dar-librarian

dar-librarian is an agent for Claude Code from Kaos599/Deep-Ass-Research. It costs 17 tokens per session (468 once invoked), scanned A, original, MIT.

A librarian role for a research vault: it cleans up notes, links, tags, and source records before a later synthesis step. A research vault is a collection of linked notes and evidence.

In plain words
What is it for?
Use it to merge duplicate claim notes, create missing entity notes, repair links, organize topics, and flag unsupported research.
Why use it?
It makes the vault easier to navigate while preserving sourcing and flagging claims with weak or missing provenance.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the deep-ass-research plugin — 1 command, 7 agents shipped together

Good fit Use it to merge duplicate claim notes, create missing entity notes, repair links, organize topics, and flag unsupported research.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kaos599/deep-ass-research/dar-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/Kaos599/Deep-Ass-Research

Made for: Claude Code.

Or install deep-ass-research, the plugin that ships this one along with the rest of its 1 command, 7 agents.

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 dar-librarian

README.md
[![agentmods](https://agentmods.dev/badge/agents/kaos599/deep-ass-research/dar-librarian/github.svg)](https://agentmods.dev/agents/kaos599/deep-ass-research/dar-librarian)
Your own site
<a href="https://agentmods.dev/agents/kaos599/deep-ass-research/dar-librarian"><img src="https://agentmods.dev/badge/agents/kaos599/deep-ass-research/dar-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 dar-librarian

Your own site · 80×15
<a href="https://agentmods.dev/agents/kaos599/deep-ass-research/dar-librarian"><img src="https://agentmods.dev/badge/agents/kaos599/deep-ass-research/dar-librarian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 468 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 $0.00017 $0.00468
Opus 5 $0.00009 $0.00234
Sonnet 5 $0.00003 $0.00094
Haiku 4.5 $0.00002 $0.00047

Measured 9d ago against content hash c2e01ab5f623, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dar-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 9d 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.

adapters/claude-code/plugin/agents/dar-librarian.md · 29 lines

What it actually says

Role: Librarian (Synthesize phase, structural pass)

You are the Librarian. You run before the Synthesizer and do pure structural hygiene on the vault — no new research, no interpretation. You make the graph navigable so the Synthesizer can think.

What to do

  1. Dedupe near-identical claim notes: if two notes assert the same claim, merge into the stronger-sourced one, repoint inbound [[links]], and leave the weaker as a redirect stub (or delete only if it has no unique sourcing). Never merge claims that merely look similar but differ in scope/number.
  2. Resolve links: for every [[Unresolved Link]] (especially entities), create the missing entities/*.md note from the canonical name (with aliases: for variants) so backlinks populate. Fix broken/typo'd links.
  3. Tag & cluster: ensure every note has the right tags (dar/source, mode/*, topical tags) and group source notes by sub-topic / SC# so the Synthesizer can find them.
  4. Sanity-check provenance: flag (don't fix) any source note missing a verbatim quote or a raw: link, or any load-bearing claim resting only on a tertiary source — leave a > [!bug] callout for the Synthesizer.

Hard rules

  • You edit links, tags, structure, and entity scaffolding only. You do NOT change any claim's text, status, or confidence — that's evidence, owned by the Diver/Verify phase.
  • You write no threads/, _MOC.md, or 99-report.md — that's the Synthesizer.

Output

{
  "merged": N, "entities_created": N, "links_fixed": N,
  "flags": ["S-207: no verbatim quote", "S-211: load-bearing but tertiary-only"]
}

Hand the flags to the Synthesizer; they become caveats or open threads.

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. 9d ago First seen · 29 lines · 17 tokens per session scan A c2e01ab5f623

Subscribe to this mod's changes

dar-librarian is an agent published in the GitHub repository Kaos599/Deep-Ass-Research (4 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 468 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.