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/bitbonsai/mcpvault/agents-mdgit clone --depth 1 https://github.com/bitbonsai/mcpvaultWrote 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/bitbonsai/mcpvault/agents-md)<a href="https://agentmods.dev/instructions/bitbonsai/mcpvault/agents-md"><img src="https://agentmods.dev/badge/instructions/bitbonsai/mcpvault/agents-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 | $0.02340 | $0.02340 |
| Opus 5 | $0.01170 | $0.01170 |
| Sonnet 5 | $0.00468 | $0.00468 |
| Haiku 4.5 | $0.00234 | $0.00234 |
Grade A, and why
mcpvault AGENTS.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 4d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Project Overview
MCPVault is a Model Context Protocol (MCP) server that provides a universal AI bridge for Obsidian vaults. It enables any MCP-compatible AI assistant (Claude, ChatGPT, Gemini, etc.) to safely read and write notes in Obsidian vaults while preserving YAML frontmatter and enforcing security boundaries.
Commands
# MCP server
npm run build # Compile TypeScript to dist/
npm test # Run test suite (Vitest)
npm run test:watch # Tests in watch mode
npm start /path/vault # Run server locally with tsx
# Single test
npm test -- path/to/test.test.ts
npm test -- -t "test name pattern"
# Publishing
npm run publish:dry # Dry run
npm run publish:beta # Explicit beta publish
# Production: follow RELEASING.md and create a GitHub Release
# Website
npm run website # Start Astro dev server with Bun (http://localhost:4321)
# MCP Inspector
npx @modelcontextprotocol/inspector npm start /path/to/vault
Architecture
File Structure
server.ts # MCP server entry point, tool registration, request handlers
src/
filesystem.ts # FileSystemService — all file operations with security
frontmatter.ts # FrontmatterHandler — YAML parsing via gray-matter
pathfilter.ts # PathFilter — security layer for path validation
search.ts # SearchService — full-text search with token-optimized output
uri.ts # Obsidian URI generation
types.ts # All TypeScript interfaces
*.test.ts # Co-located test files
website-shibumi/ # Bun + Hono + TSX website serving mcpvault.org (separate package)
Core Components
server.ts — Entry point. Registers 18 MCP tools, handles CLI args (--help, --version, --read-only, vault path), initializes services, routes tool calls. Read-only mode hides mutating tools and rejects direct mutation calls. Auto-trims whitespace from all path arguments. Exits on stdin EOF / SIGTERM / SIGINT (graceful server.close()), otherwise hosts orphan the process (#159).
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.
- 4d ago First seen · 154 lines · 2,340 tokens per session scan A 7dcdfebcd452
mcpvault AGENTS.md is an instructions file published in the GitHub repository bitbonsai/mcpvault (1,645 stars, last pushed 3d ago), licensed MIT. It adds 2,340 tokens to every session, about $0.0117 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 2026-08-30.
Other instructions, from other repositories
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).