Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mickeyyaya/refactoring-skills --skill review-metricsgit clone --depth 1 https://github.com/mickeyyaya/refactoring-skillsWrote 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/mickeyyaya/refactoring-skills/review-metrics)<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/review-metrics"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/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/mickeyyaya/refactoring-skills/review-metrics"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/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 | $0.00050 | $0.03442 |
| Opus 5 | $0.00025 | $0.01721 |
| Sonnet 5 | $0.00010 | $0.00688 |
| Haiku 4.5 | $0.00005 | $0.00344 |
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 9d 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Metrics
Overview
What gets measured gets improved. Without metrics, review quality is invisible: teams cannot tell whether reviews are catching defects before production, whether reviewers are calibrated consistently, or whether the review process is slowing delivery unnecessarily. This skill teaches how to collect, calculate, and act on the six core metrics that reveal review effectiveness.
The goal is not to create a surveillance system for reviewers. The goal is to surface systemic problems — rubber-stamping, over-blocking, calibration drift — so the team can correct them. Metrics are diagnostic tools, not performance scores.
This skill pairs with review-accuracy-calibration (improving individual reviewer calibration), review-efficiency-patterns (optimizing review time allocation), and review-feedback-quality (writing comments that are actionable).
Quick Reference Table
| Metric | Formula | Healthy Range | Warning Signal |
|---|---|---|---|
| Defect Escape Rate | escaped / (found_in_review + escaped) | < 5% | > 10% |
| False Positive Rate | false_positives / total_findings | < 15% | > 25% |
| Review Cycle Time | time from PR opened to approved | < 24h standard PRs | > 48h any PR |
| Comment Resolution Rate | comments_addressed / total_comments | > 90% | < 75% |
| Reviewer Agreement Rate | agreed_findings / total_findings_across_reviewers | > 75% | < 50% |
| Review Coverage | substantive_reviews / total_PRs_merged | > 95% | < 85% |
Defect Escape Rate
What It Measures
The fraction of defects that passed through code review undetected and were found later — in QA, staging, or production. This is the primary lagging indicator of review quality.
Formula
defect_escape_rate = escaped_defects / (found_in_review + escaped_defects)
Where:
escaped_defects= bugs reported post-merge that originated in reviewed codefound_in_review= defects caught and blocked during review before merge
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.
- 9d ago First seen · 317 lines · 50 tokens per session scan A 664c7a3de7c9
review-metrics is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 50 tokens to every session and 3,442 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…