review

review is a skill for Claude Code, Codex from tessro/fab. It costs 34 tokens per session (607 once invoked), scanned A, original, MIT.

A code-review checklist and process for checking changes before they are finished. It covers correctness, completeness, tests, code quality, and documentation.

In plain words
What is it for?
Use it after implementing a feature, bug fix, or other code change to inspect the differences, run relevant checks, and decide whether the work is ready.
Why use it?
It provides a separate review of completed work so logic errors, missing tests, unfinished tasks, or unclear code are less likely to remain unnoticed.

Skill for Claude CodeCodex

Part of the fab plugin — 2 skills 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/tessro/fab/review
Any agent
npx skills add tessro/fab --skill review
Clone the repo
git clone --depth 1 https://github.com/tessro/fab

Made for: Claude Code, Codex.

Or install fab, the plugin that ships this one along with the rest of its 2 skills.

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/tessro/fab/review.svg)](https://agentmods.dev/skills/tessro/fab/review)
Your own site
<a href="https://agentmods.dev/skills/tessro/fab/review"><img src="https://agentmods.dev/badge/skills/tessro/fab/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 607 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 $0.00034 $0.00607
Opus 5 $0.00017 $0.00303
Sonnet 5 $0.00007 $0.00121
Haiku 4.5 $0.00003 $0.00061

Measured 4d ago against content hash 6fe593195e3c, 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.

internal/plugin/files/skills/review/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Perform a thorough code review of your changes before marking your task as complete.

When to Use

Run /review after you have finished implementing a feature, bug fix, or any code changes, but BEFORE running fab issue close or fab agent done.

How to Review

Use the Task tool to spawn a sub-agent for code review. This provides a fresh perspective without the context of how the code was written, leading to more objective reviews.

Step 1: Run the Sub-Agent Review

Use the Task tool with subagent_type: "general-purpose" and a prompt like:

Review all code changes (committed and uncommitted) between main and the current worktree. Run `git diff main` to see all changes.

Check each of these areas:

1. **Correctness**: Does the code solve the problem? Are there logic errors or unhandled edge cases?
2. **Completeness**: Is the implementation fully complete? Any TODOs left behind?
3. **Testing**: Are there tests for new functionality? Do existing tests pass?
4. **Code Quality**: Is the code readable and well-organized? Does it follow project conventions?
5. **Documentation**: Are public APIs documented? Do complex algorithms have comments?
6. **Security**: Any potential vulnerabilities (injection, XSS, etc.)? Is user input validated?
7. **Performance**: Any obvious performance issues (N+1 queries, unnecessary loops)?

Run the test suite and any linters configured for the project.

Report:
- Issues found (with file paths and line numbers)
- Suggestions for improvement
- Confidence level that the implementation is complete and correct

Step 2: Address Feedback

CRITICAL: You MUST address all issues found during review before proceeding. Do not skip, defer, or ignore feedback. The review exists to catch problems - ignoring it defeats the purpose.

After the sub-agent completes its review:

  1. Carefully read through ALL issues and suggestions reported
  2. Fix every problem identified - no exceptions
  3. If the sub-agent raised concerns, address each one explicitly
  4. If significant changes were made, run /review again to verify fixes

Read the full file on GitHub · 66 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 · 66 lines · 34 tokens per session scan A 6fe593195e3c

Subscribe to this mod's changes

review is a skill published in the GitHub repository tessro/fab (23 stars, last pushed 7mo ago), licensed MIT. It adds 34 tokens to every session and 607 once invoked, about $0.0002 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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