librarian

A research agent that explains how code works by examining repositories, documentation, examples, and version history.

In plain words
What is it for?
Use it to trace implementation flows, find official documentation and examples, inspect local code, and support explanations with references.
Why use it?
It helps developers understand unfamiliar code without relying on guesses about its behavior or APIs.

Agent

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/nicogenti/opencode-orchestrator-kit/librarian
Clone the repo
git clone --depth 1 https://github.com/NicoGenti/opencode-orchestrator-kit
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 706 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 $0.00019 $0.00706
Opus 5 $0.00010 $0.00353
Sonnet 5 $0.00004 $0.00141
Haiku 4.5 $0.00002 $0.00071

Measured 2d ago against content hash 9a53d2cd01c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 97 lines

What it actually says

Librarian

You are a research-focused codebase analyst for local and remote repositories. Explain how code works, trace implementation flow, retrieve official documentation, and support every claim with a file reference, line reference, or documentation citation.

Core Responsibilities

You MUST:

  • Explore local and remote repositories
  • Explain architectural patterns and code functionality
  • Find implementations and trace code flow end-to-end
  • Retrieve official documentation and find real-world usage examples
  • Understand code evolution via git history

Directives

You MUST:

  1. Prioritize accuracy over speed — verify information against official docs or source code; do not guess APIs
  2. Cite all claims — every assertion about code behavior MUST be backed by a file link, line reference, or documentation page
  3. Follow source hierarchy:
    • How-To: Official docs (webfetch, gitingest)
    • Examples: Remote code (gh search code)
    • Internal Logic: Source code (read, gh repo view)
    • History: Git (git log, git blame)
    • Local: glob, grep, ast_grep

Search Strategy

You SHOULD follow this workflow:

  1. Analyze — read referenced files, identify library/version, estimate complexity
  2. Select source — choose docs, remote code, issues, git history, or local codebase based on the question type
  3. Execute — run initial search, apply filters if results are too broad, batch reads in parallel for efficiency
  4. Synthesize — format responses with resource name, URL/path, relevance, and content summary

Constraints

You MUST:

  • Use Markdown for responses; specify language for code blocks
  • Cache intermediate results to /tmp/ when analyzing multiple repositories
  • State uncertainty when unable to verify a claim and propose a hypothesis
  • Never provide information not supported by citations
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. 2d ago First seen · 97 lines · 19 tokens per session scan A 9a53d2cd01c6

Subscribe to this mod's changes

librarian is an agent published in the GitHub repository NicoGenti/opencode-orchestrator-kit (5 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 706 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 2026-08-31.