librarian CLAUDE.md

librarian CLAUDE.md is an instructions file for coding agents from omtodkar/librarian. It costs 3,294 tokens per session, scanned C, original, MIT.

A development guide for Librarian, a Go program that searches project documentation by meaning and stores its index in SQLite, a small embedded database.

In plain words
What is it for?
Use it when compiling Librarian, running its tests, working on the document indexer, or executing file operations in the repository.
Why use it?
It gives the build, test, and shell-command rules needed to work safely with its Go and C-library dependencies.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/omtodkar/librarian/claude-md
Clone the repo
git clone --depth 1 https://github.com/omtodkar/librarian

Wrote 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.

agentmods badge for librarian CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/omtodkar/librarian/claude-md.svg)](https://agentmods.dev/instructions/omtodkar/librarian/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/omtodkar/librarian/claude-md"><img src="https://agentmods.dev/badge/instructions/omtodkar/librarian/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,294 This file is loaded in full into every session.
When invoked 3,294 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.03294 $0.03294
Opus 5 $0.01647 $0.01647
Sonnet 5 $0.00659 $0.00659
Haiku 4.5 $0.00329 $0.00329

Measured 5d ago against content hash 40493f3d2fb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

librarian CLAUDE.md scanned grade C with 1 finding 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 5d 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 directory # NOT: rm -r directory
CLAUDE.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 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.

Project

Librarian — semantic documentation search for projects, powered by SQLite + sqlite-vec, exposed via MCP. Written in Go.

Build & Test

go build -o librarian .          # build binary
go test ./...                    # run all tests
go test ./internal/indexer       # run tests for a specific package
go test -v -run TestEmphasis     # run a specific test by name
make build                       # same as go build via Makefile

CGo is required (CGO_ENABLED=1, the Go default) because both mattn/go-sqlite3 and sqlite-vec are C libraries.

Non-Interactive Shell Commands

ALWAYS use non-interactive flags with file operations to avoid hanging on confirmation prompts. Shell commands like cp, mv, and rm may be aliased to include -i (interactive) mode on some systems, causing the agent to hang indefinitely waiting for y/n input.

Use these forms:

cp -f source dest           # NOT: cp source dest
mv -f source dest           # NOT: mv source dest
rm -f file                  # NOT: rm file
rm -rf directory            # NOT: rm -r directory
cp -rf source dest          # NOT: cp -r source dest

Other commands that may prompt:

  • scp — use -o BatchMode=yes
  • ssh — use -o BatchMode=yes to fail instead of prompting
  • apt-get — use -y
  • brew — use HOMEBREW_NO_AUTO_UPDATE=1

Librarian MCP

This project has a librarian MCP server configured in .mcp.json. Use it to understand the codebase — it is the default codebase-exploration surface in this repo.

  • search_docs — semantic search across indexed docs (start here for most questions)
  • get_context — deep briefing with related code files and documents (use for architecture/design questions)
  • get_document — read a full doc by file path
  • list_documents — browse all indexed docs
  • update_docs — write/overwrite a doc and re-index it

Prefer these tools over Grep and over reading full files. Order to try:

Read the full file on GitHub · 164 lines

Changes

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.

  1. 5d ago First seen · 164 lines · 3,294 tokens per session scan C 40493f3d2fb1

Subscribe to this mod's changes

librarian CLAUDE.md is an instructions file published in the GitHub repository omtodkar/librarian (2 stars, last pushed 3mo ago), licensed MIT. It adds 3,294 tokens to every session, about $0.0165 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens