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/anthony-maio/mnemos/claude-mdgit clone --depth 1 https://github.com/anthony-maio/mnemosWrote 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/anthony-maio/mnemos/claude-md)<a href="https://agentmods.dev/instructions/anthony-maio/mnemos/claude-md"><img src="https://agentmods.dev/badge/instructions/anthony-maio/mnemos/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 5.1 | $0.00930 | $0.00930 |
| Opus 5 | $0.00465 | $0.00465 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
mnemos 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 6d 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 — 95 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
mnemos — a biomimetic memory architecture library for LLMs. Implements five neuroscience-inspired memory mechanisms: surprisal-gated encoding, mutable RAG, affective routing, sleep consolidation, and spreading activation. Python 3.10+, MIT licensed, alpha (0.1.0).
Repository Layout
mnemos/ → Source package
modules/ → Five biomimetic memory modules
utils/ → LLM, embedding, and storage provider abstractions
cli.py → Shell CLI for hooks and automation
mcp_server.py → MCP server for agent integration
tests/ → pytest suite (3 files: engine, modules, types)
examples/ → Runnable demos (basic_usage, full_pipeline, mcp_agent_demo)
docs/ → MCP_INTEGRATION.md, claude-code-hooks.json
# Website: https://mnemos.making-minds.ai (separate mnemos-web repo)
Development Commands
# Install (editable + dev deps)
pip install -e '.[dev]'
# Run all tests
pytest
# Run a single test file
pytest tests/test_engine.py
# Run a single test by name
pytest tests/test_modules.py -k "test_surprisal"
# Format
black .
# Type check (strict mode)
mypy .
# Run MCP server (stdio transport)
mnemos-mcp
# CLI commands (shell-friendly, defaults to SQLite)
mnemos-cli store "some content"
mnemos-cli retrieve "query" --top-k 5
mnemos-cli consolidate
mnemos-cli stats
Tests use MockLLMProvider + SimpleEmbeddingProvider + InMemoryStore — no external services needed. Async tests auto-detected via asyncio_mode = "auto".
Architecture
MnemosEngine (engine.py) orchestrates five modules through three paths:
- Encode (
process()): Input → SurprisalGate (filter novelty) → AffectiveRouter (tag emotion) → Store + SleepDaemon buffer - Decode (
retrieve()): Query → AffectiveRouter (classify) → SpreadingActivation (graph propagation) → AffectiveRouter (re-rank) → MutableRAG (reconsolidate stale facts) → Results - Consolidate (
consolidate()): SleepDaemon extracts semantic facts from episodic buffer → writes to store → prunes
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.
- 6d ago First seen · 95 lines · 930 tokens per session scan A 8c882ab560c7
mnemos CLAUDE.md is an instructions file published in the GitHub repository anthony-maio/mnemos (27 stars, last pushed 5mo ago), licensed MIT. It adds 930 tokens to every session, about $0.0047 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
mempalace CLAUDE.md
Claude Code instructions for MemPalace/mempalace, covering claude.md, the mission, design principles, contributing and setup.
pipelex CLAUDE.md
Claude Code instructions for Pipelex/pipelex, covering pipelex coding rules, commands, linting, keyword-only arguments check and cleaning derived files.
dingo AGENTS.md
AGENTS.md instructions for MigoXLab/dingo, covering dingo — agent instructions, project overview, tech stack, directory structure and core concepts.
parlant CLAUDE.md
Instructions for emcie-co/parlant: This is the main repo of Parlant (https://parlant.io).
redis-vl-python CLAUDE.md
Claude Code instructions for redis/redis-vl-python, covering claude.md - redisvl project context, frequently used commands, development workflow, redis setup and documentation.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.