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/stonematt/mcp-obsidian-cli/claude-mdgit clone --depth 1 https://github.com/stonematt/mcp-obsidian-cliWrote 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/stonematt/mcp-obsidian-cli/claude-md)<a href="https://agentmods.dev/instructions/stonematt/mcp-obsidian-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/stonematt/mcp-obsidian-cli/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 | $0.01010 | $0.01010 |
| Opus 5 | $0.00505 | $0.00505 |
| Sonnet 5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
mcp-obsidian-cli 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 5d 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 — 65 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
mcp-obsidian-cli — An MCP server distributed via npm/npx that wraps the Obsidian CLI plugin, exposing Obsidian's full native API surface to AI assistants. All operations go through the obsidian CLI binary (IPC to running Obsidian instance); there is no direct Obsidian API access.
Constraints
- ES modules only —
"type": "module"in package.json; MCP SDK requires ESM - Zero build step — plain
.jsfiles, no TypeScript, no bundler - Stdio transport — MCP server communicates over stdin/stdout
- Obsidian must be running — CLI commands fail if the app isn't open
Commands
# Run the server
node bin/server.js # or: npm start
# Run tests (Node.js built-in test runner)
npm test # runs everything under test/*.test.js
# Run via npx (as end users would)
npx mcp-obsidian-cli
Tests use node:test — no test framework dependency. test/run.test.js spawns bin/server.js as a child process to assert exit code and the running banner; test/server.test.js exercises createServer end-to-end via the SDK's InMemoryTransport with a fake ObsidianCli. The current contract is warn-and-continue when Obsidian is not detected — the server stays up; tool calls return OBSIDIAN_NOT_RUNNING until the app is opened.
Architecture
Three pieces, no top-level side effects in server.js:
bin/server.js(entrypoint) — the only file that performs I/O at module load. Reads config, prompts, andpackage.json#version; probes the CLI path viaresolveCliPath; builds theObsidianCliadapter; callscreateServer(...); connectsStdioServerTransport. Fatal errors here are the only path that callsprocess.exit.server.js(createServerfactory) — pure factory that returns a wiredMcpServer. Registers the genericobsidianpass-through tool, ~13 typed convenience tools, and four MCP prompts. Takescli,prompts,manifest(reserved for #10),version,knownVaults, andruntimeVaultas injected deps. Importing this file is silent.lib/obsidian-cli.js— adapter around theobsidian-clisubprocess.createObsidianCli({cliPath, vault, timeoutMs, execFile})returns{ exec, getVault, setVault }; result shape is{stdout, stderr, error|null}witherror.type ∈ {CLI_NOT_FOUND, TIMEOUT, EXECUTION_ERROR}. Also exportsresolveCliPath(PATH / known paths / pgrep fallback) andcreateObsidianRunningChecker(TTL-cached pgrep probe). All probes are dependency-injectable for tests.
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.
- 5d ago First seen · 65 lines · 1,010 tokens per session scan A b09621d187de
mcp-obsidian-cli CLAUDE.md is an instructions file published in the GitHub repository stonematt/mcp-obsidian-cli (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,010 tokens to every session, about $0.0051 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.
Other instructions, from other repositories
obsidian-mcp-server AGENTS.md
AGENTS.md instructions for nbaradar/obsidian-mcp-server, covering obsidian mcp server — agents.md, purpose, implementation plan, resources (planned) and tools (current).
mytwin-mcp CLAUDE.md
Claude Code instructions for LutoLabs/mytwin-mcp, covering myaitwin — guide for claude / agents, the canonical reference: read this first, architecture in one paragraph, local dev quickstart and open http://localhost:3000/twin.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).