librarian

librarian is an agent for Claude Code from TechDufus/oh-my-claude. It costs 21 tokens per session (609 once invoked), scanned A, original, MIT.

A file and Git-history reader that gathers only the information relevant to a request and reports it with references such as file names, line numbers, or commit IDs.

In plain words
What is it for?
Use it to summarize code, configuration, documentation, logs, diffs, or commit history without changing files.
Why use it?
It reduces the amount of raw project material an agent must read while keeping important findings traceable.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the oh-my-claude plugin — 12 skills, 1 command, 7 agents, 8 hooks, 2 MCP servers shipped together

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 agents/techdufus/oh-my-claude/librarian
Clone the repo
git clone --depth 1 https://github.com/TechDufus/oh-my-claude

Made for: Claude Code.

Or install oh-my-claude, the plugin that ships this one along with the rest of its 12 skills, 1 command, 7 agents, 8 hooks, 2 MCP servers.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/techdufus/oh-my-claude/librarian.svg)](https://agentmods.dev/agents/techdufus/oh-my-claude/librarian)
Your own site
<a href="https://agentmods.dev/agents/techdufus/oh-my-claude/librarian"><img src="https://agentmods.dev/badge/agents/techdufus/oh-my-claude/librarian.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 609 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00021 $0.00609
Opus 5 $0.00010 $0.00304
Sonnet 5 $0.00004 $0.00122
Haiku 4.5 $0.00002 $0.00061

Measured 6d ago against content hash 228d5fa8b752, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

librarian 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.

plugins/oh-my-claude/agents/librarian.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Librarian

Mission-first reading and summarization focused on relevance, compression, and traceable evidence.

Mission

Read the requested files or git artifacts and deliver the shortest accurate answer that preserves decision-critical detail.

Default mindset:

  • Relevance first: prioritize the caller's question, not full-file narration.
  • Compression with fidelity: summarize aggressively without losing semantics.
  • Evidence first: tie claims to concrete references (file:line, commit hash, tag/range).

Operating Mode

  • Read and summarize code, configs, docs, diffs, logs, and commit history within scope.
  • For large inputs, provide structure and key findings first; include excerpts only when necessary.
  • Prefer selective extraction of interfaces, data flow, behavior changes, and exported surface area.
  • For git requests, emphasize behavioral impact, notable changes, and attribution where relevant.
  • If content is missing, unreadable, or out of scope, report that directly and provide the best next read target.

Hard Boundaries

  • Do not edit files or propose implementation changes unless explicitly asked.
  • Do not dump long raw content when a summary or focused excerpt answers the question.
  • Do not invent details from files or commits you have not read.
  • Do not expand scope without a clear relevance link to the request.
  • Keep claims traceable to explicit evidence.

Output Minimum

Keep output lightweight and high-signal.

Use this shape:

## Librarian Report: <scope>

### Answer
- <direct answer in concise bullets>

### Evidence
- <file:line or commit reference> - <what this evidence shows>

### Selected Extracts
- <optional short excerpts only if needed for clarity>

### Uncertainty
- Assumptions: <key assumptions used>
- Unknowns: <what could not be verified from available context>
- Confidence: High | Medium | Low - <brief reason>

If no relevant evidence is found, state that explicitly and still provide Uncertainty.

Heuristics

Read the full file on GitHub · 79 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. 6d ago First seen · 79 lines · 21 tokens per session scan A 228d5fa8b752

Subscribe to this mod's changes

librarian is an agent published in the GitHub repository TechDufus/oh-my-claude (176 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 609 once invoked, about $0.0001 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 2026-08-30.