Borrowing it
Nothing to install: this file belongs to Praeviso/GitShelf. 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/Praeviso/GitShelf/main/CLAUDE.mdgit clone --depth 1 https://github.com/Praeviso/GitShelfWrote 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/praeviso/gitshelf/claude-md)<a href="https://agentmods.dev/instructions/praeviso/gitshelf/claude-md"><img src="https://agentmods.dev/badge/instructions/praeviso/gitshelf/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 5.1 | $0.01533 | $0.01533 |
| Opus 5 | $0.00766 | $0.00766 |
| Sonnet 5 | $0.00307 | $0.00307 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
GitShelf 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 6d 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 — 118 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 Project Is
GitShelf is a serverless content shelf on GitHub Pages. Users upload PDFs, Markdown files, or ZIP archives through the browser admin panel, GitHub Actions processes them into books, documents, or static sites, and the result is a GitHub-hosted reading and publishing site. No backend server — everything runs in GitHub Actions and the browser.
Commands
Development
npm run dev # Vite dev server (serves src/ with docs/ data via middleware)
npm run build # Build frontend to docs/ (generated docs/index.html + docs/assets stay ignored)
npm run preview # Preview production build
Before starting a dev server (npm run dev, npm run preview, or any long-running service), check if the port is already in use and kill the existing process first:
# Check and kill existing process on port 5173 (or whichever port)
lsof -ti:5173 | xargs kill -9 2>/dev/null; npm run dev
Testing
npm test # Vitest: components, hooks, lib tests (jsdom)
npm run test:watch # Vitest watch mode
npm run test:frontend # Frontend behavior tests
python -m unittest discover -s tests/scripts -v # Python pipeline tests
CI
The test.yml workflow runs both Python and JS tests. The content-processing workflows handle uploads and conversions. deploy-pages.yml builds and deploys to GitHub Pages.
Architecture
Two codebases, one repo
- Frontend (Preact + Vite):
src/builds to generateddocs/index.html+docs/assets/. Those build artifacts are ignored by Git and recreated in the Pages deploy workflow. Renders books, articles, and site cards, with markdown-it, syntax highlighting, and KaTeX support. - Pipeline (Python 3.11):
scripts/runs in GitHub Actions. Processes PDFs, Markdown files, and ZIP archives into typed content directories and regenerates catalog data.
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.
- 6d ago First seen · 118 lines · 1,533 tokens per session scan A ce97b27ee2fb
GitShelf CLAUDE.md is an instructions file published in the GitHub repository Praeviso/GitShelf (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,533 tokens to every session, about $0.0077 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).
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.
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.