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 pr-review-workflowgit 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/pr-review-workflow)<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/pr-review-workflow"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/pr-review-workflow/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/pr-review-workflow"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/pr-review-workflow.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 | $0.00055 | $0.03835 |
| Opus 5 | $0.00028 | $0.01917 |
| Sonnet 5 | $0.00011 | $0.00767 |
| Haiku 4.5 | $0.00006 | $0.00383 |
Grade A, and why
pr-review-workflow 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.
This is a copy
86% identical to content-research — 575 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Workflow — End-to-End Orchestrator
Overview
This skill is the orchestrator for the full PR review library. Load it first. It tells you which skills to load at each phase, in what order, and why. A full review using this workflow takes 20–35 minutes for a typical PR. The workflow is designed to be risk-ordered, meaning you stop the review early if a blocker is found rather than wasting time on a PR that cannot be approved.
The library has 67 skills. You do not load all of them for every PR. This skill tells you which ones matter for the PR in front of you.
For a quick one-page reference that maps every review dimension to a deeper skill, see review-cheat-sheet. For a library of concrete end-to-end scenarios using this workflow, see review-walkthroughs.
Quick Reference
| Phase | Time | Skills to Load |
|---|---|---|
| 0: Pre-Review Setup | 2 min | review-efficiency-patterns, review-automation-patterns |
| 1: Triage | 3 min | review-cheat-sheet (Stop-the-PR section), ai-generated-code-review (if AI-assisted) |
| 2: Deep Review | 10–20 min | Language skill, cross-language-review-heuristics, review-code-quality-process, security-patterns-code-review (if security-sensitive) |
| 3: Calibrate | 3 min | review-accuracy-calibration |
| 4: Write Feedback | 5 min | review-feedback-quality |
| 5: Verdict | 1 min | — (decision criteria below) |
Phase 0: Pre-Review Setup (2 min)
Before reading any code, establish context.
Actions:
- Read the PR title and description. Understand the stated intent.
- Check CI status. If the build is red, stop — do not review a failing PR.
- Assess diff size. Count lines changed excluding auto-generated files (lock files, generated protos, vendored code).
- Note the risk profile: Is this a security-sensitive area? Database migration? Public API change? High-traffic path?
Load review-efficiency-patterns to determine time allocation and review ordering based on diff size and risk signals. This skill provides heuristics for when to ask the author to split a PR, how to sequence which files to read first, and how to time-box each dimension.
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 · 333 lines · 55 tokens per session scan A 1441b944d991
pr-review-workflow is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 3,835 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to content-research, differing in 575 lines, and is treated as a copy.
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…