor boundaries, and the decision this map must support.

For a breadth-first signal scan:

python skills/repository-intelligence/scripts/repo_signal_scan.py . --format markdown

Treat scanner output as evidence leads, not ownership truth.

Safety baseline

  • Preserve uncommitted user work and remain read-only.
  • Do not edit generated/vendor content during mapping.
  • Distinguish facts from inference and state confidence.
  • Prefer repository-native manifests, imports, registrations, schemas, tests, and build/deploy configuration over naming guesses.

Workflow

  1. Frame the decision. State what must be mapped and what would change the next action.
  2. Establish state. Record branch/ref, worktree changes, languages/workspaces, generated boundaries, and major entry points. For large/noisy repositories or restartable long tasks, read references/context-loading.md and pack only decision-relevant evidence.
  3. Map components and dependencies. Trace imports/calls, data/contracts, routes/events, build/runtime links, persistence, and operational boundaries.
  4. Determine ownership. Use code/config/history/docs evidence; mark ambiguous ownership rather than inventing it.
  5. Map impact. Identify direct edits, consumers, compatibility surfaces, tests, deployment units, migrations, and generated outputs.
  6. Locate hotspots/conflicts. Highlight high-coupling/stateful areas and likely overlapping write scopes.
  7. Report. Use references/evidence-model.md and references/output-schema.md for the evidence/confidence contract.

Handoffs and interaction boundaries

Hand parallelization to multi-agent-work-coordinator, unknown-defect hunting to bug-finder, concrete failures to debugging-investigator, migrations to codebase-evolution-controller, security-first questions to security-review, and implementation to the owning specialist.

Failure handling

If the repository is too large, state a bounded slice and expand breadth-first. If source/config disagree, report both and identify which governs runtime. If ownership cannot be proven, keep it unknown.

Stop conditions

Stop when the requested boundary, affected surfaces, confidence, and unresolved ambiguity are explicit enough for the next specialist to act safely.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free