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/rickonono3/thinkmem/claude-mdgit clone --depth 1 https://github.com/RickoNoNo3/ThinkMemWrote 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/rickonono3/thinkmem/claude-md)<a href="https://agentmods.dev/instructions/rickonono3/thinkmem/claude-md"><img src="https://agentmods.dev/badge/instructions/rickonono3/thinkmem/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 | $0.01119 | $0.01119 |
| Opus 5 | $0.00560 | $0.00560 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
ThinkMem 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 3d 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 — 132 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.
Project Overview
THINK-MEM is an AI memory management system for LLMs, providing multiple memory types and communication protocols. It's built as an MCP (Model Context Protocol) server with both stdio and HTTP modes.
Core Architecture
The system provides three types of memory storage for LLMs:
Memory Types
- RawMemory: Unstructured text with summary management and line-level operations
- ListMemory: Ordered collections that can function as arrays, deques, or stacks
- GraphMemory: Graph/knowledge graph structures (planned but not yet implemented)
Key Components
- MCP Server (
src/server/ThinkMemServer.ts): Handles stdio protocol communication - StreamableHTTP Server (
src/server/HttpServer.ts): Web API with real-time events - Memory Management (
src/memory/): Core memory implementations - Storage Layer (
src/storage/): JSON file persistence with proper locking - Utilities (
src/utils/): Text processing and error handling
Development Commands
Build and Development
# Install dependencies
npm install
# Build TypeScript to JavaScript
npm run build
# Development mode (stdio)
npm run dev
# Production start (stdio mode by default)
npm start
# HTTP mode with custom port
npm start -- --mode http --port 8080
# Code linting
npm run lint
# Version synchronization (auto-runs after npm version)
npm run postversion
Testing
# Run all tests
npm test
# Run specific test pattern
npm test -- --testNamePattern="RawMemory"
# Run tests in watch mode
npm test -- --watch
# Generate coverage report
npm test -- --coverage
# Run tests with CI-like clean install
npm ci && npm test
Key Design Patterns
Dual Operation Modes
- Stdio Mode: MCP protocol over stdin/stdout for AI assistant integration
- HTTP Mode: StreamableHTTP for web applications and multi-client support
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.
- 3d ago First seen · 132 lines · 1,119 tokens per session scan A f5df323b5ec8
ThinkMem CLAUDE.md is an instructions file published in the GitHub repository RickoNoNo3/ThinkMem (7 stars, last pushed 10mo ago), licensed MIT. It adds 1,119 tokens to every session, about $0.0056 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
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
cyxj-groksearch CLAUDE.md
Instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.