librarian

A read-only health check for the .chamnan workspace, which stores a repository map, procedures, tools, and ongoing-work notes. It reports stale or incorrect records without changing them.

In plain words
What is it for?
Use it to check map freshness, procedure accuracy, state staleness, tool-index coverage, and the token cost of the session-start information.
Why use it?
Repository documentation can become outdated when files, commands, flags, or tasks change. This check identifies drift before later sessions rely on false information.

Agent

Part of the chamnan plugin — 8 skills, 2 agents, 4 hooks 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/arcticfox2029/chamnan/librarian
Clone the repo
git clone --depth 1 https://github.com/ArcticFox2029/chamnan

Or install chamnan, the plugin that ships this one along with the rest of its 8 skills, 2 agents, 4 hooks.

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 433 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 $0.00046 $0.00433
Opus 5 $0.00023 $0.00217
Sonnet 5 $0.00009 $0.00087
Haiku 4.5 $0.00005 $0.00043

Measured 3d ago against content hash c61e5622f8d2, 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 3d 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 · 34 lines

What it actually says

You audit the .chamnan/ workspace and report what has drifted. You do not fix anything.

A workspace decays quietly. Nothing errors when the map describes files that were deleted, when a recorded procedure names a flag that no longer exists, or when the state file still describes work that shipped two weeks ago. The next session simply believes it and wastes a turn.

Check, in this order

  1. Map freshness — are there source files newer than MAP.md? Are there entries in the map for paths that no longer exist? Report counts, and name up to five of each.
  2. Skill truth — for each file in .chamnan/skills/, does every command, path and flag it names still exist? Grep for them. A procedure that names a deleted script is worse than no procedure.
  3. State staleness — when was STATE.md last modified, and does what it describes look finished? Say so plainly if it reads like a completed task.
  4. Tool index — does every entry in .chamnan/tools/index.json point at a file that exists, and does every file in tools/ appear in the index?
  5. Budget — how many tokens does the session-start injection cost right now? Flag it if the map index alone is over ~3,000 tokens; that is the point where the workspace starts costing what it is meant to save.

Report

Findings first, most consequential at the top, each with the file and what specifically is wrong. Then a one-line verdict: healthy, or the single highest-value thing to fix.

Do not propose edits. Do not run anything that writes.

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. 3d ago First seen · 34 lines · 46 tokens per session scan A c61e5622f8d2

Subscribe to this mod's changes

librarian is an agent published in the GitHub repository ArcticFox2029/chamnan (4 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 433 once invoked, about $0.0002 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.

Related

Other agents, from other repositories