agentmods.dev

obsidian-wiki-mcp: Instructions file for Claude Code

CLAUDE.md

obsidian-wiki-mcp CLAUDE.md is an instructions file for Claude Code from aud1ence/obsidian-wiki-mcp. It costs 1,084 tokens per session, scanned A, original, MIT.

A project instruction file for an Obsidian wiki MCP server, explaining its coding rules, commands, architecture, and startup process.

In plain words
What is it for?
It is for guiding work on the TypeScript server, including its BM25 search index, tests, build commands, and startup sequence.
Why use it?
It gives the coding agent project-specific guidance, reducing the risk of ambiguous changes, unnecessary abstractions, or untested tool modifications.

Instructions file for Claude Code

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

This is aud1ence/obsidian-wiki-mcp's own configuration. It tells Claude Code how to work on obsidian-wiki-mcp 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-wiki-mcp configures →

not rated 1repo 6mo ago A scan 1,084 tokens original MIT
View source ↗ aud1ence/obsidian-wiki-mcp
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/aud1ence/obsidian-wiki-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/aud1ence/obsidian-wiki-mcp

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-wiki-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aud1ence/obsidian-wiki-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/aud1ence/obsidian-wiki-mcp/claude-md)
Your own site
<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.

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

Your own site · 80×15
<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>
Per session 1,084 This file is loaded in full into every session.
When invoked 1,084 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 $0.01084 $0.01084
Opus 5.5 $0.00434 $0.00434
Sonnet 5.5 $0.00217 $0.00217
Haiku 4.5 $0.00108 $0.00108

Measured 2mo ago against content hash 311fc1759406, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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 · 75 lines

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)

  1. resolveConfig() — reads vault path from CLI --vault, WIKI_VAULT_PATH env, or ~/.obsidian-wiki-mcp.json
  2. Builds two in-memory indexes from _index.md and _wiki/**/*.md:
    • BM25 index (src/lib/index_manager.ts) — keyword scoring for wiki_query and wiki_ingest
    • Backlink index (src/lib/backlink_index.ts) — [[wikilink]] forward/back maps for lint and integrity
  3. Registers all tools via registerTools(server, ctx) (src/tools/index.ts)
  4. Connects an MCP StdioServerTransport

Read the full file on GitHub · 75 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. 2mo ago First seen · 75 lines · 1,084 tokens per session scan A 311fc1759406

Subscribe to this mod's changes

obsidian-wiki-mcp CLAUDE.md is an instructions file published in the GitHub repository aud1ence/obsidian-wiki-mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 1,084 tokens to every session, about $0.0043 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 2026-08-31.

karpathy-llm-wikillm-wikiobsidian
Related

obsidian-wiki-mcp CLAUDE.md compared with instructions from other repositories

obsidian-wiki-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
obsidian-wiki-mcp CLAUDE.mdaud1ence/obsidian-wiki-mcpInstructions file16mo agoMITA1,084Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode