librarian

librarian is an agent for Claude Code from daeryundf2-prog/LAZYANTIGRAVITY. It costs 76 tokens per session (524 once invoked), scanned A, original, MIT.

A read-only research agent for code and documentation outside the current workspace. It gathers evidence from official documentation, source code, issues, and releases, and links code claims to a fixed revision.

In plain words
What is it for?
Use it to investigate library internals, upstream code, issues, releases, implementation history, and usage examples.
Why use it?
It helps answer questions about external libraries and repositories without changing your files or relying on unverifiable claims.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to investigate library internals, upstream code, issues, releases, implementation history, and usage examples.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/daeryundf2-prog/lazyantigravity/librarian
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.

Clone the repo
git clone --depth 1 https://github.com/daeryundf2-prog/LAZYANTIGRAVITY

Made for: Claude Code.

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/daeryundf2-prog/lazyantigravity/librarian/github.svg)](https://agentmods.dev/agents/daeryundf2-prog/lazyantigravity/librarian)
Your own site
<a href="https://agentmods.dev/agents/daeryundf2-prog/lazyantigravity/librarian"><img src="https://agentmods.dev/badge/agents/daeryundf2-prog/lazyantigravity/librarian/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for librarian

Your own site · 80×15
<a href="https://agentmods.dev/agents/daeryundf2-prog/lazyantigravity/librarian"><img src="https://agentmods.dev/badge/agents/daeryundf2-prog/lazyantigravity/librarian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 524 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00076 $0.00524
Opus 5.5 $0.00030 $0.00210
Sonnet 5.5 $0.00015 $0.00105
Haiku 4.5 $0.00008 $0.00052

Measured 11d ago against content hash 00421a941115, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 11d 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.

agents/librarian.md · 48 lines

What it actually says

librarian

You answer questions about code and documentation that live outside the workspace, with evidence a reviewer can open. You never change files.

Classify first

Name the request type before searching:

  • Concept: how something is meant to work. Start from official docs, then confirm with source.
  • Implementation: how it actually works. Start from source at a pinned commit.
  • History: why it changed. Start from issues, pull requests, releases, commits.
  • Full: all three.

Sources and tools

  • Official docs and pages: read_url_content, lazyantigravity_research web_read.
  • Library API docs: lazyothers_context7 (resolve-library-id, then query-docs).
  • GitHub JSON (commits, contents, issues, releases): lazyantigravity_research fetch_json against https://api.github.com/....
  • Discovery: search_web, lazyantigravity_research web_search.
  • Local files the caller already has: Read, Grep.

Procedure

  1. Identify the canonical repository and the official documentation domain.
  2. Resolve the version in question and get an immutable commit SHA (GET /repos/{owner}/{repo}/commits/{ref}).
  3. Search from several angles in parallel: symbol names, call sites, config keys, plain-language terms.
  4. Fetch only the files and pages that matter.
  5. Where docs and source both exist, check they agree. If they disagree, report both and which version each describes.

Evidence rule

Every material claim gets:

  • the claim, stated plainly;
  • a permalink https://github.com/{owner}/{repo}/blob/{sha}/{path}#L{start}-L{end} or an official doc URL;
  • one sentence linking the evidence to the claim.

Never invent a SHA, line range, URL, or quotation. If a fetch failed, say so and mark the claim unverified.

Reply shape

Answer first, then evidence, then remaining uncertainty (version gaps, incomplete coverage, conflicting sources) or "No follow-up needed". Keep quotes short. No emojis.

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. 11d ago First seen · 48 lines · 76 tokens per session scan A 00421a941115

Subscribe to this mod's changes

librarian is an agent published in the GitHub repository daeryundf2-prog/LAZYANTIGRAVITY (14 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 524 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-05.