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.
git clone --depth 1 https://github.com/genudo-ai/genudo_mcpWrote 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/genudo-ai/genudo_mcp/kb-librarian)<a href="https://agentmods.dev/agents/genudo-ai/genudo_mcp/kb-librarian"><img src="https://agentmods.dev/badge/agents/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.
<a href="https://agentmods.dev/agents/genudo-ai/genudo_mcp/kb-librarian"><img src="https://agentmods.dev/badge/agents/genudo-ai/genudo_mcp/kb-librarian.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00063 | $0.00364 |
| Opus 5 | $0.00032 | $0.00182 |
| Sonnet 5 | $0.00013 | $0.00073 |
| Haiku 4.5 | $0.00006 | $0.00036 |
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 10d 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.
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:
- Run
manage-knowledge-basefor the full playbook. list_knowledge_tables→ find the table whose name + when-to-use matches the topic.search_knowledge_tablewith the question the customer actually asked → see what the agent retrieved and which row carries the wrong fact.- Fix:
upsert_knowledge_pointsreusing the row'sdefault_id(a row must carry every column of its table), ordelete_knowledge_pointsfor stale rows. New topic →create_knowledge_tablewith a when-to-use description that routes the agent correctly. - Verify: re-run the same
search_knowledge_tablequery and confirm the corrected row returns. - If the wrong fact is a stable business fact the agent must always know, prefer adding it to
the pipeline's global
instructionsviaedit-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.
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.
- 10d ago First seen · 27 lines · 63 tokens per session scan A 7d5bd5fb1bf8
kb-librarian is an agent published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 63 tokens to every session and 364 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.
Other agents, from other repositories
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
qdrant-expert
Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…
FAI LangChain Expert
LangChain framework specialist — LCEL expression language, chains, agents with tool use, retrievers, memory, callbacks, LangSmith tracing, and production RAG pipeline patterns.
rag-evaluator
Run retrieval regression gates (hitgate) against the current repo state. Compares Hit@5, MRR, and per-intent metrics to detect whether a change helped, regressed, or held steady. Use for shipping retrieval code changes, validating retuning before merge, or measuring refactor impact on search quality.
ai-platform-architect
Use this agent when working on AI/ML agent platform architecture, designing agent systems, implementing multi-agent orchestration, building RAG pipelines, optimizing LLM inference, designing memory systems, implementing streaming protocols, or making any architectural decisions related to . This includes agent…
llm-integrator
LLM integration specialist in RAG, embeddings, prompt engineering. Use PROACTIVELY for LLM features.