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.
npx skills add genudo-ai/genudo_mcp --skill manage-knowledge-basegit 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/skills/genudo-ai/genudo_mcp/manage-knowledge-base)<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/manage-knowledge-base"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/manage-knowledge-base/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/skills/genudo-ai/genudo_mcp/manage-knowledge-base"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/manage-knowledge-base.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 | $0.00513 |
| Opus 5 | $0.00032 | $0.00257 |
| Sonnet 5 | $0.00013 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
manage-knowledge-base 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
Manage Knowledge Base
Curate the grounded facts an agent answers from. A knowledge base is a set of knowledge tables; each table has a name, a when-to-use description, columns (the schema), and rows the pipeline agent retrieves via semantic search at runtime.
Tools
| Task | Tool |
|---|---|
| See tables, their columns + attached pipelines | list_knowledge_tables |
| Create a table with its columns | create_knowledge_table |
| Insert or update rows | upsert_knowledge_points |
| Test what the agent would retrieve | search_knowledge_table |
| Remove rows | delete_knowledge_points |
Workflow
- Discover —
list_knowledge_tablesto find the right table (or confirm none exists). - Create —
create_knowledge_tableneedsnameand at least one column; write thedescriptionas a when-to-use so the agent picks the right table. - Fill / fix —
upsert_knowledge_points: every row needs a stabledefault_id(matchingdefault_idupdates the row, new one inserts) and a value for every column. Reuse the samedefault_idto correct a fact in place. - Verify retrieval —
search_knowledge_tablewith a question a real customer would ask; confirm the fixed row comes back (hybrid search is on by default;limitup to 20). - Prune —
delete_knowledge_pointsbydefault_idvalues. Confirm with the user first; there is no undo, and there is no table-delete tool — only rows can be removed.
Cautions
- A wrong fact in the KB propagates to every conversation — confirm every write.
- For a stable business fact the agent must always know, prefer the pipeline's global
instructions(viaedit-pipeline-instructions); use the KB for facts that vary by product, plan, or row.
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 · 41 lines · 63 tokens per session scan A 1f598db2f0ff
manage-knowledge-base is a skill 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 513 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 skills, from other repositories
chroma-mcp
Skill "chroma-mcp" from Friz-zy/ai-capability-registry, covering chroma, when to use, connection, docker stdio and mcp instructions.
amazon-kendra-index-mcp
Enterprise search and RAG enhancement.
customgpt.ai-mcp
RAG-as-a-service MCP server by CustomGPT.ai.
deepwiki-mcp
RAG-as-a-Service MCP server by Devin.
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.