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/rand/mnemosyne/claude-mdgit clone --depth 1 https://github.com/rand/mnemosyneWrote 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/rand/mnemosyne/claude-md)<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>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 | $0.08021 | $0.08021 |
| Opus 5 | $0.04011 | $0.04011 |
| Sonnet 5 | $0.01604 | $0.01604 |
| Haiku 4.5 | $0.00802 | $0.00802 |
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 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 pushis blocked until memories are stored. This is not optional.
Table of Contents
- Multi-Agent Orchestration System
- Work Plan Protocol START HERE
- Agentic Workflow (Beads)
- Critical Thinking & Pushback
- Language Stack & Tooling
- Testing & Validation
- Version Control & Git
- Experience Design + Development
- Skills System
- Anti-Patterns
- 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
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 · 1,103 lines · 8,021 tokens per session scan C f65d95932c1b
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.
Other instructions, from other repositories
gossipcat-ai CLAUDE.md
Claude Code instructions for gossipcat-ai/gossipcat-ai, covering claude.md, gossipcat — multi-agent orchestration, your role, agent accuracy — skill development and scoped agent contract.
Dorothy CLAUDE.md
Instructions for Charlie85270/Dorothy, covering memory system, memory and autonomy.
workflow AGENTS.md
AGENTS.md instructions for vercel/workflow, covering agent instructions, architecture, core components, workflow execution model and development commands.
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
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.