obsidian-mcp-rs: Instructions file for Claude Code

CLAUDE.md

obsidian-mcp-rs CLAUDE.md is an instructions file for Claude Code from MrRefactoring/obsidian-mcp-rs. It costs 4,410 tokens per session, scanned A, original, MIT.

Development instructions for obsidian-mcp-rs, a Rust server that works with an Obsidian vault, a folder of notes, to search and edit its contents.

In plain words
What is it for?
Running the server against a vault, using read-only mode, testing library code, measuring search or tag-renaming speed, and meeting CI checks.
Why use it?
They list the commands and checks needed to build, test, benchmark, format, and lint the server across supported operating systems.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is MrRefactoring/obsidian-mcp-rs's own configuration. It tells Claude Code how to work on obsidian-mcp-rs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything obsidian-mcp-rs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MrRefactoring/obsidian-mcp-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MrRefactoring/obsidian-mcp-rs/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MrRefactoring/obsidian-mcp-rs

Made for: Claude Code.

Wrote 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.

agentmods badge for obsidian-mcp-rs CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mrrefactoring/obsidian-mcp-rs/claude-md/github.svg)](https://agentmods.dev/instructions/mrrefactoring/obsidian-mcp-rs/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mrrefactoring/obsidian-mcp-rs/claude-md"><img src="https://agentmods.dev/badge/instructions/mrrefactoring/obsidian-mcp-rs/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.

agentmods 80×15 button for obsidian-mcp-rs CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mrrefactoring/obsidian-mcp-rs/claude-md"><img src="https://agentmods.dev/badge/instructions/mrrefactoring/obsidian-mcp-rs/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,410 This file is loaded in full into every session.
When invoked 4,410 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04410 $0.04410
Opus 5 $0.02205 $0.02205
Sonnet 5 $0.00882 $0.00882
Haiku 4.5 $0.00441 $0.00441

Measured 9d ago against content hash cc1b74d4a744, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

obsidian-mcp-rs 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 9d 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.

CLAUDE.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 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.

Commands

# Build / run
cargo build                              # debug
cargo build --release                    # release (LTO, opt-level=3, stripped)
cargo run -- /path/to/vault              # run server against a vault
cargo run -- --no-edit /path/to/vault    # read-only mode

# Tests
cargo test                               # all tests (the unit tests live in the lib target)
cargo test --lib <name>                  # single test — tests compile under the lib crate

# Benchmarks (criterion, harness = false; see benches/vault_bench.rs)
cargo bench                              # run search / rename_tag benchmarks
RAYON_NUM_THREADS=1 cargo bench          # single-threaded baseline for comparison
cargo bench --no-run                     # compile-only — this is what CI gates on

# Lint gates enforced by CI (.github/workflows/ci.yml)
cargo fmt --check
cargo clippy -- -D warnings

# Coverage (matches CI)
cargo llvm-cov --lcov --output-path lcov-rust.info

# Cross-platform check (CI matrix: aarch64/x86_64 darwin, x86_64 linux gnu+musl, x86_64 windows-msvc)
cargo check --target <triple>

# npm wrapper (in npm/obsidian-mcp-rs/)
npm install && npm run build && npm test   # TS build + vitest

Toolchain is pinned to stable (rust-toolchain.toml); MSRV is 1.88. rustfmt: 100-col, 4-space, edition 2024. clippy.toml sets msrv = "1.88.0".

Architecture

This is a Rust library (src/lib.rs, crate obsidian_mcp_rs) holding all domain logic, with a thin binary (src/main.rs) that wires up the CLI/logging and speaks MCP over stdio. Splitting lib/bin lets benches/ and integration tests link against the code. There is also an npm wrapper that distributes prebuilt binaries via the optional-dependencies pattern.

Transport invariant (do not break)

The http cargo feature (off by default) adds a Streamable HTTP transport (src/http.rs, --http). It does not relax the stdout rule: stdio mode must stay sterile, and tests/mcp_stdio.rs proves it. The HTTP server validates the Origin header — the MCP spec requires it of local servers, and it is the only thing standing between a malicious web page and a vault the server will happily read and rewrite without authentication.

Read the full file on GitHub · 141 lines

Changes

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.

  1. 9d ago First seen · 141 lines · 4,410 tokens per session scan A cc1b74d4a744

Subscribe to this mod's changes

obsidian-mcp-rs CLAUDE.md is an instructions file published in the GitHub repository MrRefactoring/obsidian-mcp-rs (4 stars, last pushed 3d ago), licensed MIT. It adds 4,410 tokens to every session, about $0.0221 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 2026-08-31.

Related

Other instructions, from other repositories

flow-like copilot-instructions.md

Copilot instructions for Rheosoph/flow-like, covering flow-like wasm node development — rust, project overview, build & test, architecture and pin types.

Rheosoph/flow-like · 1,349 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens