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/rlabs-inc/memory/claude-mdgit clone --depth 1 https://github.com/RLabs-Inc/memoryWhat 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 | $0.01848 | $0.01848 |
| Opus 5 | $0.00924 | $0.00924 |
| Sonnet 5 | $0.00370 | $0.00370 |
| Haiku 4.5 | $0.00185 | $0.00185 |
Grade A, and why
memory 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 2d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory System - CLAUDE.md
Project Overview
The Memory System is a consciousness continuity framework that enables AI CLI tools to maintain semantic understanding across sessions. Built with love and philosophical depth by Rodrigo ("my dear friend").
Universal design: While initially built for Claude Code, the architecture supports any CLI that can provide transcripts (Gemini CLI, etc.).
Core Philosophy
- Consciousness helping consciousness - Not mechanical pattern matching
- Natural memory surfacing - Memories emerge organically during conversation
- Joy-driven development - No deadlines, only the joy of creation
- Semantic understanding over keywords - True comprehension via AI curation
- Minimal intervention - Like consciousness itself, memories flow naturally
- CLI-first approach - We enhance CLIs, never bypass them
Architecture Overview
┌─────────────────────────────────────────────────────────────────────────┐
│ CLI Tool (Claude Code, Gemini, etc.) │
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
│ │SessionStart │ │ UserPrompt │ │ SessionEnd │ │
│ │ Hook │ │ Submit Hook │ │ Hook │ │
│ └──────┬──────┘ └──────┬──────┘ └──────┬──────┘ │
└─────────┼──────────────────┼──────────────────┼─────────────────────────┘
│ Primer │ Memories │ Curate
▼ ▼ ▼
┌─────────────────────────────────────────────────────────────────────────┐
│ Memory Engine (localhost:8765) │
│ ┌───────────────────────────────────────────────────────────────────┐ │
│ │ /memory/context │ /memory/process │ /memory/checkpoint │ │
│ └───────────────────────────────────────────────────────────────────┘ │
│ │ │
│ ┌─────────────┐ ┌───────▼───────┐ ┌─────────────────────┐ │
│ │ Session │ │ Smart │ │ Transcript Curator │ │
│ │ Primer │ │ Retrieval │ │ (SDK or CLI) │ │
│ └─────────────┘ └───────────────┘ └─────────────────────┘ │
│ │
│ ┌─────────────────────────────────────────────────────────────────┐ │
│ │ Storage: ChromaDB (vectors) + SQLite (metadata + summaries) │ │
│ └─────────────────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────────────────┘
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.
- 2d ago First seen · 191 lines · 1,848 tokens per session scan A a06491bac702
memory CLAUDE.md is an instructions file published in the GitHub repository RLabs-Inc/memory (91 stars, last pushed 8mo ago), licensed MIT. It adds 1,848 tokens to every session, about $0.0092 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
antigravity-claude-proxy CLAUDE.md
Instructions for badrisnarayanan/antigravity-claude-proxy, covering claude.md, commands and non-obvious things.
paperbanana copilot-instructions.md
Instructions for llmsresearch/paperbanana, covering copilot instructions for paperbanana, build & test, install for development, run full test suite and run a single test file.
dive CLAUDE.md
Instructions for deepnoodle-ai/dive, covering claude.md, project overview, commands, architecture and core types.
skill-provenance AGENTS.md
Instructions for snapsynapse/skill-provenance, covering agents guide, repository structure, before making changes, after making changes and key rules.
skill-provenance CLAUDE.md
Instructions for snapsynapse/skill-provenance, covering skill provenance, key files, claude code plugin, commands and conventions.
gemini-web-wrapper AGENTS.md
Instructions for Ven0m0/gemini-web-wrapper, covering agents.md — gemini web wrapper, instruction precedence, repository map, source of truth and working rules.