hakuto-review

hakuto-review is a skill for Claude Code from teamniteo/hakuto. It costs 0 tokens per session (9,435 once invoked), scanned A, original, MIT.

A source-code review guide for Hakuto websites built with Astro, Tailwind CSS, and shadcn/ui components. It checks the project files and configuration against the rules in the project's CLAUDE.md file.

In plain words
What is it for?
Use it to review one file, changed files, or the whole project. It checks images, components, styling, Cloudflare setup, links, accessibility, rendering performance, and public-file headers.
Why use it?
It catches problems in source code before the site is built, while a separate SEO audit checks the generated HTML. This can reveal issues that are not obvious from viewing the finished page.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the hakuto plugin — 14 skills, 1 command, 1 agent shipped together

Good fit Use it to review one file, changed files, or the whole project. It checks images, components, styling, Cloudflare setup, links, accessibility, rendering performance, and public-file headers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/teamniteo/hakuto/hakuto-review
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.

Any agent
npx skills add teamniteo/hakuto --skill hakuto-review
Clone the repo
git clone --depth 1 https://github.com/teamniteo/hakuto

Made for: Claude Code.

Or install hakuto, the plugin that ships this one along with the rest of its 14 skills, 1 command, 1 agent.

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 hakuto-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/teamniteo/hakuto/hakuto-review/github.svg)](https://agentmods.dev/skills/teamniteo/hakuto/hakuto-review)
Your own site
<a href="https://agentmods.dev/skills/teamniteo/hakuto/hakuto-review"><img src="https://agentmods.dev/badge/skills/teamniteo/hakuto/hakuto-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.

agentmods 80×15 button for hakuto-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/teamniteo/hakuto/hakuto-review"><img src="https://agentmods.dev/badge/skills/teamniteo/hakuto/hakuto-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,435 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00000 $0.09435
Opus 5 $0.00000 $0.04718
Sonnet 5 $0.00000 $0.01887
Haiku 4.5 $0.00000 $0.00944

Measured 9d ago against content hash 0ed50b3f37e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hakuto-review scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> **Verification tip for the user (not for the skill to run):** `curl -I https://{domain}/_astro/{any-file}` on a deployed URL should return the `max-age=31536000, immutable` header. Pingdom's legacy "Add Expires headers
skills/hakuto-review/SKILL.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hakuto Review Skill

Audit Hakuto-built sites against the project's own CLAUDE.md rules.

This skill is the source-side counterpart to seo-audit (which audits the built _dist/ HTML): it catches issues in src/, astro.config.mjs, and src/index.css before build; seo-audit catches what the build produces.

Flexible Scope: parses the user request to choose what to review:

  • Single file: "Review src/pages/index.astro" or "Audit Header.astro"
  • Changed files: "Review my changes" or "Review recent changes"
  • Whole project (default): "Run a Hakuto review", "Audit the site"

Execution Flow

0. Determine Scope

Parse the user prompt:

  • Single file — explicit path mentioned → review only that file plus its directly-imported configs.
  • Changed files — phrases like "my changes" / "recent changes" / "what I edited" → run git diff --name-only HEAD and also include unstaged/untracked under src/ (git status --short). Restrict checks to those files.
  • Whole project (default) — walk src/**/*.{astro,ts,tsx,css}, plus the project's astro.config.mjs, src/index.css, package.json, and tailwind.config.* if present.

If the user names a file that doesn't exist, list nearby candidates and stop.

1. Read Project Context

Always read these first — many checks depend on them:

  • package.json — confirm bun scripts, dependency versions, that tailwind.config.mjs is NOT present.
  • astro.config.mjs — Cloudflare adapter options, experimental.fonts configuration, integrations.
  • src/index.css — verify Tailwind v4 ordering and @theme / @layer base structure.
  • src/layouts/Layout.astro (top ~80 lines) — <Font /> preloads, schema/SEO setup.

2. Initialize Trackers

critical = []   # blocking issues
warnings = []   # should-fix but non-blocking
passed   = []   # checks that passed

Each entry should be { rule, file, line, message } so the report can show file:line.

3. Run Checks

Run every category below that applies to the in-scope files. Each violation cites the CLAUDE.md rule it ties to so future rule changes flow through automatically.

Read the full file on GitHub · 387 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. 9d ago First seen · 387 lines · 0 tokens per session scan A 0ed50b3f37e6

Subscribe to this mod's changes

hakuto-review is a skill published in the GitHub repository teamniteo/hakuto (5 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 9,435 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.