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 agents/techdufus/oh-my-claude/librariangit clone --depth 1 https://github.com/TechDufus/oh-my-claudeWrote 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/agents/techdufus/oh-my-claude/librarian)<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>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 5.1 | $0.00021 | $0.00609 |
| Opus 5 | $0.00010 | $0.00304 |
| Sonnet 5 | $0.00004 | $0.00122 |
| Haiku 4.5 | $0.00002 | $0.00061 |
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.
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
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.
- 6d ago First seen · 79 lines · 21 tokens per session scan A 228d5fa8b752
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.
Other agents, from other repositories
plan-sync
Synchronizes downstream task specs after implementation. Spawned by flow-next-work once per resolved wave. Do not invoke directly.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
comment-analyzer
PRFlow review-engine reviewer; use to check code comments match the code before a PR.
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…
expert
Frontier-grade domain-authority evaluator. Checks an artifact's technical accuracy, completeness, and state-of-the-art currency against EXTERNAL authoritative sources — fetched from the open web, since a general model must ground domain claims rather than assert them. Top tier of the user-mastery spectrum (beginner →…