kb-librarian

kb-librarian is a skill for Claude Code, Codex from genudo-ai/genudo_mcp. It costs 63 tokens per session (360 once invoked), scanned A, original, MIT.

A librarian for a Genudo pipeline's knowledge base, which is the set of facts an agent uses to answer questions. It searches knowledge tables, corrects outdated rows, and verifies the results.

In plain words
What is it for?
Use it to find the table behind a wrong answer, update or remove incorrect knowledge rows with confirmation, and check that corrected facts are retrieved.
Why use it?
It helps fix answers caused by incorrect or stale stored information. It also prevents unsupported facts from being added just to fill gaps.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to find the table behind a wrong answer, update or remove incorrect knowledge rows with confirmation, and check that corrected facts are retrieved.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/genudo-ai/genudo_mcp/kb-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.

Any agent
npx skills add genudo-ai/genudo_mcp --skill kb-librarian
Clone the repo
git clone --depth 1 https://github.com/genudo-ai/genudo_mcp

Made for: Claude Code, Codex.

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 kb-librarian

README.md
[![agentmods](https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/kb-librarian/github.svg)](https://agentmods.dev/skills/genudo-ai/genudo_mcp/kb-librarian)
Your own site
<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/kb-librarian"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/kb-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 kb-librarian

Your own site · 80×15
<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/kb-librarian"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/kb-librarian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 360 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 $0.00063 $0.00360
Opus 5 $0.00032 $0.00180
Sonnet 5 $0.00013 $0.00072
Haiku 4.5 $0.00006 $0.00036

Measured 11d ago against content hash 81f687edc0ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

kb-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 11d 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.

chatgpt/genudo-chatgpt-plugin/skills/kb-librarian/SKILL.md · 26 lines

What it actually says

You are the Genudo Knowledge Base Librarian. You keep the facts an agent answers from correct and well-targeted.

Operating procedure:

  1. Run manage-knowledge-base for the full playbook.
  2. list_knowledge_tables → find the table whose name + when-to-use matches the topic.
  3. search_knowledge_table with the question the customer actually asked → see what the agent retrieved and which row carries the wrong fact.
  4. Fix: upsert_knowledge_points reusing the row's default_id (a row must carry every column of its table), or delete_knowledge_points for stale rows. New topic → create_knowledge_table with a when-to-use description that routes the agent correctly.
  5. Verify: re-run the same search_knowledge_table query and confirm the corrected row returns.
  6. If the wrong fact is a stable business fact the agent must always know, prefer adding it to the pipeline's global instructions via edit-pipeline-instructions (with confirmation).

Rules:

  • A wrong fact in the KB reaches every conversation — confirm every change before writing.
  • Confirm before delete_knowledge_points; there is no undo and no table-delete tool.
  • Never invent facts to fill a gap; mark unknowns and ask.
  • Never claim a fix worked without a confirming search result.
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. 11d ago First seen · 26 lines · 63 tokens per session scan A 81f687edc0ea

Subscribe to this mod's changes

kb-librarian is a skill published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 63 tokens to every session and 360 once invoked, about $0.0003 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.