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/craftos-dev/craftbot/airweavenpx skills add CraftOS-dev/CraftBot --skill airweavegit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWhat 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 | $0.00125 | $0.01012 |
| Opus 5 | $0.00063 | $0.00506 |
| Sonnet 5 | $0.00025 | $0.00202 |
| Haiku 4.5 | $0.00013 | $0.00101 |
Grade A, and why
airweave 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Airweave Search
Search and retrieve context from Airweave collections using the search script at {baseDir}/scripts/search.py.
When to Search
Search when the user:
- Asks about data in their connected apps ("What did we discuss in Slack about...")
- Needs to find documents, messages, issues, or records
- Asks factual questions about their workspace ("Who is responsible for...", "What's our policy on...")
- References specific tools by name ("in Notion", "on GitHub", "in Jira")
- Needs recent information you don't have in your training
- Needs you to check app data for context ("check our Notion docs", "look at the Jira ticket")
Don't search when:
- User asks general knowledge questions (use your training)
- User already provided all needed context in the conversation
- The question is about Airweave itself, not data within it
Query Formulation
Turn user intent into effective search queries:
| User Says | Search Query |
|---|---|
| "What did Sarah say about the launch?" | "Sarah product launch" |
| "Find the API documentation" | "API documentation" |
| "Any bugs reported this week?" | "bug report issues" |
| "What's our refund policy?" | "refund policy customer" |
Tips:
- Use natural language — Airweave uses semantic search
- Include context — "pricing feedback" beats just "pricing"
- Be specific but not too narrow
- Skip filler words like "please find", "can you search for"
Running a Search
Execute the search script:
python3 {baseDir}/scripts/search.py "your search query"
Optional parameters:
--limit N— Max results (default: 20)--temporal N— Temporal relevance 0-1 (default: 0, use 0.7+ for "recent", "latest")--strategy TYPE— Retrieval strategy: hybrid, semantic, keyword (default: hybrid)--raw— Return raw results instead of AI-generated answer--expand— Enable query expansion for broader results--rerank / --no-rerank— Toggle LLM reranking (default: on)
Examples:
What ships with it
4 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.
- 3d ago First seen · 107 lines · 125 tokens per session scan A e253d815d779
airweave is a skill published in the GitHub repository CraftOS-dev/CraftBot (376 stars, last pushed 3d ago), licensed MIT. It adds 125 tokens to every session and 1,012 once invoked, about $0.0006 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
go4
Use when designing, architecting, planning, or debugging any system with an LLM in it — agents, agent loops, RAG and retrieval, prompt pipelines, multi-agent or subagent orchestration, tool use and MCP, memory and context management, evals, or production guardrails. Trigger BEFORE committing to an approach — choosing…
enterprise-search-knowledge
Combines search results from multiple sources into coherent, deduplicated answers with source attribution. Handles confidence scoring based on freshness and authority, and summarizes large result sets effectively.
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.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
embeddings
Vector embeddings configuration and semantic search.
session-rag-eval
Run and debug Chatbox session attachment RAG model evaluation with synthetic and real long-file fixtures.