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/sshisto/mnemo-mcp/agents-mdgit clone --depth 1 https://github.com/sshisto/mnemo-mcpWrote 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/sshisto/mnemo-mcp/agents-md)<a href="https://agentmods.dev/instructions/sshisto/mnemo-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sshisto/mnemo-mcp/agents-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 | $0.01265 | $0.01265 |
| Opus 5 | $0.00633 | $0.00633 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
mnemo-mcp AGENTS.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 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.
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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - mnemo-mcp
Persistent AI memory MCP Server. Python 3.13, uv, src layout.
Build / Lint / Test Commands
uv sync --group dev # Install dependencies
uv build # Build package (hatchling)
uv run ruff check . # Lint
uv run ruff format --check . # Format check
uv run ruff format . # Format fix
uv run ruff check --fix . # Lint fix (with --unsafe-fixes for aggressive)
uv run ty check # Type check (Astral ty)
uv run pytest # Run all tests (integration excluded by default)
uv run pytest -v # Verbose
uv run pytest -m integration # Run integration tests only
# Run a single test file
uv run pytest tests/test_db.py
# Run a single test class
uv run pytest tests/test_db.py::TestSearch
# Run a single test function
uv run pytest tests/test_db.py::TestSearch::test_basic_match -v
# Mise shortcuts
mise run setup # Full dev environment setup
mise run lint # ruff check + ruff format --check + ty check
mise run test # pytest
mise run fix # ruff check --fix + ruff format
mise run dev # uv run mnemo-mcp
Pytest Configuration
asyncio_mode = "auto"-- no@pytest.mark.asyncioneeded- Default timeout: 30 seconds per test
- Integration tests excluded by default (
-m 'not integration') - Test files:
test_*.pyintests/directory
Code Style
Formatting (Ruff)
- Line length: 88
- Quotes: Double quotes
- Indent: 4 spaces (Python), 2 spaces (JSON/YAML/TOML)
- Line endings: LF
- Target: Python 3.13
Ruff Rules
select = ["E", "F", "W", "I", "UP", "B", "C4"], ignore = ["E501"]
I= isort import ordering,UP= pyupgrade (modern syntax),B= bugbear,C4= comprehensions
Type Checker (ty)
Lenient config: unresolved-import, unresolved-attribute, possibly-missing-attribute all "ignore".
Import Ordering (isort via Ruff)
__future__imports- Standard library (
import asyncio,import json) - Third-party (
from loguru import logger,from pydantic_settings import BaseSettings) - Local (
from mnemo_mcp.config import settings,from mnemo_mcp.db import MemoryDB)
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 · 143 lines · 1,265 tokens per session scan A 635aefd28aff
mnemo-mcp AGENTS.md is an instructions file published in the GitHub repository sshisto/mnemo-mcp (2 stars, last pushed 6d ago), licensed MIT. It adds 1,265 tokens to every session, about $0.0063 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
wife AGENTS.md
Instructions for ma-nucho-pro/wife, covering if the user wants to install it, if the user wants to change something and rules that are not negotiable.
memohood AGENTS.md
Instructions for maximskorohod/memohood, covering agents.md — установка плагина memohood, что это, способ b — через git (человек ставит вручную, без чата), безопасность and справочные факты (для сверки при установке).
Muninn GEMINI.md
Gemini CLI instructions for wjohns989/Muninn, covering muninn mcp — sota+ development context, 🚀 sota+ development philosophy, 🛠 operational guidelines (always-on), 🏗 system architecture and 📂 project structure.
claude-persistent-memory CLAUDE.md
Instructions for MIMI180306/claude-persistent-memory, covering claude.md, what this is, commands, architecture and internal service communication.
muninn CLAUDE.md
Claude Code instructions for ravnltd/muninn, covering claude.md — muninn memory system, what happens automatically (no action needed), the 4 mcp tools (manual escape hatch), architecture and install / update.
wife CLAUDE.md
Instructions for ma-nucho-pro/wife, covering wife — notes for the agent reading this, if the user wants to install it, if the user wants to change something and rules that are not negotiable.