Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/b4tchkn/claude-review-metricsnpx agentmods add skills/b4tchkn/claude-review-metrics/review-metricsWrote 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.
[](https://agentmods.dev/skills/b4tchkn/claude-review-metrics/review-metrics)<a href="https://agentmods.dev/skills/b4tchkn/claude-review-metrics/review-metrics"><img src="https://agentmods.dev/badge/skills/b4tchkn/claude-review-metrics/review-metrics/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.
<a href="https://agentmods.dev/skills/b4tchkn/claude-review-metrics/review-metrics"><img src="https://agentmods.dev/badge/skills/b4tchkn/claude-review-metrics/review-metrics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00101 | $0.01040 |
| Opus 5 | $0.00051 | $0.00520 |
| Sonnet 5 | $0.00020 | $0.00208 |
| Haiku 4.5 | $0.00010 | $0.00104 |
Grade A, and why
review-metrics scanned grade A with 0 findings 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Metrics
Collect and analyze team review metrics from GitHub pull requests.
Invocation
Run via the unified dispatch script:
../../scripts/dispatch.sh $0 $1
Where $0 is the period (default: week) and $1 is the command.
If no command is provided, all rankings are shown.
Examples
| Command | Dispatch |
|---|---|
/review-metrics |
../../scripts/dispatch.sh week |
/review-metrics last-week |
../../scripts/dispatch.sh last-week |
/review-metrics month comments |
../../scripts/dispatch.sh month comments |
/review-metrics last-week response-time |
../../scripts/dispatch.sh last-week response-time |
/review-metrics last-week fix-time |
../../scripts/dispatch.sh last-week fix-time |
/review-metrics last-week bottleneck |
../../scripts/dispatch.sh last-week bottleneck |
/review-metrics stuck |
../../scripts/dispatch.sh week stuck |
/review-metrics last-week reviewer-load |
../../scripts/dispatch.sh last-week reviewer-load |
/review-metrics last-week cycles |
../../scripts/dispatch.sh last-week cycles |
/review-metrics last-week pr-size |
../../scripts/dispatch.sh last-week pr-size |
Available Scripts
Ranking Scripts (Top 3)
| Script | Description |
|---|---|
collect-metrics.sh |
All rankings combined |
ranking-comments.sh |
Review comments ranking only |
ranking-reviewed.sh |
Reviewed PRs ranking only |
ranking-approved.sh |
Approved PRs ranking only |
ranking-response-time.sh |
Response time ranking only |
ranking-fix-time.sh |
Fix time ranking (comment to commit) |
Analysis Scripts (Team-wide)
| Script | Description |
|---|---|
analysis-bottleneck.sh |
PR lifecycle phase breakdown (wait/review/merge) with p50/p90 |
analysis-stuck-prs.sh |
Currently stuck PRs needing attention |
analysis-reviewer-load.sh |
Full team review workload distribution |
analysis-review-cycles.sh |
Review round counts and change-request patterns |
analysis-pr-size.sh |
PR size vs review speed correlation |
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.
- 12d ago First seen · 109 lines · 101 tokens per session scan A ae79693abede
review-metrics is a skill published in the GitHub repository b4tchkn/claude-review-metrics (1 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 101 tokens to every session and 1,040 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
generic-react-code-reviewer
Review React/TypeScript code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Enforces TypeScript strict mode, GPU-accelerated animations, WCAG AA accessibility, bundle size limits, and surgical simplicity. Use when completing features, before commits, or…
generic-fullstack-code-reviewer
Review full-stack code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md compliance. Enforces TypeScript strict mode, input validation, GPU-accelerated animations, and design system consistency. Use when completing features, before commits, or reviewing pull requests.
generic-static-code-reviewer
Review static site code for bugs, security issues, performance problems, accessibility gaps, and CLAUDE.md compliance. Enforces pure HTML/CSS/JS standards, minimal page weight, mobile-first design. Use when completing features, before commits, or reviewing changes.
unity-reviewer
Use when reviewing Unity C# code changes — checks for runtime-breaking bugs, performance anti-patterns, and maintainability issues. Provides severity-tiered review organized as Critical, Performance, and Style.
generic-code-reviewer
Review code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Supports any tech stack - HTML/CSS/JS, React, TypeScript, Node.js, Python, NestJS, Next.js, and more. Use when completing features, before commits, or reviewing pull requests.
audit
Read-only quality gate that audits already-built work against its stated requirement and Definition of Done before it is allowed to move to 2done/. Produces a severity-ranked decision proposal (BLOCKER/MAJOR/MINOR/NIT) with evidence, never a fix. Use when an item is claimed complete, before moving anything to 2done/…