Borrowing it
Nothing to install: this file belongs to jaxx2104/blog. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jaxx2104/blog/main/CLAUDE.mdgit clone --depth 1 https://github.com/jaxx2104/blogWrote 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/jaxx2104/blog/claude-md)<a href="https://agentmods.dev/instructions/jaxx2104/blog/claude-md"><img src="https://agentmods.dev/badge/instructions/jaxx2104/blog/claude-md/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/instructions/jaxx2104/blog/claude-md"><img src="https://agentmods.dev/badge/instructions/jaxx2104/blog/claude-md.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 | $0.01951 | $0.01951 |
| Opus 5.5 | $0.00780 | $0.00780 |
| Sonnet 5.5 | $0.00390 | $0.00390 |
| Haiku 4.5 | $0.00195 | $0.00195 |
Grade C, and why
blog CLAUDE.md scanned grade C with 2 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`rm -rf <output-dir> && pnpm test` before pushing. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s localhost:PORT/ | grep -ao 'style-[^"]*\.css'` has to match How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
Development
pnpm dev # Start Vite dev server (TanStack Start)
pnpm build # Run velite build + vite build (prerender to dist/client/)
pnpm start # Serve dist/ via vite preview
pnpm deploy # Alias for pnpm build
pnpm optimize:images # Re-encode content/posts images (pass --dry-run first)
pnpm build reaches the network to fill data/ogp-cache.json for any link
card URL it has not seen, and to re-check entries older than 90 days. Set
OGP_OFFLINE=1 to render fallback cards instead, or OGP_OFFLINE=strict to
fail the build on a cache miss. CI builds with strict, so a post that adds a
link needs the cache entry your local build produced to be committed with it.
A URL that will never resolve goes in data/ogp-unfetchable.json instead.
Code Quality
pnpm lint # Run Biome with --write
pnpm lint:ci # Run Biome ci (no fixes; fails on warnings/errors)
pnpm lint:text # Check Japanese text in blog posts (textlint)
pnpm lint:textfix # Auto-fix Japanese text issues
pnpm test # Run unit tests (vitest run)
pnpm test:types # Run TypeScript type checking (tsc -p)
pnpm format # Format code with Biome
Stack
A statically prerendered blog: TanStack Start (Vite + React) over a Velite +
Zod content layer, CSS Modules, Biome, Vitest, pnpm, deployed to Cloudflare
Pages. package.json is the source of truth for versions; what is worth
knowing beyond it:
- Vite 8 bundles with rolldown, not rollup. Chunking behaves differently — see the pitfalls below before touching chunk configuration
- CSS ships as one asset (
build.cssCodeSplit: false). Code-split CSS drops the previous route's stylesheet during SPA navigation, leaving the navi and footer unstyled until a hard reload - Velite writes two things:
.velite/for the build to read, andpublic/content/for the client to fetch. Syntax highlighting (shiki + rehype-pretty-code) happens there, so it never reaches the browser - Specs live next to their source as
*.test.ts/*.test.tsx
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.
- 2mo ago First seen · 140 lines · 1,951 tokens per session scan C 1136a66fa61d
blog CLAUDE.md is an instructions file published in the GitHub repository jaxx2104/blog (5 stars, last pushed 6d ago), licensed MIT. It adds 1,951 tokens to every session, about $0.0078 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
blog CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blog CLAUDE.mdjaxx2104/blog | Instructions file | 5 | 6d ago | MIT | C | 1,951 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |