Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Python aicode-complexitycode-healthcode-intelligencecode-qualitydead-codedeveloper-toolsdocumentationgit-analyticsmcpopen-sourcepythonrefactoringstatic-analysistechnical-debt
description: Rank a live change for review using a repo-relative percentile and an auditable supporting diff-shape score. allowed-tools: Bash(repowise risk:*), Read
Repowise Risk
Rank a change (not a file) by size and spread. risk_percentile is its rank
among the repo's recent commits by diff size: not a bug predictor. The response
includes fix_history: the recency-weighted bug-fix record of the files the
change touches, manifests and lockfiles excluded. The supporting 0–10 score measures diff size and spread (named
in score_measures) rather than danger and is not a probability. Pure git +
learned constants: no LLM, no network. A natural pre-merge / PR gate.
Steps
- If
.repowise/doesn't exist: "This repo isn't indexed yet. Run/repowise:initfirst." Stop. - Resolve the target from
$ARGUMENTS, runrepowise risk, and present the size-and-spread percentile, then the fix history (which files carry prior bug fixes), then the score and its drivers.
Choosing the revspec
- No args →
repowise risk(scores uncommitted work, orHEADwhen the tree is clean) - A commit SHA →
repowise risk <sha> - A range / PR / branch →
repowise risk <base>..<head>(e.g.repowise risk main..HEAD)
Useful flags:
--ext .py,.ts— only count changes in those file types-x, --exclude <pattern>— gitignore-style pattern to drop from the diff (repeatable; also honors a.riskignorefile)--format json— machine-readable fix history + score + features + drivers--baseline <n>— how many recent commits to rank the change against (0 disables)-t, --target <path>— score what history says about named files instead of a change (repeatable; reads the index)--path <dir>— point at a different git repo
How this differs from the other risk views
- This command = the whole change ranked against recent repository history.
- For per-file structural reach, missing co-changes, and missing tests,
use the
get_riskMCP tool / thechange-reviewskill. - For per-file health scores, use
/repowise:health.