Borrowing it
Nothing to install: this file belongs to rollecode/obsidian-remote-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/rollecode/obsidian-remote-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/rollecode/obsidian-remote-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/rollecode/obsidian-remote-mcp/claude-md)<a href="https://agentmods.dev/instructions/rollecode/obsidian-remote-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rollecode/obsidian-remote-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/rollecode/obsidian-remote-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rollecode/obsidian-remote-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 | $0.00618 | $0.00618 |
| Opus 5.5 | $0.00247 | $0.00247 |
| Sonnet 5.5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
obsidian-remote-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 7d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commits and code style
- 2 space indents
- One logical change per commit
- Commit subjects: one line, under 50 characters (GitHub's display limit)
- Use present tense in commits and CHANGELOG.md
- Use sentence case for headings (not Title Case)
- Never use bold text as headings, use proper heading levels instead
- Always add an empty line after headings
- No formatting in CHANGELOG.md except
inline codeand when absolute necessary - Use
*as bullets in CHANGELOG.md - CHANGELOG.md bullets: 2-10 words
- Rationale belongs in code comments or docs, never in commits or CHANGELOG.md
- Real semver: patch = fix/tweak, minor = new capability, major = breaking change. Default to patch
- One version bump per work session, not per commit or per fix
- Never use Claude watermark in commits (FORBIDDEN: "Co-Authored-By")
- No emojis in commits or code
- Keep CHANGELOG.md date up to date when adding entries
Architecture
auth-server.jsis the only network security boundary: OAuth 2.1 authorization server plus resource guard, proxying to supergateway on :8420- Port 8420 has no authentication at all and must never be exposed
- Two credential paths by design: OAuth for Claude.ai, static bearer token for Claude Code
- Tokens and authorization codes are stored as SHA-256 hashes in SQLite
- Single user by design - "authentication" is proving you know one password, there are no accounts
vault-mcp.jsis the MCP server over the vault, stdio only, no auth of its own. Tools live inlib/tools/, shared parsing inlib/- Every tool advertises a
vaultproperty, becauserelaxVaultRequirementin the auth server keys off it to injectDEFAULT_VAULT - Listings, tags, links and search all read one index in
lib/vault.js. Every write callsvault.invalidate() npm testruns the whole tool surface through a real MCP client against a throwaway vault. Add a case there for anything new
Security invariants
Do not weaken these without a deliberate decision:
- Every filesystem path goes through
resolveInVault, which resolves symlinks and proves containment .obsidianis never written to- Deletes move to
.trashunless the caller asks forpermanent - Writes are temp-file-then-rename, never truncate in place
- PKCE
S256only, neverplain - Redirect URIs matched exactly, never by prefix
- Authorization codes single use, deleted on first sight
- Refresh tokens rotate on every use
- Token audience validated against the resource identifier
- Secrets compared with
crypto.timingSafeEqual - A bad
client_idorredirect_urirenders an error, never redirects
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.
- 7d ago Changed · +8 lines · +191 tokens per session 3ac4d0d267f2
- 2mo ago First seen · 39 lines · 427 tokens per session scan A dc67875f003e
obsidian-remote-mcp CLAUDE.md is an instructions file published in the GitHub repository rollecode/obsidian-remote-mcp (2 stars, last pushed 7d ago), licensed MIT. It adds 618 tokens to every session, about $0.0025 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.
Other instructions, from other repositories
mcp-server-excel copilot-instructions.md
Copilot instructions for sbroenne/mcp-server-excel: This repository contains generated plugin publication output. Before changing anything, read the repository warning.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).