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/babosina/librarymcp/claude-mdgit clone --depth 1 https://github.com/babosina/libraryMCPWrote 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/babosina/librarymcp/claude-md)<a href="https://agentmods.dev/instructions/babosina/librarymcp/claude-md"><img src="https://agentmods.dev/badge/instructions/babosina/librarymcp/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 | $0.00503 | $0.00503 |
| Opus 5 | $0.00251 | $0.00251 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
libraryMCP 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
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
Install dependencies:
uv sync
Run the server:
uv run uvicorn backend.main:app --reload
Seed the database with sample data:
uv run python backend/seed.py
There is no test suite configured. API endpoints can be tested via:
- Swagger UI at
http://127.0.0.1:8000/docswhen server is running LibraryMCP.postman_collection.json(import into Postman)test_main.http(REST client file)
Architecture
The backend follows a four-layer architecture:
-
Routers (
backend/routers/): HTTP handlers for books, members, and loans. Each router enforces business rules (e.g., blocking deletion when active loans exist, preventing duplicate borrows) before delegating to CRUD. -
CRUD (
backend/crud.py): All database queries and write operations. Contains fine calculation logic ($0.50/day overdue). This is the single place for data access—routers never query the DB directly. -
Models (
backend/models.py): SQLAlchemy ORM models:Book,Member,Loan.Loanhas FK relationships to bothBookandMember.Book.available_copiesis decremented/incremented on borrow/return. -
Schemas (
backend/schemas.py): Pydantic models for request/response validation. Email validation uses a regex pattern defined here.
Database (backend/database.py): SQLAlchemy session factory with FastAPI dependency injection (get_db). SQLite file (library.db) is auto-created on startup via Base.metadata.create_all() in main.py.
Key business rules enforced in routers:
- Books cannot be deleted if they have active loans
- Members cannot be deactivated or deleted if they have active loans or unpaid fines
- A member cannot borrow the same book twice simultaneously
- Fine rate: $0.50/day for overdue loans (calculated in
crud.py)
Frontend (frontend/index.html): Minimal vanilla JS/HTML demo page; not the primary interface. Backend runs at http://localhost:8000 with CORS open to all origins.
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 · 47 lines · 503 tokens per session scan A c550df538084
libraryMCP CLAUDE.md is an instructions file published in the GitHub repository babosina/libraryMCP (4 stars, last pushed 3mo ago), licensed MIT. It adds 503 tokens to every session, about $0.0025 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
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.