agentmods.dev

mindcache CLAUDE.md

Project instructions for MindCache, an MCP server that lets AI assistants read and manage notes in Obsidian vaults. They describe the repository layout, server code, commands, tools, and resources.

In plain words
What is it for?
Building, checking, testing, and developing MindCache, including its server, Obsidian file access, configuration, note templates, tools, and vault resources.
Why use it?
They give a coding agent the project context needed to work in the right packages and use the correct commands.

Instructions file

2 4mo ago A scan 542 tokens original MIT
View the source file augmnt/mindcache
Install

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.

agentmods
npx agentmods add instructions/augmnt/mindcache/claude-md
Clone the repo
git clone --depth 1 https://github.com/augmnt/mindcache
Per session 542 This file is loaded in full into every session.
When invoked 542 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00542 $0.00542
Opus 5 $0.00271 $0.00271
Sonnet 5 $0.00108 $0.00108
Haiku 4.5 $0.00054 $0.00054

Measured yesterday against content hash 324165875af5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mindcache 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 yesterday.

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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MindCache

MCP server that bridges Obsidian vaults with AI assistants.

Project Structure

mindcache/
├── packages/
│   ├── server/         # MCP server (npm package: mindcache)
│   └── website/        # Landing page (usemindcache.com)
├── package.json        # Root workspace config
└── pnpm-workspace.yaml

Server Package (packages/server/)

  • Entry: src/cli.ts — CLI + MCP server startup
  • Server: src/server.ts — MCP server creation, tool/resource registration
  • Obsidian Client: src/obsidian.ts — Direct filesystem client for Obsidian vaults (no plugin required)
  • Config: src/config.ts — Configuration loading from YAML/env vars
  • Templates: src/templates.ts — Note template engine
  • Tools: src/tools/ — 44 MCP tools organized by category (find, read, remember, journal, write, connect, organize, understand, tasks, vault)
  • Resources: src/resources/ — 4 MCP resources (vault://today, vault://recent, vault://tags, vault://context)

Commands

# Build
pnpm build          # Build all packages
pnpm --filter server build

# Type check
pnpm --filter server lint

# Test
pnpm --filter server test

# Dev
pnpm --filter server dev     # Watch mode
pnpm --filter website dev    # Website dev server

Tech Stack

  • TypeScript, ESM-only
  • MCP SDK v1.x (@modelcontextprotocol/sdk)
  • Zod for schema validation
  • tsup for building
  • Vitest for testing
  • Astro + Tailwind for website

Conventions

  • Logging: Always use process.stderr.write(), never console.log
  • Error handling: Return { content: [...], isError: true } for tool errors
  • Tool signatures: (server: McpServer, client: ObsidianClient, config: MindCacheConfig) => void
  • Config: Support both YAML file and environment variables
  • Templates: Mustache-style {{variable}} placeholders

Important

  • @modelcontextprotocol/sdk is imported from subpaths: server/mcp.js, server/stdio.js
  • All tool files must use _config prefix for unused config parameters (strict mode)
  • The server reads the vault directly from the filesystem — no Obsidian plugins required

Read the full file on GitHub · 66 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. yesterday First seen · 66 lines · 542 tokens per session scan A 324165875af5

Subscribe to this mod's changes

mindcache CLAUDE.md is an instructions file published in the GitHub repository augmnt/mindcache (2 stars, last pushed 4mo ago), licensed MIT. It adds 542 tokens to every session, about $0.0027 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.

Data and AIMemory and contextTestingaiclaudeclaude-codeknowledge-basemcpmcp-server
Related

Other instructions, from other repositories

openagent CLAUDE.md

Claude Code instructions for the-open-agent/openagent, covering claude.md, commands, architecture, backend (go / beego) and frontend (react).

the-open-agent/openagent · 1,049 tokens

llm-wiki-agent GEMINI.md

Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.

SamurAIGPT/llm-wiki-agent · 1,590 tokens

OpenKB AGENTS.md

Instructions for VectifyAI/OpenKB, covering agents.md — openkb map for coding agents, read next, dev commands, module map (openkb/) and hard invariants.

VectifyAI/OpenKB · 681 tokens

Starcat AGENTS.md

Instructions for starcat-app/Starcat, covering agents.md, 🚨 硬性铁律（每次写代码前必读，违反即返工）, 🌿 git 分支与 worktree（强制）, 🧭 主进度索引（每次开工前必读） and 状态符号（与功能实现总览.md 同步）.

starcat-app/Starcat · 7,077 tokens

DocMason copilot-instructions.md

Instructions for JetXu-LLM/DocMason, covering docmason github copilot notes and copilot-specific delta.

JetXu-LLM/DocMason · 482 tokens

DeepRefine-Skill GEMINI.md

Instructions for HKUST-KnowComp/DeepRefine-Skill, covering deeprefine skill for gemini cli, core behavior and commands.

HKUST-KnowComp/DeepRefine-Skill · 372 tokens