review

review is a skill for Claude Code from iroha924/mumei. It costs 216 tokens per session (2,239 once invoked), scanned C, original, MIT.

A read-only code-review workflow for the current Git changes. It examines committed changes since the branch point together with uncommitted changes and reports findings and a verdict.

In plain words
What is it for?
Reviewing a pull request or local diff, checking a change against a supplied specification, and getting findings for a small change that does not need a full planning process.
Why use it?
It provides a thorough review without changing project files, creating commits, or storing review data in the project's planning system.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the mumei plugin — 11 skills, 10 agents, 18 hooks shipped together

Good fit Reviewing a pull request or local diff, checking a change against a supplied specification, and getting findings for a small change that does not need a full planning process.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add iroha924/mumei
Claude Code
/plugin install mumei

Made for: Claude Code.

Or install mumei, the plugin that ships this one along with the rest of its 11 skills, 10 agents, 18 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/skills/iroha924/mumei/review/github.svg)](https://agentmods.dev/skills/iroha924/mumei/review)
Your own site
<a href="https://agentmods.dev/skills/iroha924/mumei/review"><img src="https://agentmods.dev/badge/skills/iroha924/mumei/review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/skills/iroha924/mumei/review"><img src="https://agentmods.dev/badge/skills/iroha924/mumei/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 216 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,239 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00216 $0.02239
Opus 5 $0.00108 $0.01120
Sonnet 5 $0.00043 $0.00448
Haiku 4.5 $0.00022 $0.00224

Measured 10d ago against content hash 1e800782594d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

review scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

trap 'rm -rf "$work_dir"' EXIT
skills/review/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

source "${CLAUDE_PLUGIN_ROOT}/hooks/_lib/detectors.sh"
source "${CLAUDE_PLUGIN_ROOT}/hooks/_lib/detectors-ext.sh"
source "${CLAUDE_PLUGIN_ROOT}/hooks/_lib/review.sh"
source "${CLAUDE_PLUGIN_ROOT}/hooks/_lib/residual.sh"

base_arg="$1"   # optional
spec_arg="$2"   # optional spec file for spec-compliance scope_source

if ! git rev-parse --git-dir >/dev/null 2>&1; then
  echo "not a git repository; /mumei:review needs a git repo." >&2
  exit 0
fi

# Base resolution: explicit arg → origin/HEAD → main → master.
if [[ -n "$base_arg" ]]; then
  base="$base_arg"
else
  base="$(git symbolic-ref --quiet --short refs/remotes/origin/HEAD 2>/dev/null \
    | sed 's#^origin/##')"
  [[ -z "$base" ]] && { git show-ref --verify --quiet refs/heads/main && base="main"; }
  [[ -z "$base" ]] && { git show-ref --verify --quiet refs/heads/master && base="master"; }
fi
if [[ -z "$base" ]]; then
  echo "could not resolve a base ref (no origin/HEAD, main, or master). Pass one explicitly: /mumei:review <base-ref>" >&2
  exit 0
fi

merge_base="$(git merge-base "$base" HEAD 2>/dev/null)"
if [[ -z "$merge_base" ]]; then
  echo "could not compute merge-base against '${base}'." >&2
  exit 0
fi

# Includes pushed commits since the branch point AND uncommitted working-tree
# changes (REQ-27.4).
diff="$(git diff "$merge_base")"
diff_lines="$(printf '%s\n' "$diff" | wc -l | tr -d ' ')"
if [[ -z "$diff" ]]; then
  echo "no changes against ${base} (merge-base ${merge_base}); nothing to review."
  exit 0
fi

Read the full file on GitHub · 193 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 193 lines · 216 tokens per session scan C 1e800782594d

Subscribe to this mod's changes

review is a skill published in the GitHub repository iroha924/mumei (2 stars, last pushed 4d ago), licensed MIT. It adds 216 tokens to every session and 2,239 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

pr-comment

Post friendly review comments to a GitHub PR — prepare locally, preview, then submit as atomic review. Use when: posting code review comments, giving PR feedback, sending inline suggestions. Not for: reading existing reviews (use load-pr-review), creating PRs (use create-pr), PR status (use pr-summary).

sd0xdev/sd0x-harness · 67 tokens

pr-review

PR self-review — review changes, produce checklist, update rules.

sd0xdev/sd0x-harness · 15 tokens

dhpk-gitnexus-refactoring

Safely rename, extract, split, move, or restructure code using the GitNexus graph + coordinated rename. Use when: renaming a symbol across files, extracting a module, splitting a function/service, moving code. Not for: understanding code (use dhpk-gitnexus-exploring), pre-change risk only (use…

hmj1026/dhpk · 112 tokens

dhpk-gitnexus-impact-analysis

Assess the blast radius of a code change via the GitNexus graph. Use when: asking what breaks if you change X, who depends on a symbol, or for a pre-commit safety check. Not for: understanding how code works (use dhpk-gitnexus-exploring), bug tracing (use dhpk-gitnexus-debugging), performing the rename/refactor (use…

hmj1026/dhpk · 110 tokens

storozh

Advisory semantic guard over a changeset manifest before it lands in shared state. Use after a multi-repo session produces a changeset-manifest (mirabilis C1) and before the co-sign push gate — classify each unit's routing against the darwin routing-policy (C3) and NLI-check each unit against the shield corpus (claims…

AlexShchuka/neuro-matrix · 104 tokens

review-before-commit

Run a behavioral self-check before persisting story results. Verifies diff simplicity, scope adherence, and verifiable completion against enso §10 behavioral principles. Use when a story's implementation is complete and ready to close.

usefulmove/enso · 49 tokens