code-review

A guide for reviewing pull requests, commits, or code changes for important engineering problems before merging them.

In plain words
What is it for?
Use it to assess changed code, identify merge risks, and report findings with enough context for the author to fix them.
Why use it?
It focuses attention on defects involving correctness, security, performance, reliability, compatibility, testing, and observability instead of minor style issues.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/fiveonecode/agent-skills/code-review
Any agent
npx skills add fiveonecode/agent-skills --skill code-review
Clone the repo
git clone --depth 1 https://github.com/fiveonecode/agent-skills

Made for: Claude Code, Codex.

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 891 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00078 $0.00891
Opus 5 $0.00039 $0.00445
Sonnet 5 $0.00016 $0.00178
Haiku 4.5 $0.00008 $0.00089

Measured yesterday against content hash 5d38a08f3697, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review 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 yesterday.

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.

code-review/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Overview

Run a high-signal review with a low false-positive rate. Prioritize issues the author would likely fix immediately if they knew.

Required Inputs

  • Changed code scope (PR, commit range, patch, or diff).
  • Author intent (PR title/description, ticket, or summary).
  • Project-specific rules if provided. Treat explicit local rules as higher priority than generic guidance.

If intent or scope is missing, infer conservatively and state assumptions.

Workflow

1. Triage Scope

  • Confirm what changed and where.
  • Focus on changed code first; use nearby context only when needed to validate impact.
  • Ignore mechanical noise unless it introduces risk.

2. Run Multi-Pass Analysis

  • Pass A: Compile/runtime correctness (syntax, type use, imports, control flow).
  • Pass B: Security and data integrity (auth, validation, secret handling, unsafe defaults).
  • Pass C: Reliability and performance (resource leaks, blocking calls, hot-path regressions).
  • Pass D: API and compatibility impact (breaking behavior, migrations, version assumptions).
  • Pass E: Test and observability coverage for changed behavior.

Use independent perspectives when possible, then merge only validated findings.

3. Qualify Each Candidate Issue

Keep a finding only if all checks pass:

  • Introduced by this change (not pre-existing debt).
  • Evidence-backed and reproducible from available context.
  • Meaningful impact on correctness, security, performance, reliability, or maintainability.
  • Discrete and actionable with a clear fix direction.
  • Not an intentional behavior change by the author.
  • Likely something the author would want to fix now.

If confidence is low, drop the finding or convert it into an explicit question.

4. Assign Severity and Confidence

Use priority tags:

  • P0: Release-blocking or universally critical failure.
  • P1: Urgent and should be fixed in the next cycle.
  • P2: Important but not immediately blocking.
  • P3: Low urgency but valid and actionable.

Read the full file on GitHub · 119 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 119 lines · 78 tokens per session scan A 5d38a08f3697

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository fiveonecode/agent-skills (19 stars, last pushed 10d ago), licensed MIT. It adds 78 tokens to every session and 891 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens