Borrowing it
Nothing to install: this file belongs to jmilinovich/grove. 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/jmilinovich/grove/main/CLAUDE.mdgit clone --depth 1 https://github.com/jmilinovich/groveWrote 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/jmilinovich/grove/claude-md)<a href="https://agentmods.dev/instructions/jmilinovich/grove/claude-md"><img src="https://agentmods.dev/badge/instructions/jmilinovich/grove/claude-md.svg" alt="Measured on agentmods" 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 | $0.00804 | $0.00804 |
| Opus 5 | $0.00402 | $0.00402 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
grove CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grove
Grove is a single-user MCP server over a git-backed Obsidian vault. Six tools, no SaaS layer, no autonomous agent, no multi-tenant routing. The vault is sacred; Grove is the plumbing that makes it reachable from any MCP client.
Architecture rules
- The vault is the source of truth. State.db, QMD indexes, embeddings — all derived. If they diverge, rebuild the derived state.
- All writes are serialized. Single-threaded write queue. No concurrent git operations. Ever.
- Every write creates a git commit with attribution + optional provenance trailers.
- Search index updates synchronously on write. Agents have no memory between calls — eventual consistency means duplicates.
- Six tools.
query,get,multi_get,write_note,list_notes,vault_status. If you're adding a seventh, prove it doesn't overlap an existing tool's parameter shape first.
Running locally
GROVE_VAULT=/path/to/vault \
GROVE_API_KEY=$(openssl rand -hex 32) \
VOYAGE_API_KEY=... \
npx tsx src/server.ts
Listens on 127.0.0.1:8420/mcp. Set GROVE_AUTH=none to bypass the bearer check for local-only dev.
The discovery worker (extract→link engine) is a separate process:
GROVE_VAULT=/path/to/vault ANTHROPIC_API_KEY=... npx tsx src/discovery-worker.ts
Code conventions
- TypeScript, strict mode. No
anyunless interfacing with untyped externals. - Raw
node:http. No Express, no Fastify. The server is small enough. - Node ≥ 22. Built-in
fetch,crypto. Don't polyfill. - ESM only (
"type": "module"). - Run with
tsxin dev. - Dependencies are intentionally minimal. Don't add packages for what Node can do natively.
What not to do
- Don't add web frameworks. Raw
node:httpis the choice. - Don't break the MCP protocol. The server speaks
StreamableHTTPServerTransport; clients connect with a static bearer. - Don't sprawl tools. Six tools today. The next-cliff is around twelve, where overlap risk starts hurting tool selection.
- Don't write to the vault outside the write queue. Ever.
- Don't store raw API tokens anywhere. Compare in constant time with
timingSafeEqual. - Don't re-introduce multi-tenant routing, encryption, OAuth, trails, waitlists, or per-vault key minting. Those were costumes; the teardown was deliberate. (See
RETROSPECTIVE.md.)
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.
- 8d ago First seen · 71 lines · 804 tokens per session scan A 1b3fb1ab89cf
grove CLAUDE.md is an instructions file published in the GitHub repository jmilinovich/grove (23 stars, last pushed today), licensed MIT. It adds 804 tokens to every session, about $0.0040 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).
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.
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.