review

review is a skill for Claude Code, Codex from huzaifa525/claude-code-optimizer. It costs 21 tokens per session (1,176 once invoked), scanned A, original, MIT.

A two-step method for reviewing code changes. It first checks whether the changes meet the intended requirements, then checks code quality if they do.

In plain words
What is it for?
Use it to review uncommitted or staged changes, compare code with a task or issue, check edge cases, and identify missing tests.
Why use it?
It separates “does this solve the requested problem?” from “is the code well written?”, so quality checks do not hide missing requirements.

Skill for Claude CodeCodex

Part of the claude-code-optimizer plugin — 25 skills, 4 hooks shipped together

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/huzaifa525/claude-code-optimizer/review
Any agent
npx skills add huzaifa525/claude-code-optimizer --skill review
Clone the repo
git clone --depth 1 https://github.com/huzaifa525/claude-code-optimizer

Made for: Claude Code, Codex.

Or install claude-code-optimizer, the plugin that ships this one along with the rest of its 25 skills, 4 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/huzaifa525/claude-code-optimizer/review.svg)](https://agentmods.dev/skills/huzaifa525/claude-code-optimizer/review)
Your own site
<a href="https://agentmods.dev/skills/huzaifa525/claude-code-optimizer/review"><img src="https://agentmods.dev/badge/skills/huzaifa525/claude-code-optimizer/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,176 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 $0.00021 $0.01176
Opus 5 $0.00010 $0.00588
Sonnet 5 $0.00004 $0.00235
Haiku 4.5 $0.00002 $0.00118

Measured 4d ago against content hash ea90434b6953, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

templates/.claude/skills/review/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review all current code changes using two-stage review.

Iron Law

Two stages. In order. No shortcuts. Stage 1 (Spec Compliance) MUST pass before Stage 2 (Code Quality) begins. These are different questions: "Did you build the right thing?" vs "Did you build it well?"

Stage 1: Spec Compliance

Question: Does the code do what was intended?

  1. Get the diff

    git diff
    git diff --cached
    
  2. Identify the intent — What was the goal of these changes? Check:

    • Commit messages
    • Related issue/PR descriptions
    • task_plan.md if it exists
    • Ask the user if intent is unclear
  3. Verify spec compliance:

    • Does the implementation match the stated goal?
    • Are all requirements addressed?
    • Are edge cases from the spec handled?
    • Were the correct files modified (not random unrelated changes)?
    • Do new features have corresponding tests?
  4. Stage 1 Verdict:

    • PASS — Implementation matches intent. Proceed to Stage 2.
    • FAIL — Implementation misses requirements. List what's missing. STOP HERE.

Stage 2: Code Quality

Question: Is the code well-written? (Only after Stage 1 PASSES)

Read each changed file in full to understand context, then check:

Security

  • Hardcoded secrets, API keys, passwords
  • SQL injection, XSS, command injection
  • Unsanitized user input
  • Missing authentication/authorization checks
  • Sensitive data in logs or error messages

Performance

  • N+1 query patterns
  • Missing database indexes on new columns
  • Unnecessary re-renders (React)
  • Large synchronous operations blocking event loop
  • Missing pagination on list endpoints
  • Memory leaks (unclosed resources, event listeners)

Code Quality

  • Dead code or unused imports
  • Duplicated logic (DRY violations)
  • Functions too long (> 50 lines)
  • Deeply nested conditionals (> 3 levels)
  • Magic numbers or hardcoded strings
  • Inconsistent naming with rest of codebase
  • Missing error handling on external calls

Convention Compliance

  • Does it follow existing codebase patterns?
  • Consistent with CLAUDE.md rules?
  • Test coverage for new code?
  • Consistent file/function naming?

Read the full file on GitHub · 144 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. 4d ago First seen · 144 lines · 21 tokens per session scan A ea90434b6953

Subscribe to this mod's changes

review is a skill published in the GitHub repository huzaifa525/claude-code-optimizer (9 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 1,176 once invoked, about $0.0001 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 2026-08-31.