Borrowing it
Nothing to install: this file belongs to jj-valentine/cerebellum. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jj-valentine/cerebellum/main/CLAUDE.mdgit clone --depth 1 https://github.com/jj-valentine/cerebellumWrote 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/instructions/jj-valentine/cerebellum/claude-md)<a href="https://agentmods.dev/instructions/jj-valentine/cerebellum/claude-md"><img src="https://agentmods.dev/badge/instructions/jj-valentine/cerebellum/claude-md/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/instructions/jj-valentine/cerebellum/claude-md"><img src="https://agentmods.dev/badge/instructions/jj-valentine/cerebellum/claude-md.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 | $0.00459 | $0.00459 |
| Opus 5 | $0.00230 | $0.00230 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
cerebellum 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 11d 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
Cerebellum
Personal agent-readable second brain. Postgres + pgvector + MCP.
What this is
A knowledge capture + retrieval system. Thoughts go in via CLI or MCP. Every AI tool (Claude, ChatGPT, Cursor, VS Code) can query it via a single MCP server.
Stack
- Database: Supabase (Postgres + pgvector)
- Embeddings: OpenRouter →
openai/text-embedding-3-small - Classifier: OpenRouter →
openai/gpt-4o-mini - MCP server:
src/mcp/server.ts(Node.js,@modelcontextprotocol/sdk) - CLI:
src/cli/index.ts
Commands
npm run build # compile TypeScript
npm run mcp # start MCP server
npm run cli -- "text" # capture a thought
npm run cli -- search "query" # search thoughts
Key files
| File | Purpose |
|---|---|
schema/schema.sql |
Postgres schema — run once in Supabase SQL editor |
src/config.ts |
All env var loading + validation |
src/capture.ts |
Core pipeline: embed → classify → store |
src/mcp/server.ts |
MCP server entry point |
Environment
Copy .env.example → .env and fill in:
SUPABASE_URLSUPABASE_SERVICE_KEY(service role, not anon)OPENROUTER_API_KEY
MCP setup (Claude Code)
After npm run build:
claude mcp add --transport stdio --scope user cerebellum -- node /Users/james/dev/new/cerebellum/dist/mcp/server.js
This stores the config in ~/.claude.json and makes the server available globally across all Claude Code sessions.
Dev workflow
- Branch:
feat/<scope>,fix/<scope>, etc. - Commits: conventional (
feat(mcp): add semantic_search tool) - Plans:
docs/plans/ - Never commit
.env
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.
- 11d ago First seen · 58 lines · 459 tokens per session scan A 7bf15db4f73b
cerebellum CLAUDE.md is an instructions file published in the GitHub repository jj-valentine/cerebellum (38 stars, last pushed 3mo ago), licensed MIT. It adds 459 tokens to every session, about $0.0023 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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 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).
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.