review-metrics

review-metrics is a skill for Claude Code, Codex from mickeyyaya/refactoring-skills. It costs 50 tokens per session (3,442 once invoked), scanned A, original, MIT.

A guide to measuring whether code reviews find defects and remain useful. It explains measures such as escaped defects, incorrect findings, review time, and reviewer agreement.

In plain words
What is it for?
Use it to calculate and improve code-review effectiveness and coverage.
Why use it?
It helps teams see whether reviews catch problems before release or waste time through missed issues and false alarms.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to calculate and improve code-review effectiveness and coverage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mickeyyaya/refactoring-skills/review-metrics
Install

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.

Any agent
npx skills add mickeyyaya/refactoring-skills --skill review-metrics
Clone the repo
git clone --depth 1 https://github.com/mickeyyaya/refactoring-skills

Made for: Claude Code, Codex.

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-metrics

README.md
[![agentmods](https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/review-metrics/github.svg)](https://agentmods.dev/skills/mickeyyaya/refactoring-skills/review-metrics)
Your own site
<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.

agentmods 80×15 button for review-metrics

Your own site · 80×15
<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>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,442 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00050 $0.03442
Opus 5 $0.00025 $0.01721
Sonnet 5 $0.00010 $0.00688
Haiku 4.5 $0.00005 $0.00344

Measured 9d ago against content hash 664c7a3de7c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

skills/review-metrics/SKILL.md · 317 lines

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 code
  • found_in_review = defects caught and blocked during review before merge

Read the full file on GitHub · 317 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. 9d ago First seen · 317 lines · 50 tokens per session scan A 664c7a3de7c9

Subscribe to this mod's changes

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.