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 agentmods add instructions/teamniteo/hakuto/claude-mdgit 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/instructions/teamniteo/hakuto/claude-md)<a href="https://agentmods.dev/instructions/teamniteo/hakuto/claude-md"><img src="https://agentmods.dev/badge/instructions/teamniteo/hakuto/claude-md.svg" alt="Measured on agentmods" 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 | $0.00867 | $0.00867 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
hakuto CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`/*`. Verify with `curl -sI <origin>/some/inner/page/`, never `curl -sI <origin>/`, which How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hakuto — plugin development
Hakuto is a Claude Code plugin that scaffolds and builds Astro + Cloudflare sites. This file is memory for working on the plugin. It is not shipped to generated sites.
Two audiences — know which tree you are editing
| Tree | Who loads it | Effect of a change |
|---|---|---|
skills/, agents/, commands/ |
Claude Code, when the plugin is installed | Changes agent behaviour on the next /plugin update hakuto |
scaffold/ |
Copied into an empty directory by /hakuto:init |
Changes what new sites get |
scaffold/CLAUDE.md |
The generated site's agent | A shipped artifact — not this repo's memory |
Existing sites never pick up scaffold changes on their own. Anything they need requires a
versioned entry in the Migration Registry in skills/scaffold-sync/SKILL.md.
Commands
bun is not on PATH — it comes from devenv/direnv. From scaffold/:
export PATH="$PWD/.devenv/profile/bin:$PATH" # or: devenv shell
bun install
bun run check # astro check — type errors
bun run build # → dist/client
bun test test/dev-smoke.test.ts # worker + static serving smoke (4 tests)
Never pipe a bun command straight into tail/head. A missing bun exits 127, but a
pipeline reports the tail's status, so a build that never ran looks like it passed and
&& happily continues. Grep the output for command not found — don't trust the exit code.
Gotchas
- Do not hand-edit
versionin.claude-plugin/plugin.json..github/workflows/bump-plugin-version.ymlbumps the minor on every PR automatically. scaffold/AGENTS.mdis regenerated by every build (@nuasite/agent-summary) and leaves the tree dirty.git checkout scaffold/AGENTS.mdbefore committing unless the change is intended. Its meta-description regexcontent=["']([^"']*)["']truncates at the first apostrophe (0.0.36), so descriptions in that file are unreliable — read the real string out ofdist/client/._headersrules scoped to/match the homepage only./is an exact path, not a prefix, and it fails silently — no build error, no deploy error. Site-wide rules go under/*. Verify withcurl -sI <origin>/some/inner/page/, nevercurl -sI <origin>/, which passes either way.public/andsrc/pages/share a URL namespace.public/robots.txtandsrc/pages/robots.txt.tscannot coexist — deleting thepublic/file is part of the change, not cleanup afterwards.- JSON-LD must not be HTML-escaped.
<script type="application/ld+json">is a raw-text element, so entities are never decoded and'reaches consumers literally. Seescaffold/src/components/Schema.astro— it escapes<only, and that is deliberate.
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.
- 4d ago First seen · 62 lines · 867 tokens per session scan A 36aa4e707544
hakuto CLAUDE.md is an instructions file published in the GitHub repository teamniteo/hakuto (5 stars, last pushed 9d ago), licensed MIT. It adds 867 tokens to every session, about $0.0043 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.