Borrowing it
Nothing to install: this file belongs to eph5xx/surfskills.surf. 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/eph5xx/surfskills.surf/main/CLAUDE.mdgit clone --depth 1 https://github.com/eph5xx/surfskills.surfWrote 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/eph5xx/surfskills.surf/claude-md)<a href="https://agentmods.dev/instructions/eph5xx/surfskills.surf/claude-md"><img src="https://agentmods.dev/badge/instructions/eph5xx/surfskills.surf/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/eph5xx/surfskills.surf/claude-md"><img src="https://agentmods.dev/badge/instructions/eph5xx/surfskills.surf/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 | $0.01237 | $0.01237 |
| Opus 5 | $0.00619 | $0.00619 |
| Sonnet 5 | $0.00247 | $0.00247 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
surfskills.surf 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 68 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.
What this is
surfskills.surf — a curated directory of open-source AI agent skills. Astro 5 site deployed to Cloudflare Workers. The catalog is a frozen build-time snapshot (no database at runtime); PostHog handles analytics.
Commands
npm run dev # astro dev; .dev.vars secrets available via Cloudflare platformProxy
npm run build # astro build → dist/
npm run preview # build + wrangler dev — closest to production runtime
npx astro check # typecheck (.astro + .ts); no npm script for it
There is no test suite and no linter configured.
Git workflow
core.hooksPath is set to .githooks, which blocks committing and pushing to main. Always work on a feature branch and PR into main.
Environment / secrets
Two distinct channels — don't mix them up:
.env(from.env.example):PUBLIC_*build-time values, inlined by Vite, read viaimport.meta.env. PostHog key/host..dev.vars(from.dev.vars.example): runtime secrets, read viaAstro.locals.runtime.env(typed insrc/env.d.ts). Production useswrangler secret put+wrangler.jsoncvars.
Architecture
Rendering model: static by default, SSR opt-in
astro.config.mjs keeps output: 'static'; marketing/blog/legal pages and the whole catalog prerender. The catalog is a frozen build-time snapshot (content collections), so /discover, /s/[owner]/[repo], /s/[owner]/[repo]/[skill], sitemap.xml.ts, and llms.txt.ts are all prerender = true — the dynamic /s/** routes enumerate every path via getStaticPaths from the snapshot. The homepage (index.astro) is the lone remaining prerender = false route. URLs never have trailing slashes (trailingSlash: 'never' + build.format: 'file' — both are needed so static output serves /discover without a redirect, matching canonicals/sitemap).
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.
- 10d ago First seen · 68 lines · 1,237 tokens per session scan A de1c257692fa
surfskills.surf CLAUDE.md is an instructions file published in the GitHub repository eph5xx/surfskills.surf (2 stars, last pushed 28d ago), licensed MIT. It adds 1,237 tokens to every session, about $0.0062 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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.
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).
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.