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 prelaunch-checklistgit 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/prelaunch-checklist)<a href="https://agentmods.dev/skills/teamniteo/hakuto/prelaunch-checklist"><img src="https://agentmods.dev/badge/skills/teamniteo/hakuto/prelaunch-checklist/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/prelaunch-checklist"><img src="https://agentmods.dev/badge/skills/teamniteo/hakuto/prelaunch-checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00133 | $0.03500 |
| Opus 5 | $0.00067 | $0.01750 |
| Sonnet 5 | $0.00027 | $0.00700 |
| Haiku 4.5 | $0.00013 | $0.00350 |
Grade A, and why
prelaunch-checklist 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 8d 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.
- **Enable Markdown for Agents** (Cloudflare dashboard → AI Crawl Control → Markdown for Agents, or `dash.cloudflare.com/?to=/:account/:zone/ai`). Cloudflare converts HTML to markdown on the fly for clients sending `Acce How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prelaunch Checklist Skill
Validate a Hakuto site is ready to go live. Report findings only — user requests fixes separately.
Run when the user says any of:
- "Run prelaunch checklist"
- "Is the site ready to ship?"
- "Pre-launch check"
- "Check before launch"
Execution Flow
1. Read project files in parallel
Read these into context up front:
wrangler.tomlpackage.jsonsrc/layouts/Layout.astrosrc/components/Footer.astro(if it exists; otherwise globsrc/components/*Footer*)astro.config.mjs
Glob for:
src/pages/privacy.*,src/pages/terms.*,src/pages/cookies.*(any extension)src/components/**/*Form*.astro,src/components/**/*Form*.tsxsrc/pages/**/*.astro(for the form scan in check #4)worker/index.js(for form handler in check #4)
2. Initialize trackers
critical = []
warnings = []
passed = []
manual_reminders = []
gates = [] # SEO + source-review confirmations
3. Run automated checks
Check 1 — wrangler.toml customized
In wrangler.toml:
name = 'hakuto-site'→ critical: "wrangler.tomlnameis still the scaffold default. Change to your project's worker name."mainmissing → critical- All
[[routes]]blocks still commented out AND no other custom-domain config → warning: "No custom domain in wrangler.toml. If you plan to use a custom domain via routes, uncomment the[[routes]]block. (Skip this if you're configuring the domain in the Cloudflare dashboard instead.)" - Otherwise → pass
Check 2 — compatibility_date freshness
Parse compatibility_date in wrangler.toml. If older than 12 months from today → warning: "compatibility_date is X months old; consider bumping for newer Workers runtime features."
Check 3 — package.json name
In package.json, if "name": "hakuto-site" → warning: "package.json name is still the scaffold default."
Check 4 — Forms wired
Grep src/ for <form (case-insensitive). For each match:
- Find the enclosing component file.
- Inspect the form's submission target (action attribute, fetch URL in script, or worker handler reference).
- Critical if any of:
action="#"oraction=""oraction="/api/placeholder"or similar dummy values- Submits via
fetch("/api/...")to a path that has no corresponding handler inworker/index.js - Recipient email/destination is a placeholder (
[email protected],your-email@,[email protected])
- Pass if a real endpoint and real recipient are wired.
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.
- 8d ago First seen · 279 lines · 133 tokens per session scan A 5e88c0570fc4
prelaunch-checklist is a skill published in the GitHub repository teamniteo/hakuto (5 stars, last pushed 7d ago), licensed MIT. It adds 133 tokens to every session and 3,500 once invoked, about $0.0007 per session on Opus 5. 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.