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 agentmods add skills/sharpdeveye/maestro/enrichnpx skills add sharpdeveye/maestro --skill enrichgit clone --depth 1 https://github.com/sharpdeveye/maestroWhat 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 | $0.00027 | $0.00695 |
| Opus 5 | $0.00014 | $0.00347 |
| Sonnet 5 | $0.00005 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
enrich 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY PREPARATION
Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first. Consult the knowledge-systems reference in the agent-workflow skill for RAG architecture, chunking strategies, and retrieval patterns.
Add knowledge sources to ground the workflow in facts. Without grounding, agents hallucinate. With grounding, they cite sources.
Knowledge Source Assessment
Identify what knowledge the workflow needs:
| Knowledge Type | Source | Update Frequency | Access Pattern |
|---|---|---|---|
| Domain docs | Internal docs, specs | Monthly | Semantic search |
| Code context | Codebase | Real-time | Code search |
| User data | Database, CRM | Real-time | Structured query |
| External data | APIs, web | Real-time | API call |
| Historical | Logs, past interactions | Daily | Time-range query |
Add RAG Pipeline
For document-based knowledge (consult the knowledge-systems reference in the agent-workflow skill):
- Select documents: Identify the authoritative source documents
- Chunk strategy: Choose chunking based on document type (semantic > token-based)
- Embed: Use appropriate embedding model for the domain
- Index: Store in vector database with metadata
- Retrieve: Implement hybrid search (semantic + keyword)
- Inject: Add retrieved context to the prompt with source attribution
Add Structured Data
For database-backed knowledge:
- Define the query interface: Natural language → structured query
- Add guardrails: Read-only access, query complexity limits
- Format results: Transform raw data into context the model can use
- Attribute: Include data source and freshness in the context
Add Real-Time Data
For live information:
- Identify APIs: What external services provide the needed data
- Cache strategy: How often does the data change? Cache accordingly
- Fallback: What happens when the API is down?
- Attribution: Include data timestamp and source
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.
- 3d ago First seen · 80 lines · 27 tokens per session scan A d47c539e83ee
enrich is a skill published in the GitHub repository sharpdeveye/maestro (415 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 695 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 2026-08-30.
Other skills, from other repositories
documentation-search
Search the internal knowledge base for runbooks, architecture documentation, ADRs, best practices, and troubleshooting guides using RAG. Use when looking for internal documentation, deployment procedures, architecture decisions, or operational runbooks.
rag-knowledge
RAG domain knowledge — architecture, component routing, rules, and reference tables. Use when working on any file under rag/.
vector-search
Semantic vector search with moflo — RAG over your own documents, similarity matching, context-aware retrieval via HNSW (node:sqlite-backed). Use when building retrieval layers for chat, search, or context-assembly.
memory-optimization
Tune moflo's memory stack for speed, RAM, and index quality. Covers HNSW parameters (M, efConstruction, ef), vector quantization, batch operations, and common bottlenecks. Use when scaling past 100k entries or when search latency regresses.
agentic-rag
Use when building self-correcting retrieval systems for AI agents. Keywords: RAG, retrieval, Corrective RAG, Self-RAG, query decomposition, reranking, hallucination, grounding.
graph-rag
Use when needing global or relational understanding of codebases or knowledge corpora. Keywords: GraphRAG, knowledge graph, entity extraction, community summarization, graph traversal, Microsoft GraphRAG.