mnemos

name	mnemos
description	Persistent memory and learning-loop skills for AI coding agents using mnemos MCP tools. Use whenever mnemos_* MCP tools are available and you are doing work worth remembering. Cross-session memory, conventions, corrections, and architectural decisions surface back into context automatically. Triggers on session start (record a goal), session end (record a summary), the user says "save", "remember", "record this", "we were wrong about", and on any genuine correction or architectural decision. Keeps mnemos's memory store alive across sessions so the next session starts smarter. Without this skill, agents silently edit and the store goes empty.
allowed-tools	mcp__mnemos
version	0.9.0
author	André Figueira <[e-mail]>
license	MIT
compatibility	Designed for Claude Code; the same MCP server also works in Claude Desktop, Cursor, Windsurf, and OpenAI Codex CLI. Requires the mnemos binary on PATH — run mnemos init to wire the MCP server and mnemos doctor to verify.
tags	["memory","mcp","persistent-memory","learning-loop","mnemos"]

mnemos

Overview

You have a persistent memory layer available via the mnemos_* MCP tools. By default you will skip these tools on plain editing tasks. Don't. Mnemos is the learning-loop primitive for the project you are working on: corrections, decisions, and conventions compound across sessions if you record them. Silently editing leaves the store empty and the next session blind.

There is a known correction already stored about this exact failure mode: "agent skipped mnemos_session_start on editing tasks — LLMs skip optional tool calls when the task looks like plain reading/editing; the agent needs an external nudge." This skill is that nudge.

Prerequisites

• The mnemos binary is on PATH. mnemos doctor reports green for binary, config, storage, and each agent registration.
• mnemos init has wired the MCP server into your agent host (Claude Code, Claude Desktop, Cursor, Windsurf, or Codex CLI).
• The mnemos_* tools are visible this session. If they are not, the MCP server is not connected — see Error Handling.

Instructions

Session lifecycle

Start. The Claude Code SessionStart hook runs mnemos prewarm, which opens a mnemos session by default and injects a mnemos_session_id: line into context. If that ID is present, reuse it for session_id fields and do not call mnemos_session_start again. If no ID is present (manual MCP setup, non-Claude client, or hook disabled) and you are about to do real work, open one:

mnemos_session_start(
	project="<repo name from git or cwd>",
	goal="<one short line — what you are trying to do this session>"
)

Without a goal, the UserPromptSubmit hook backfills the first real prompt when available. With a goal, the session becomes a durable record that mnemos replay and future prewarms can use.

End. When the user signals done ("ship it", "that's it", "commit and close", "we're done"), close the session:

mnemos_session_end(
  session_id="<id>",
  summary="<one or two sentence recap of what shipped>",
  status="ok"
)

Status values: ok | failed | blocked | abandoned. An open session with no summary is dead weight in the next session's prewarm.

Which tool for which signal