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 favcrm/mcp --skill favcrm-knowledge-traininggit clone --depth 1 https://github.com/favcrm/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/favcrm/mcp/favcrm-knowledge-training)<a href="https://agentmods.dev/skills/favcrm/mcp/favcrm-knowledge-training"><img src="https://agentmods.dev/badge/skills/favcrm/mcp/favcrm-knowledge-training/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/favcrm/mcp/favcrm-knowledge-training"><img src="https://agentmods.dev/badge/skills/favcrm/mcp/favcrm-knowledge-training.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 | $0.00033 | $0.00212 |
| Opus 5.5 | $0.00013 | $0.00085 |
| Sonnet 5.5 | $0.00007 | $0.00042 |
| Haiku 4.5 | $0.00003 | $0.00021 |
Grade A, and why
favcrm-knowledge-training 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 1mo 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
FavCRM Knowledge Training
Use this skill when a merchant wants the FavCRM AI agent to learn policies, services, FAQs, pricing, scripts, SOPs, or website content.
Operating Rules
- Confirm source ownership or permission before adding content.
- Prefer URLs for public pages and pasted text for private SOPs.
- Use descriptive document names so retrieval can disambiguate.
- Deleting knowledge is destructive. Confirm document ID/title before deletion.
- Do not claim the agent has learned content until status confirms ready or queued.
Standard Flow
- Identify source type: URL or pasted text.
- Confirm title/name and business purpose.
- Add or scrape document.
- List/check documents to confirm status.
- Report document ID, status, and expected retrieval timing.
Read references/knowledge-flows.md for exact patterns.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 28 lines · 33 tokens per session scan A d2e74fcd0eca
favcrm-knowledge-training is a skill published in the GitHub repository favcrm/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 212 once invoked, about $0.0001 per session on Opus 5.5. 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
graph-retrieval
Exposes graph-based retrieval as a tool capability via querygraph. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.
knowledge-layer
High-level deployment wrapper over RepoBrain core with graph-first knowledge injection and all-file support. Exposes refreshfilesystem and askfilesystem for building and querying the knowledge graph.
haiku-rag
Search, read and compute over the user's haiku.rag knowledge base through the haiku-rag MCP tools. Use whenever a request could be answered from the user's ingested documents, when asked to find, look up, check or cite something in their documents or knowledge base, or when the question is about the user's own…
library-rag
Semantic search over a personal library using Nemotron-3-Embed-1B embeddings + sqlite-vec. Index books, documents, any text corpus; query by meaning. Includes EPUB→Markdown conversion and MCP server for auto-available search tools.
portable-rag-per-skill
Pattern for standalone RAG indexes that live inside a skill directory — portable, no external DB or MCP dependency.
opik-evaluate
Build an LLM evaluation and run it against the app, returning an Opik experiment with scores and its link. Picks a test suite with judge assertions or a dataset with metrics, sources cases from traces or synthetic data, scores heuristics-first then one-failure-mode judges, runs client-side via the SDK or server-side…