reviewlisted
Install: claude install-skill hir4ta/mumei
<!--
Role: standalone (detached) review entry point. Shares hooks/_lib/review.sh +
detectors with /mumei:peruse and /mumei:compose Phase 5, but runs without any
feature dir and writes nothing under .mumei.
Principle: fail-open, metadata-quarantined, evidence-gated. Same pipeline math
as the vehicle reviews (mumei_review_apply_advisory_downgrade /
ground_truth_high_count / aggregate_verdict / detached_report).
-->
# Review — standalone diff review
Runs mumei's review engine against an arbitrary diff and reports findings +
verdict in the conversation. No `.mumei` footprint, no commits, no memory writes.
## When to use
- The user wants a strong review of the current changes but is NOT driving the
feature through `/mumei:compose` (spec) or `/mumei:peruse` (plan).
- The user keeps their own spec/SDD and wants mumei's detector + reviewer + gate
pipeline on top of it (pass the spec file as the second argument).
- A change too small to plan, where the user still wants the strongest review.
## When NOT to use
- An active mumei feature is mid-flight and the user wants its lifecycle review —
use `/mumei:compose` (spec) or `/mumei:peruse` (plan) instead.
- The user wants findings persisted / phase advanced / archived — this skill is
intentionally read-only.
## Method
All steps run from the project root in a git repo. The skill never mutates
`.mumei`, never commits, and never writes the ledger or agent memory.
### Step 1 — Resolve base ref and diff
```bash
source "${CLAU