Borrowing it
Nothing to install: this file belongs to Epistates/turbovault. 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/Epistates/turbovault/main/CLAUDE.mdgit clone --depth 1 https://github.com/Epistates/turbovaultWrote 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/epistates/turbovault/claude-md)<a href="https://agentmods.dev/instructions/epistates/turbovault/claude-md"><img src="https://agentmods.dev/badge/instructions/epistates/turbovault/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/epistates/turbovault/claude-md"><img src="https://agentmods.dev/badge/instructions/epistates/turbovault/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 | $0.05085 | $0.05085 |
| Opus 5.5 | $0.02034 | $0.02034 |
| Sonnet 5.5 | $0.01017 | $0.01017 |
| Haiku 4.5 | $0.00509 | $0.00509 |
Grade A, and why
turbovault 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 21d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
TurboVault is an MCP (Model Context Protocol) server that gives AI agents safe, fast access to Obsidian vaults. It's written in Rust and exposes 52 tools (30 listed by default, 22 advanced ones on request), note resources, workflow prompts and completions, for reading, writing, searching, analyzing and managing notes.
Key design principle: built on the TurboMCP framework (3.x; the exact version is in the workspace Cargo.toml), which provides typed tool definitions, transports, auth and telemetry. TurboVault adds the vault: write safety, an index that can't miss an outside edit, and the tools on top.
Development Commands
Build and test
just build # cargo build
just release # cargo build --release (fat LTO)
just test # fmt-check, lint, test-all
just test-quick # tests only
just test-one module::test_name
cargo test --workspace --all-features
cargo test --workspace --tests # integration tests only
cargo test --workspace --lib # unit tests only
Code quality
cargo fmt --all
cargo clippy --workspace --all-features --all-targets -- -D warnings
RUSTDOCFLAGS="-D warnings" cargo doc --workspace --no-deps --all-features
cargo machete # unused dependencies (CI runs it)
cargo deny check && cargo audit --deny warnings
CI runs clippy on current stable; a newer clippy can flag code an older one passed, so keep the local toolchain current (rustup update stable).
Snapshots, properties, fuzzing, benchmarks
# The tool catalog snapshot (names, descriptions, input and output schemas).
# Re-bless after changing any tool, then review the diff.
UPDATE_TOOL_CATALOG=1 cargo test -p turbovault --lib
# The parser contract snapshot.
UPDATE_PARSER_SNAPSHOT=1 cargo test -p turbovault-parser --test test_contract_snapshot
# Property tests run with the normal suite; raise the case count to dig.
PROPTEST_CASES=4096 cargo test -p turbovault-tools --test proptest_rewriter
# Fuzz targets (nightly, outside the workspace): parse_note, parse_blocks,
# frontmatter, edit_blocks, rewrite_links.
cd fuzz && cargo +nightly fuzz run parse_note -- -max_total_time=60
# Benchmarks, including a 10,000-note vault.
cargo bench -p turbovault --bench vault_10k
cargo bench -p turbovault-git --bench vault_size
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.
- 21d ago Changed · +17 tokens per session 55cf6d0e9a10
- 24d ago First seen · 274 lines · 5,068 tokens per session scan A 66a49f81c29a
turbovault CLAUDE.md is an instructions file published in the GitHub repository Epistates/turbovault (158 stars, last pushed 6d ago), licensed MIT. It adds 5,085 tokens to every session, about $0.0203 per session on Opus 5.5. 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 2026-10-14.
turbovault CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| turbovault CLAUDE.mdEpistates/turbovault | Instructions file | 158 | 6d ago | MIT | A | 5,085 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |