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/crazywillbear/blogman/claude-mdgit clone --depth 1 https://github.com/CrazyWillBear/blogmanWrote 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/crazywillbear/blogman/claude-md)<a href="https://agentmods.dev/instructions/crazywillbear/blogman/claude-md"><img src="https://agentmods.dev/badge/instructions/crazywillbear/blogman/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 | $0.00349 | $0.00349 |
| Opus 5 | $0.00175 | $0.00175 |
| Sonnet 5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
blogman CLAUDE.md 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 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.
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.
What it actually says
CLAUDE.md
Blogman v2 — a reusable blog engine: Next.js (App Router, TypeScript),
Tailwind v4, Drizzle ORM on Neon Postgres, Auth.js (GitHub) guarding the
/admin editor.
Rules
- Frontend work: invoke the
frontend-designskill before any frontend change. The design language is dark academia (palette/type/ornament inapp/globals.css) — stay inside it. - Done-check (run before declaring any change done):
npm run check(lint + typecheck + Vitest) andnpm run build. - Blog identity lives in
blog.config.ts; secrets in.env.local(see.env.example). Never hardcode either.
Layout
app/— routes:/(search/sort homepage),/[slug](post),/admin/**(auth-guarded editor),/api/auth/[...nextauth].lib/—posts.ts(queries),markdown.ts(remark/rehype pipeline),sort.ts(client-safe sort constants — keep db imports out of anything a client component touches),allowlist.ts(admin allowlist).db/— Drizzle schema + migrations (npm run db:generate,db:migrate).
Conventions
- Conventional commits.
- Tests colocated as
*.test.ts; new logic gets Vitest coverage. - Old v1 slugs (
Title-With-Dashes, case preserved) must keep resolving — don't "normalize" existing slugs.
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 · 32 lines · 349 tokens per session scan A 6636ab94e220
blogman CLAUDE.md is an instructions file published in the GitHub repository CrazyWillBear/blogman (11 stars, last pushed 2mo ago), licensed MIT. It adds 349 tokens to every session, about $0.0017 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 instructions, from other repositories
quireink CLAUDE.md
Claude Code instructions for joiha-steven/quireink, covering quire ink, verify, read first, debug router — a symptom, and the files to open first and hard rules — each one is a bug that already shipped.
Ghost AGENTS.md
AGENTS.md instructions for TryGhost/Ghost, covering agents.md, required workflow, repository skills and task routing and important warnings.
zrlog AGENTS.md
AGENTS.md instructions for 94fzb/zrlog, covering agents.md, 工程定位, 目录职责, 必读文档 and 构建与验证.
freek.dev CLAUDE.md
Claude Code instructions for spatie/freek.dev, covering laravel boost guidelines, foundational context, skills activation, conventions and verification scripts.
blog AGENTS.md
Instructions for sabertaz/blog, covering agents.md, quick start, first time setup, development and common tasks.
enferno AGENTS.md
Instructions for level09/enferno, covering agents.md, framework overview, project structure, development commands and setup & installation.