Borrowing it
Nothing to install: this file belongs to jclement/obsidian-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/jclement/obsidian-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/jclement/obsidian-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/jclement/obsidian-mcp/claude-md)<a href="https://agentmods.dev/instructions/jclement/obsidian-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jclement/obsidian-mcp/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 5.1 | $0.01607 | $0.01607 |
| Opus 5 | $0.00804 | $0.00804 |
| Sonnet 5 | $0.00321 | $0.00321 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
obsidian-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 6d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for working in this repo. Read this before making changes.
What this is
A self-hosted single-container service exposing an Obsidian vault over MCP, with a passkey-protected management UI, OAuth 2.1 + bearer auth, optional Obsidian Sync, and automatic git snapshots. Runtime is Bun + TypeScript + Hono; UI is server-rendered Hono JSX + HTMX + Tailwind v4; state is bun:sqlite.
Commands
Use mise tasks (they pin the toolchain):
| Task | What |
|---|---|
mise run dev |
Server with hot reload + Tailwind watch → http://localhost:3000 |
mise run test |
Full bun test suite |
mise run typecheck |
tsc --noEmit |
mise run build |
Minify CSS + bundle server to dist/ |
mise run docker:build |
Build the container image |
Direct equivalents: bun test, bun test test/vault.test.ts (single file), bun test -t "name" (by test name), bunx tsc --noEmit.
Always run bunx tsc --noEmit and bun test before committing. The suite is ~133 tests and ~25s; keep it green.
Architecture (src/)
server.ts— boot: config → migrate DB → snapshotter → sync supervisor →Bun.serve; SIGTERM lifecycle.app.tsx— Hono wiring, middleware order, route mounting.config.ts— env parsing.PUBLIC_URLis optional; when unset the public origin/rpID are derived per-request from proxy headers (web/origin.ts).vault/— the filesystem core.paths.ts(thesafePath/safeWritePathchokepoint — all paths go through it),store.ts(atomic writes, per-path mutex, content-hash optimistic concurrency),frontmatter.ts,markdown.ts,links.ts(wikilink resolution + rewrite),search.ts,obsidian-config.ts(reads.obsidian/settings + moment-format dates).mcp/—server.tsbuilds the McpServer; one file per tool intools/;audit.tsrecords every call;context.tsis the per-process handle passed to tools.auth/—webauthn.ts(passkeys, rpID pinning),sessions.ts,tokens.ts(static + OAuth bearer, hashed),middleware.ts(guards, rate limit, origin resolution).oauth/— hand-rolled OAuth 2.1 AS (DCR, PKCE, refresh rotation).snapshots/— git snapshots in a bare repo outside the vault (--git-dir/--work-tree), so no.gitever lands indata/Vault.sync/—ob.ts(isolates the obsidian-headless CLI; it's 0.0.x beta, flags may drift — change them only here),supervisor.ts(process supervision, SIGTERM→SIGKILL),lock.ts(one ob per vault).web/—layout.tsx,routes/*.tsx(one router per page),origin.ts.db/—index.ts(open + numbered migrations) andmigrations/*.sql.
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.
- 6d ago First seen · 63 lines · 1,607 tokens per session scan A 456d7604d8cf
obsidian-mcp CLAUDE.md is an instructions file published in the GitHub repository jclement/obsidian-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,607 tokens to every session, about $0.0080 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
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).
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.