Borrowing it
Nothing to install: this file belongs to WaniWani-AI/sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/WaniWani-AI/sdk/main/.agents/skills/wani-code-review/SKILL.mdgit clone --depth 1 https://github.com/WaniWani-AI/sdkWrote 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.
[](https://agentmods.dev/skills/waniwani-ai/sdk/wani-code-review)<a href="https://agentmods.dev/skills/waniwani-ai/sdk/wani-code-review"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/wani-code-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/waniwani-ai/sdk/wani-code-review"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/wani-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00093 | $0.03407 |
| Opus 5 | $0.00046 | $0.01703 |
| Sonnet 5 | $0.00019 | $0.00681 |
| Haiku 4.5 | $0.00009 | $0.00341 |
Grade A, and why
wani-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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WaniWani Code Review
Quality gate that runs before code reaches human reviewers. Catches the patterns that cause PR feedback loops — type safety violations, missing translations, architectural anti-patterns, and convention drift.
The skill works in three layers: automated tooling checks, a diff analysis against project conventions, and finally a broader code review pass via the code-review:code-review skill.
Step 0: Scope Detection
Before running any checks, determine which repo you're working in:
- Identify the repo from the user's request or from the current working directory / recent file edits
- Find the repo root (look for
.git/,package.json,CLAUDE.md) - Read the repo's own
CLAUDE.mdif one exists — it contains repo-specific conventions, commands, and rules that Layer 1 and Layer 2 checks must respect - If the repo happens to sit inside a larger workspace that has its own root
CLAUDE.mdabove it, read that too for cross-repo rules — but don't assume one exists; many repos are standalone
The repo's CLAUDE.md is the source of truth for:
- Which package manager and commands to use (
bun lintvsnpm run lint) - Which linter/formatter is configured (Biome vs ESLint)
- Repo-specific patterns (data fetching conventions, auth patterns, file structure)
- What tools exist for checking (knip, tsc, translations:build, etc.)
Adapt all Layer 1 commands and Layer 2 checks to the specific repo. The categories below use examples from a Next.js/TypeScript app, but the same principles apply to any repo — adapt to whatever conventions that repo's CLAUDE.md documents.
When to Run
- Before creating a PR or pushing a branch
- Before claiming implementation work is complete
- When the user asks for a review, QA pass, or pre-review check
- Proactively after finishing a multi-file feature implementation
Layer 1: Automated Checks
Run the repo's own tooling and report any failures. Adapt commands based on what the repo's CLAUDE.md documents. These are non-negotiable — fix failures before proceeding to Layer 2.
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.
- 10d ago First seen · 213 lines · 93 tokens per session scan A 76147a6e498d
wani-code-review is a skill published in the GitHub repository WaniWani-AI/sdk (17 stars, last pushed 2d ago), licensed MIT. It adds 93 tokens to every session and 3,407 once invoked, about $0.0005 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.
Other skills, from other repositories
code-review
Review a bounded diff against repository standards and the originating specification.
implement
Implement an agreed specification through existing seams with tests, checks, and review.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.
opencode
Delegate coding to OpenCode CLI (features, PR review).
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.