A command for checking and maintaining the article layer of a wiki. It looks at issues such as outdated information, quality, accuracy, and consistency between articles.

Use it to review wiki articles for staleness, errors, quality problems, and conflicts between related pages.

It helps keep a growing knowledge base trustworthy and coherent over time.

librarian — Command for coding agents by nvk: A command for checking and maintaining the article layer…

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 commands/nvk/llm-wiki/librarian

Clone the repo

git clone --depth 1 https://github.com/nvk/llm-wiki

Or install claude-plugin, the plugin that ships this one along with the rest of its 1 skill, 28 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/nvk/llm-wiki/librarian.svg)](https://agentmods.dev/commands/nvk/llm-wiki/librarian)

Your own site

<a href="https://agentmods.dev/commands/nvk/llm-wiki/librarian"><img src="https://agentmods.dev/badge/commands/nvk/llm-wiki/librarian.svg" alt="Measured on agentmods" height="20"></a>

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,913 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.

Model	Per session	Once invoked
Fable 5	$0.00035	$0.02913
Opus 5	$0.00017	$0.01456
Sonnet 5	$0.00007	$0.00583
Haiku 4.5	$0.00003	$0.00291

Measured 4d ago against content hash 1dc3b98b13d8, 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 4d 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.

claude-plugin/commands/librarian.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your task

Resolve the wiki. Do NOT search the filesystem or read reference files — follow these steps:

Read $HOME/.config/llm-wiki/config.json. If it has hub_path, expand leading ~ only (not tildes in com~apple~CloudDocs) and prefer that path; use resolved_path only as a fallback cache when the expanded hub_path is unavailable and resolved_path is initialized. If config has only resolved_path, use it. If the configured path can be statted but reading wikis.json or listing topics/ fails with Operation not permitted, stop and ask the user to grant Full Disk Access/iCloud Drive access to the launcher; do not fall back to ~/wiki or resolved_path. Do not write machine-specific resolved_path into shared configs.
If no config → read $HOME/wiki/_index.md. If it exists → HUB = $HOME/wiki. If nothing found, ask the user where to create the wiki.
Wiki location (first match): --local → .wiki/ in CWD; --wiki all → HUB with an ALL_TOPICS flag for step 5; --wiki <name> → HUB/wikis.json lookup with portable path resolution (<HUB>, ~, absolute, or HUB-relative); if the registry path is stale, fall back to HUB/topics/<name>; CWD has .wiki/ → use it; else → HUB.
Read <wiki>/_index.md to verify. If missing → stop with "No wiki found. Run /wiki init first."
Hub-level detection: Librarian operates on the wiki/ layer of a single topic wiki. The HUB has no wiki/ subdirectory — only wikis.json, _index.md, log.md, and topics/. If ALL_TOPICS is set from --wiki all, read registered topic wikis from HUB/wikis.json (excluding the synthetic hub entry) and iterate the scan against each topic wiki sequentially. If the resolved wiki is the HUB (detected by the presence of wikis.json and the absence of a wiki/ subdir) AND the user did not pass --wiki <name>, do NOT proceed with the scan against an empty topic surface. Instead, present a numbered list of registered topic wikis from HUB/wikis.json and ask the user to pick one. Re-resolve the wiki path with the selected name (HUB/topics/<name>/) and continue.

Read the librarian reference at skills/wiki-manager/references/librarian.md. Then execute the requested subcommand.

/wiki:librarian is the focused wiki-maintenance tool. It reviews the wiki/ layer only. If the user wants a broader trust inspection across outputs, provenance, and fresh research, direct them to /wiki:audit.

Inventory awareness: librarian reports may recommend inventory records for durable maintenance follow-ups such as stale article clusters, weak source chains, recurring refresh tasks, or watch items. Do not create records during a scan unless the user explicitly asks; include a compact sample shape when suggesting a larger maintenance backlog.

Read the full file on GitHub · 201 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.

4d ago First seen · 201 lines · 35 tokens per session scan A 1dc3b98b13d8

Subscribe to this mod's changes

librarian is a command published in the GitHub repository nvk/llm-wiki (1,188 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 2,913 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 2026-08-30.

LLM Writing and docs agentic-ai agentic-skills agentic-workflow claude-code codex

librarian

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Your task

What this file has done since we first saw it

Other commands, from other repositories

gen-plan

refine-plan

gen-idea

start-rlcr-loop

sync_roleplay_docs

sync_contributors