remember

Codify user friction into actionable methodology notes under ops/methodology.

1|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/adiman9/mnemos --skill remember-adiman9
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: remember
Source: https://github.com/adiman9/mnemos/tree/main/core/skills/remember
Command: npx skills add https://github.com/adiman9/mnemos --skill remember-adiman9

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Remember skill captures friction as actionable methodology notes, enabling a system to learn from corrections and improved workflows by codifying guidance that can be reused across sessions.

Core Features & Use Cases

  • Supports three capture modes: explicit, contextual, and session-mining to extract actionable guidance from user interactions.
  • Files notes into ops/methodology/ and maintains a living MOC to drive system behavior and learning cycles.
  • Works with /remember, /rethink, and context persistence to reduce repeated corrections and evolve the agent's playbook.

Quick Start

Run /remember with a clear friction description to capture a new methodology note.

Frequently Asked Questions about remember

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I save agent memory from user corrections to avoid repeating mistakes?

To save agent memory from user corrections, you can capture friction as actionable methodology notes. This process files guidance into ops/methodology/ and links it to a methodology MOC, enabling the system to learn and reuse corrections across sessions.

What is the best way to extract methodology notes from chat sessions?

Extracting methodology notes from chat sessions is best done using a session-mining mode. This approach identifies friction in user interactions and codifies them into actionable notes that guide future agent behavior and reduce repeated corrections.

Can I automatically build a methodology MOC from notes during my sessions?

Yes, you can automatically build and maintain a living methodology MOC from notes. The system files captured friction into ops/methodology/ and links them to the MOC to drive system behavior and learning cycles.

Does capturing context persistence require any specific dependencies or components?

Capturing context persistence requires no specific dependencies or components. The system verifies dependencies and enforces safety checks internally, producing a deployable metadata payload for discovery without external requirements.

When should I use explicit mode versus contextual mode for saving agent memory?

Use explicit mode when you run /remember with a clear friction description to capture agent memory directly. Use contextual mode to passively identify and codify friction from ongoing interactions without explicit commands.