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/omtodkar/librarian/claude-mdgit clone --depth 1 https://github.com/omtodkar/librarianWrote 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/omtodkar/librarian/claude-md)<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>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 | $0.03294 | $0.03294 |
| Opus 5 | $0.01647 | $0.01647 |
| Sonnet 5 | $0.00659 | $0.00659 |
| Haiku 4.5 | $0.00329 | $0.00329 |
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 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=yesssh— use-o BatchMode=yesto fail instead of promptingapt-get— use-ybrew— useHOMEBREW_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 pathlist_documents— browse all indexed docsupdate_docs— write/overwrite a doc and re-index it
Prefer these tools over Grep and over reading full files. Order to try:
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.
- 5d ago First seen · 164 lines · 3,294 tokens per session scan C 40493f3d2fb1
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.
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.
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).