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.
npx skills add teamniteo/hakuto --skill hakuto-reviewgit clone --depth 1 https://github.com/teamniteo/hakutoWrote 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/teamniteo/hakuto/hakuto-review)<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.
<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>- 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 | $0.00000 | $0.09435 |
| Opus 5 | $0.00000 | $0.04718 |
| Sonnet 5 | $0.00000 | $0.01887 |
| Haiku 4.5 | $0.00000 | $0.00944 |
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 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 HEADand also include unstaged/untracked undersrc/(git status --short). Restrict checks to those files. - Whole project (default) — walk
src/**/*.{astro,ts,tsx,css}, plus the project'sastro.config.mjs,src/index.css,package.json, andtailwind.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— confirmbunscripts, dependency versions, thattailwind.config.mjsis NOT present.astro.config.mjs— Cloudflare adapter options,experimental.fontsconfiguration, integrations.src/index.css— verify Tailwind v4 ordering and@theme/@layer basestructure.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.
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.
- 9d ago First seen · 387 lines · 0 tokens per session scan A 0ed50b3f37e6
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…