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 instructions/spillwavesolutions/agent-brain/claude-mdgit 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 | $0.03973 | $0.03973 |
| Opus 5 | $0.01987 | $0.01987 |
| Sonnet 5 | $0.00795 | $0.00795 |
| Haiku 4.5 | $0.00397 | $0.00397 |
Grade A, and why
agent-brain CLAUDE.md 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 2d 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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Brain Development Guidelines
Instructions for Claude Code when working on this repository.
Planning rule: after any planning step, save the plan to docs/plans/<name>.md before doing work.
CRITICAL: NEVER PUSH WITHOUT TESTING
ABSOLUTE RULE: You MUST run task before-push BEFORE EVERY git push. NO EXCEPTIONS.
task before-push
This runs format, lint, typecheck, and tests. Do NOT push code that fails this check.
Why this matters: PRs trigger expensive CI pipelines. Pushing broken code wastes time and money. Every single push failure that could have been caught locally is unacceptable.
Enforcement checklist (verify ALL pass before pushing):
task before-pushexits with code 0- No lint errors (Ruff)
- No type errors (mypy)
- All tests pass
- Code is formatted (Black)
If task before-push fails, DO NOT push. Fix the issues first.
Project Overview
Agent Brain is a RAG-based document indexing and semantic search system. It's a monorepo containing:
| Package | Path | PyPI Name | Description |
|---|---|---|---|
| agent-brain-server | agent-brain-server/ |
agent-brain-rag |
FastAPI REST API server |
| agent-brain-cli | agent-brain-cli/ |
agent-brain-cli |
CLI management tool |
| agent-brain-uds | agent-brain-uds/ |
agent-brain-uds |
Unix domain socket transport |
| agent-brain-mcp | agent-brain-mcp/ |
agent-brain-ag-mcp |
MCP server (tools, resources, prompts) |
| agent-brain-skill | agent-brain-skill/ |
— | Claude Code skill |
| agent-brain-plugin | agent-brain-plugin/ |
— | Claude Code plugin (commands, agents, skills) |
PyPI rename note: the MCP package publishes as agent-brain-ag-mcp (renamed in v10.1.2 — PyPI typosquatting filter rejected the original name). The console script is still agent-brain-mcp and the import path is still agent_brain_mcp.
Technology Stack
- Python: 3.10+
- Build System: Poetry
- Package Installer: uv (preferred over pip)
- Server: FastAPI + Uvicorn
- CLI: Click + Rich
- Vector Store: ChromaDB
- Embeddings: OpenAI text-embedding-3-large
- Indexing: LlamaIndex
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.
- 2d ago First seen · 364 lines · 3,973 tokens per session scan A 07acc0f3a0d9
agent-brain CLAUDE.md is an instructions file published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 3d ago), licensed MIT. It adds 3,973 tokens to every session, about $0.0199 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.