mnemosyne CLAUDE.md

mnemosyne CLAUDE.md is an instructions file for coding agents from rand/mnemosyne. It costs 8,021 tokens per session, scanned C, original, MIT.

Development instructions for the rand/mnemosyne project, including a workflow where separate agents coordinate planning, optimization, review, and memory handling. It also describes automatic checks around edits, commits, and pull requests.

In plain words
What is it for?
Use it when planning changes, coordinating the project's agents, following its work protocol, reviewing code, and preparing commits or pull requests.
Why use it?
It explains the project's required development process and the checks that can stop work from being committed or pushed when required memories or reviews are missing.

Instructions file

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/rand/mnemosyne/claude-md
Clone the repo
git clone --depth 1 https://github.com/rand/mnemosyne

Wrote 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.

agentmods badge for mnemosyne CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rand/mnemosyne/claude-md.svg)](https://agentmods.dev/instructions/rand/mnemosyne/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rand/mnemosyne/claude-md"><img src="https://agentmods.dev/badge/instructions/rand/mnemosyne/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,021 This file is loaded in full into every session.
When invoked 8,021 The same file — it is already loaded in full.
Security scan C 2 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 $0.08021 $0.08021
Opus 5 $0.04011 $0.04011
Sonnet 5 $0.01604 $0.01604
Haiku 4.5 $0.00802 $0.00802

Measured 4d ago against content hash f65d95932c1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

mnemosyne CLAUDE.md scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/steveyegge/beads/main/scripts/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/steveyegge/beads/main/scripts/install.sh | bash
CLAUDE.md · 1,103 lines

How it starts

The opening of the file, as written. The whole thing — 1,103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Development Guidelines

Core Principle: These guidelines establish workflows, decision trees, and checkpoints that protect against wasted time and technical debt. The Work Plan Protocol takes priority for all development work.

Multi-Agent Architecture: A sophisticated multi-agent system operates continuously in Claude Code to orchestrate work, optimize context, validate quality, and execute tasks in parallel.

⚡ AUTOMATIC MEMORY ENFORCEMENT: Mnemosyne usage is technically enforced via hooks. You cannot bypass this system:

  • SessionStart: Auto-loads memories at every session start
  • PostToolUse: Tracks "memory debt" after Edit/Write/Commit
  • PreToolUse: BLOCKS git push and PR creation if debt > 0
  • Stop: Validates memory usage before finishing responses

Memory debt system: Every Edit, Write, or Commit increments debt. After 3 events, you'll be prompted. git push is blocked until memories are stored. This is not optional.

Table of Contents

  1. Multi-Agent Orchestration System
  2. Work Plan Protocol START HERE
  3. Agentic Workflow (Beads)
  4. Critical Thinking & Pushback
  5. Language Stack & Tooling
  6. Testing & Validation
  7. Version Control & Git
  8. Experience Design + Development
  9. Skills System
  10. Anti-Patterns
  11. Quick Reference

1. Multi-Agent Orchestration System

Four primary agents operate continuously in every Claude Code session:

Agent 1: Orchestrator

Role: Central coordinator and state manager

Responsibilities:

  • Coordinate handoffs between agents with zero-copy data passing
  • Monitor execution state across parallel workstreams
  • Prevent race conditions and deadlocks through dependency-aware scheduling
  • Preserve context before compaction (75% threshold → .claude/context-snapshots/)
  • Maintain global work graph and schedule parallel work

Read the full file on GitHub · 1,103 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. 4d ago First seen · 1,103 lines · 8,021 tokens per session scan C f65d95932c1b

Subscribe to this mod's changes

mnemosyne CLAUDE.md is an instructions file published in the GitHub repository rand/mnemosyne (84 stars, last pushed 9mo ago), licensed MIT. It adds 8,021 tokens to every session, about $0.0401 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.