Borrowing it
Nothing to install: this file belongs to aud1ence/obsidian-wiki-mcp. 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/aud1ence/obsidian-wiki-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/aud1ence/obsidian-wiki-mcpWrote 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/aud1ence/obsidian-wiki-mcp/claude-md)<a href="https://agentmods.dev/instructions/aud1ence/obsidian-wiki-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aud1ence/obsidian-wiki-mcp/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/aud1ence/obsidian-wiki-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aud1ence/obsidian-wiki-mcp/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 | $0.01084 | $0.01084 |
| Opus 5 | $0.00542 | $0.00542 |
| Sonnet 5 | $0.00217 | $0.00217 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
obsidian-wiki-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 75 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.
Coding principles
Think before coding. When a request is ambiguous, surface the interpretations with tradeoffs and ask — don't pick silently. This matters most when modifying tool behavior, since changing a tool's response shape can silently break the host LLM's workflow.
Simplicity first. Minimum code that solves the problem. No speculative abstractions, no configurability that wasn't asked for. The BM25 implementation in index_manager.ts is intentionally self-contained (no external NLP library) — preserve that constraint unless there's a concrete reason to change it.
Surgical changes. Touch only what the task requires. _log.md and _index.md are auto-managed side effects of writes — don't clean them up or reformat them incidentally.
Verify with tests. For any change to a tool, run npm run test and confirm the relevant suite passes. Tests spin up a real MCP server process; a passing suite means the full request→response contract is intact.
Commands
npm run build # TypeScript compile → dist/
npm run dev # Run directly with tsx (no build needed)
npm run test # Integration test suite against a real MCP server process
Tests spin up a live McpTestClient subprocess per suite using a fresh temp vault — there is no mocking layer. The test runner is test/runner.js (plain Node, no framework).
Architecture
This is an MCP (Model Context Protocol) server that exposes wiki tools over stdio. The server is a pure storage/retrieval layer — it never calls an AI model; all content decisions are delegated to the host LLM.
Startup sequence (src/index.ts)
resolveConfig()— reads vault path from CLI--vault,WIKI_VAULT_PATHenv, or~/.obsidian-wiki-mcp.json- Builds two in-memory indexes from
_index.mdand_wiki/**/*.md:- BM25 index (
src/lib/index_manager.ts) — keyword scoring forwiki_queryandwiki_ingest - Backlink index (
src/lib/backlink_index.ts) —[[wikilink]]forward/back maps for lint and integrity
- BM25 index (
- Registers all tools via
registerTools(server, ctx)(src/tools/index.ts) - Connects an MCP
StdioServerTransport
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.
- 9d ago First seen · 75 lines · 1,084 tokens per session scan A 311fc1759406
obsidian-wiki-mcp CLAUDE.md is an instructions file published in the GitHub repository aud1ence/obsidian-wiki-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 1,084 tokens to every session, about $0.0054 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
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.