A general code-review tool that examines a Git diff, file, folder, or pull request for bugs, security risks, performance problems, missing tests, and maintainability issues. A Git diff is the set of changes between two versions of code.

Use it to review uncommitted changes, a branch, a pull request, or selected code. It can review at different effort levels and optionally apply reported fixes.

It helps catch problems before code is shipped or merged. It separates thorough review from cleanup-only or security-only checks and reports concrete findings.

code-review — Skill for Claude Code and Codex by airvalona: A general code-review tool that examines a Git diff…

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/airvalona/antigravity-like-claude-code/code-review

Any agent

npx skills add airvalona/antigravity-like-claude-code --skill code-review

Clone the repo

git clone --depth 1 https://github.com/airvalona/antigravity-like-claude-code

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/airvalona/antigravity-like-claude-code/code-review.svg)](https://agentmods.dev/skills/airvalona/antigravity-like-claude-code/code-review)

Your own site

<a href="https://agentmods.dev/skills/airvalona/antigravity-like-claude-code/code-review"><img src="https://agentmods.dev/badge/skills/airvalona/antigravity-like-claude-code/code-review.svg" alt="Measured on agentmods" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 531 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.00531
Opus 5	$0.00030	$0.00266
Sonnet 5	$0.00012	$0.00106
Haiku 4.5	$0.00006	$0.00053

Measured 5d ago against content hash 3d0033531852, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 5d 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.

skills/code-review/SKILL.md · 46 lines

What it actually says

/code-review — Diff & Bug Review

Port of Claude Code's /code-review. Runs a structured review pass, distinct from simplify (cleanup-only) and security-review (security-only).

Arguments

/code-review — review the current uncommitted diff.
/code-review <target> — review a specific file, folder, or PR number/branch.
/code-review high / low — adjust thoroughness (see Effort below).
/code-review --fix — after reporting, apply the fixes directly.

Steps

Get the diff. Run git diff (or git diff <base>...<branch> for a PR-style review) if no explicit target was given. If a target file/folder was given, read it in full instead.
Review checklist — go through each in order, only reporting genuine findings:
1. Correctness: logic errors, off-by-one, unhandled edge cases, race conditions
2. Security: injection risks, exposed secrets, unsafe deserialization, auth gaps
3. Performance: obvious inefficiencies, N+1 patterns, unnecessary re-renders/loops
4. Test coverage: missing tests for new branches/edge cases
5. Readability/maintainability: naming, duplication, dead code
Effort levels
- low: correctness + security only, skip style commentary
- default: all five checklist items, moderate depth
- high: all five, plus trace through call sites of changed functions to check for downstream breakage
Report format — group findings by severity (Blocking / Should Fix / Nit), each with file:line, a one-line explanation, and a suggested fix. Do not pad the report with praise for unchanged code.
If --fix was passed: apply the Blocking and Should Fix items directly as edits, then summarize what was changed. Leave Nits for the user to decide on.

Notes

This is a review, not a rewrite — don't restructure code beyond what's needed to fix a specific finding.

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.

5d ago First seen · 46 lines · 59 tokens per session scan A 3d0033531852

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository airvalona/antigravity-like-claude-code (2 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 531 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 2026-08-31.

Code review

systematic-debugging

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

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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

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