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 commands/spillwavesolutions/agent-brain/agent-brain-embeddingsgit clone --depth 1 https://github.com/SpillwaveSolutions/agent-brainWhat 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 | $0.00014 | $0.01461 |
| Opus 5 | $0.00007 | $0.00731 |
| Sonnet 5 | $0.00003 | $0.00292 |
| Haiku 4.5 | $0.00001 | $0.00146 |
Grade A, and why
agent-brain-embeddings 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Brain Embeddings Configuration
Purpose
Configures the embedding provider used for vector/semantic search. Embeddings convert text into numerical vectors that enable semantic similarity search.
Usage
/agent-brain:agent-brain-embeddings [provider] [--model <model>]
Parameters
| Parameter | Required | Default | Description |
|---|---|---|---|
| provider | No | - | Provider name: openai, cohere, ollama, gemini, grok, sentence-transformers |
| --model | No | Provider default | Specific model to use |
Available Providers
OpenAI
Industry-standard embeddings with high quality vectors.
| Model | Dimensions | Use Case |
|---|---|---|
| text-embedding-3-large | 3072 | Highest quality, production |
| text-embedding-3-small | 1536 | Faster, cost-effective |
| text-embedding-ada-002 | 1536 | Legacy, widely compatible |
Configuration:
export EMBEDDING_PROVIDER=openai
export EMBEDDING_MODEL=text-embedding-3-large
export OPENAI_API_KEY=sk-proj-...
Cohere
Multi-language support with good quality vectors.
| Model | Dimensions | Use Case |
|---|---|---|
| embed-english-v3.0 | 1024 | English content |
| embed-multilingual-v3.0 | 1024 | International content |
| embed-english-light-v3.0 | 384 | Lightweight, fast |
Configuration:
export EMBEDDING_PROVIDER=cohere
export EMBEDDING_MODEL=embed-english-v3.0
export COHERE_API_KEY=...
Ollama (Local)
Privacy-first local embeddings with no API costs.
| Model | Dimensions | Use Case |
|---|---|---|
| nomic-embed-text | 768 | General purpose |
| mxbai-embed-large | 1024 | Higher quality |
| all-minilm | 384 | Lightweight, fast |
Configuration:
export EMBEDDING_PROVIDER=ollama
export EMBEDDING_MODEL=nomic-embed-text
export OLLAMA_BASE_URL=http://localhost:11434
Setup:
# Pull the model first
ollama pull nomic-embed-text
Execution
Interactive Configuration
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 · 234 lines · 14 tokens per session scan A 8068df20fded
agent-brain-embeddings is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 1,461 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 commands, from other repositories
ai-pipeline
RAG/embedding pipeline scaffolding — delegates to ai-data-engineer agent.
agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
ingest
Manually add knowledge to the Weaviate store.
build-search-index
Build or refresh a vault's LOCAL BM25 search index (wiki-meta/search-index.json) — a deterministic, plugin-free search tier that works on every vault, including those without Smart Connections. Idempotent (fingerprint check → no rewrite). (Skill build-search-index handles natural-language triggers.).
proofrag
Evaluate a RAG/LLM app — generate a golden set, judge it, and produce a scorecard.
qdrant-scaling
Directly invoke the qdrant-scaling skill, bypassing natural-language trigger matching.