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-code-quality-processgit 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-code-quality-process)<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/review-code-quality-process"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/review-code-quality-process/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-code-quality-process"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/review-code-quality-process.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 | $0.00060 | $0.01758 |
| Opus 5 | $0.00030 | $0.00879 |
| Sonnet 5 | $0.00012 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
review-code-quality-process 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review: Code Quality Process
Overview
Step-oriented code review process: follow phases in order, apply dimension-specific questions, classify findings by severity, deliver a structured summary.
When to Use
- Before approving any pull request
- After detecting code smells suggesting systemic issues (see
detect-code-smells) - When a PR is large or complex and needs structured coverage
Phase 1: Orientation (Before Reading Code)
Answer first:
- What is this PR trying to achieve? (read description)
- Scope? (feature, bug fix, refactor, dependency update)
- Risk surface? (auth, payments, data migrations, public API?)
- Linked tickets or design docs?
- Tests included or deferred?
Checklist:
- PR description states the goal
- Linked ticket referenced
- Single concern per PR
- PR size reviewable (aim < 400 lines changed)
Phase 2: Review Dimensions
Work through each dimension. Log every finding with severity before moving on.
Dimension 1: Logic and Correctness
Questions: Implementation matches requirement? Off-by-one errors? Null/empty inputs handled? Boundary values tested? All conditional branches covered? Concurrent access safe? Algorithm terminates? Type coercions safe?
Red flags: Functions returning undefined on some paths; always-true/false conditions; mutating collection while iterating; missing await on async side effects.
Dimension 2: Security
Questions: User input validated/sanitized? SQL parameterized? HTML escaped? No hardcoded secrets? Auth on every protected endpoint? Authorization (not just authentication) verified? File paths validated? Dependencies pinned, no known CVEs? PII not logged or in error messages? Rate limits on mutations?
Red flags: query("... " + userId) — injection; innerHTML = userInput — XSS; secrets logged; missing auth middleware; require(userProvidedPath) — traversal.
Cross-ref: anti-patterns-catalog Security section.
Dimension 3: Performance
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 · 179 lines · 60 tokens per session scan A 475c5133bd3c
review-code-quality-process is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 60 tokens to every session and 1,758 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…