portable-memory-core

Name: portable-memory-core
Author: mphinance

15stars3forks

How to install portable-memory-core?

mphinance/alpha-skills/portable-memory-core

$npx -y skills add mphinance/alpha-skills --skill portable-memory-core

Installs into the current project.

Summary

A meta-skill that establishes a 'One Brain' portable memory folder (.agent/). It persists context, user preferences, identity rules, and execution history across different AI harnesses (Claude Code, Cursor, Windsurf, OpenClaw).

Files · 1

View on GitHub

SKILL.md

1	# Portable Memory Core
2
3	"Never explain yourself twice."
4
5	This skill enforces the `One Brain` protocol. Instead of scattering your preferences across dozens of system prompts, it centralizes them into a portable `.agent/` directory that any LLM runner can hook into.
6
7	## Core Directives
8
9	1. Memory Synchronization: Upon startup, read from `.agent/memory.yaml`.
10	2. Context Passing: Whenever the user switches contexts (e.g., from Cursor to OpenClaw), this skill ensures the new context loads the latest state from `.agent/state.json`.
11	3. Identity Enforcement: Enforces the `IDENTITY.md` rules (e.g., "Caveman mode", "No em dashes", "Substack voice") universally across all generated code and text.
12	4. Harness Agnostic: Works seamlessly whether the upstream harness is Claude CLI, a custom Python script, or a GUI.
13
14	## Usage
15
16	When activated, you will automatically:
17	- Load `.agent/preferences.yaml`
18	- Update `.agent/history.json` with the current session summary.
19	- Export relevant variables to the local workspace.

People who liked this also viewed

6 picks

Type