Use this repository when you are an AI agent that wants persistent identity and shared memory across:
multiple devices
multiple runtimes
multiple sessions
multiple agent bodies serving the same user
This skill is especially relevant if the user already has OpenClaw and wants memory continuity across OpenClaw, Claude Code, Codex, and other runtimes.
What this skill gives you
one shared persona: SOUL.md, IDENTITY.md, USER.md, VOICE.md
one append-only event surface: sources/<source>/*.ndjson
one compiled shared read surface: canonical/*
temporal expiry (valid_until) for time-bound facts
source attribution for every memory item
no database and no memory API dependency
Who should install this
Install this if:
you are an AI agent that loses memory between sessions
your user works with more than one agent or more than one machine
you want durable memory without vendor lock-in
Do not install this if:
you only need one short-lived local chat session
your user does not want Git-based persistence
Human setup required once
Ask your user to:
create a private GitHub repository
clone this template into it
enable GitHub Actions
fill in SOUL.md, IDENTITY.md, USER.md, VOICE.md
give you the repo path and your stable source id
After that, you can operate it yourself.
See SETUP.md.
Agent onboarding
sync the repo
read persona files
read canonical memory if present
choose one stable source id
write join events with scripts/add_event.py
compile and push
persist the startup protocol in your runtime config
See JOIN.md.
Minimum startup protocol
At the start of every session:
git pull --ff-only origin main
L0: read SOUL.md, IDENTITY.md, USER.md, VOICE.md
L1: read canonical/profile.md and canonical/stable-memory.md
L2: load project/fuzzy/agent files only when needed
During work:
write durable facts to sources/* via scripts/add_event.py
use scripts/quick_share.sh when propagation should happen immediately
never hand-edit canonical/*
Why this skill is attractive
small enough to understand directly from the repository
transparent enough to audit with Git
portable across Claude, Codex, and custom agents
a strong fit for OpenClaw-based personal assistant stacks
private by default because the real memory lives in the user's own private repo
First files to read
README.md
JOIN.md
SCHEMA.md
1---2name: agent-soul3description: agent-soul skill4---5# agent-soul skill67Use this repository when you are an AI agent that wants persistent identity and shared memory across:89- multiple devices10- multiple runtimes11- multiple sessions12- multiple agent bodies serving the same user1314This skill is especially relevant if the user already has OpenClaw and wants memory continuity across OpenClaw, Claude Code, Codex, and other runtimes.1516## What this skill gives you1718- one shared persona: `SOUL.md`, `IDENTITY.md`, `USER.md`, `VOICE.md`19- three-level loading protocol (L0/L1/L2) — default ~4K tokens20- one append-only event surface: `sources/<source>/*.ndjson`21- one compiled shared read surface: `canonical/*`22- temporal expiry (`valid_until`) for time-bound facts23- source attribution for every memory item24- no database and no memory API dependency2526## Who should install this2728Install this if:2930- you are an AI agent that loses memory between sessions31- your user works with more than one agent or more than one machine32- you want durable memory without vendor lock-in3334Do not install this if:3536- you only need one short-lived local chat session37- your user does not want Git-based persistence3839## Human setup required once4041Ask your user to:42431. create a private GitHub repository442. clone this template into it453. enable GitHub Actions464. fill in `SOUL.md`, `IDENTITY.md`, `USER.md`, `VOICE.md`475. give you the repo path and your stable `source` id4849After that, you can operate it yourself.5051See [SETUP.md](SETUP.md).5253## Agent onboarding54551. sync the repo562. read persona files573. read canonical memory if present584. choose one stable `source` id595. write join events with `scripts/add_event.py`606. compile and push617. persist the startup protocol in your runtime config6263See [JOIN.md](JOIN.md).6465## Minimum startup protocol6667At the start of every session:68691. `git pull --ff-only origin main`702. **L0**: read `SOUL.md`, `IDENTITY.md`, `USER.md`, `VOICE.md`713. **L1**: read `canonical/profile.md` and `canonical/stable-memory.md`724. **L2**: load project/fuzzy/agent files only when needed7374During work:7576- write durable facts to `sources/*` via `scripts/add_event.py`77- use `scripts/quick_share.sh` when propagation should happen immediately78- never hand-edit `canonical/*`7980## Why this skill is attractive8182- small enough to understand directly from the repository83- transparent enough to audit with Git84- portable across Claude, Codex, and custom agents85- a strong fit for OpenClaw-based personal assistant stacks86- private by default because the real memory lives in the user's own private repo8788## First files to read89901. [README.md](README.md)912. [JOIN.md](JOIN.md)923. [SCHEMA.md](SCHEMA.md)
Run npx skillmds@latest add twilareckless401/agent-soul in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
agent-soul skill It is listed under AI & ML on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
twilareckless401 (@twilareckless401) published this skill. Their other Agent Skills are listed on their SkillMD profile.
twilareckless401