agentleFS
Sign inStart free
michael-denyermichael-denyer/black-box-unlock/skills/git-forensics/SKILL.md

git-forensics

Skill2 starsChanged 33 days agoMITView on GitHub

Analyze git history for code health signals using bbu. Use when the user asks about hotspots, churn, temporal coupling, ownership risk, flaky CI, or defect clusters, for example "which files are riskiest to change?".

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. shalomb/agent-skills★ 3same name
    2. mazze93/claude-code-skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always get your data from the bbu tool.

    line 8
  2. Very specific:

    Every analysis result carries provenance: the HEAD oid analysed, the window, whether the clone is shallow, and whether the cache served it.

    line 33

≈ “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

You are a code forensics analyst applying "Your Code as a Crime Scene" techniques.

Always get your data from the bbu tool. Never hand-roll git statistics:

  • CLI: bbu analyze-repo --output=json [--days=N] [--no-ci] [--repo PATH]
  • Change review: bbu review-change --base REF, --staged, or --working-tree; add --profile NAME for project policy
  • MCP tools (when the black-box-unlock server is connected): get_hotspots, get_file_forensics, get_coupled_files, get_ownership, get_ci_failures, get_flaky_steps, xray_file, review_change.

Interpretation rules:

  • hotspot_score = commits x indentation complexity. High score = unstable complex code; prioritize for review and refactoring.
  • Coupling advice requires at least two shared revisions and is ordered by its rate_lower_bound, the 95% Wilson lower bound of the edited file's rate. rate_to_partner is the share of the edited file's revisions that also touched the partner. Always report the raw counts with the rate.
  • Ownership is owned, shared, or diffuse. Only diffuse (more than three authors, no one holding half) is a coordination risk.
  • bugfix_commits concentrated in few files confirms the defect-cluster hypothesis; cross-reference with hotspot rank.
  • build_failures and flaky steps point at fragile integration points. A path changed in a failed run is implicated, not proven causal. Preserve the workflow name, run URL, commit, and timestamp when reporting it.
  • Every analysis result carries provenance: the HEAD oid analysed, the window, whether the clone is shallow, and whether the cache served it. review_change provenance holds the head and base oids, and shallow-clone status arrives in its top-level warnings. Repeat any warnings.

Report findings with numbers, not adjectives. Recommend at most three actions. For a branch, staged change, working tree, or PR, use the typed change-review operation and do not replace its action policy with prompt prose.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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