code-review

A skill for sending code to review at important points and handling the review comments. Code review is a check by another person or agent for defects, risks, and maintainability.

In plain words
What is it for?
Use it after implementing a task, before major refactoring, when an approach is unclear, or when security-related code needs review.
Why use it?
It adds a quality check before planned tasks are marked complete and helps surface problems during difficult or security-sensitive work.

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/jpm1118/threadwork/code-review
Any agent
npx skills add JPM1118/Threadwork --skill code-review
Clone the repo
git clone --depth 1 https://github.com/JPM1118/Threadwork

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,768 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 $0.00000 $0.01768
Opus 5 $0.00000 $0.00884
Sonnet 5 $0.00000 $0.00354
Haiku 4.5 $0.00000 $0.00177

Measured yesterday against content hash 3434449155e7, 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.

skills/code-review/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Skill

Dispatch code review subagents at critical points and handle review feedback systematically.

Core Principle

REVIEW EARLY, REVIEW OFTEN

Code review is a quality gate, not a formality. Every task should be reviewed before being marked complete.

When to Request Code Review

Request a code review:

  • After completing each task in a plan
  • Before marking a Beads task as complete
  • When stuck on implementation approach
  • Before significant refactoring
  • When security-sensitive code is involved

Part 1: Requesting Code Review

Step 1: Prepare for Review

Before requesting review, ensure:

# All tests pass
npm test

# Code compiles/builds
npm run build

# Linter passes
npm run lint

# Changes are committed
git status  # Should be clean or only have intended changes

Step 2: Identify the Review Scope

Determine what needs review:

# Get the base commit (before your changes)
git merge-base HEAD origin/main

# Get the current commit
git rev-parse HEAD

# See what changed
git diff <base-commit>..HEAD --stat

Step 3: Dispatch Code Review Subagent

Use the Task tool to dispatch a code-reviewer subagent:

Use the Task tool to dispatch a code review subagent with:

Prompt: "Review the code changes between commits {base-commit} and {head-commit}.

Focus on:
1. Correctness - Does the code do what it's supposed to?
2. Security - Any vulnerabilities introduced?
3. Performance - Any obvious performance issues?
4. Maintainability - Is the code clear and well-structured?
5. Test coverage - Are the changes adequately tested?

For each issue found, categorize as:
- CRITICAL: Must fix before merge (security, data loss, crashes)
- IMPORTANT: Should fix before proceeding (bugs, poor patterns)
- MINOR: Consider fixing later (style, minor improvements)

Provide specific file paths and line numbers for each issue."

Step 4: Receive Review Feedback

The review subagent will return findings in this format:

CODE REVIEW RESULTS
===================

CRITICAL (must fix immediately):
1. [file:line] SQL injection vulnerability in query builder
   → Use parameterized queries instead of string concatenation

IMPORTANT (fix before proceeding):
2. [file:line] Missing null check could cause crash
   → Add validation before accessing property
3. [file:line] Race condition in async handler
   → Use mutex or queue to serialize access

MINOR (address later):
4. [file:line] Variable name could be clearer
   → Rename 'x' to 'userCount'

OVERALL: 1 critical, 2 important, 1 minor issues found

Read the full file on GitHub · 303 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. yesterday First seen · 303 lines · 0 tokens per session scan A 3434449155e7

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository JPM1118/Threadwork (5 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,768 tokens. 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 2026-08-31.

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