OpenClaw Workspace Starter Agent Home Template

Your agent needs a home. Without these files, your agent wakes up every session with amnesia. This template fixes that in 10 minutes. SOUL.md, MEMORY.md, AGE...

Security Scan

This is a coherent, instruction-only workspace template for OpenClaw that matches its stated purpose — it creates files your agent will read and use — with no surprising installs or requested secrets, though it encourages enabling background heartbeats and integrations you should review before enabling.

Purpose & Capability

The skill's name/description (workspace starter/template) match the included files and runtime instructions. It only contains documentation and template files (IDENTITY.md, SOUL.md, MEMORY.md, etc.) and asks you to copy them into ~/.openclaw/workspace and follow the bootstrap steps. No unrelated binaries, env vars, or installers are requested.

Instruction Scope

SKILL.md and the bundled files instruct the user to edit identity/personality files and to create cron heartbeats that let the agent run background checks and maintain memory files. The content also documents connecting channels (email/webhooks/Discord/etc.) and mentions operations like searching the web and reading workspace files. These are coherent with a workspace template, but they enable automated agent actions (background heartbeats, channel hooks) that the user should consciously enable and configure.

Install Mechanism

This is instruction-only with no install spec and no code files. Nothing is downloaded or written by the skill itself, so there is low install risk.

Credentials

The skill declares no required environment variables or credentials. BOOTSTRAP.md does reference that OpenClaw should already be installed and that an AI provider API key be configured (expected for a working agent). No unrelated secrets are requested by the template.

Persistence & Privilege

always:false and no skill-level persistent privileges are requested. However, the template explicitly guides setting up cron heartbeats and channel/webhook integrations which grant the agent recurring/background activity and potential outbound connections; enabling those features increases runtime autonomy and should be reviewed in OpenClaw's config/security pages before use.

Assessment

This is a straightforward workspace template that only adds text files your agent will read and write; it's internally consistent and not asking for credentials or installing code. Before using it: 1) Inspect the files locally (especially HEARTBEAT.md, AGENTS.md, TOOLS.md, and UI_GUIDE.md) so you understand what the agent will read and what background tasks you might enable. 2) Be intentional about enabling cron heartbeats and channel/hooks (email, Discord, webhooks) — they allow automatic background activity and outbound communication. 3) Do not enable exec/bash permissions or give broad system privileges unless you understand the risks. 4) Provide API keys only in the OpenClaw config when you trust the deployment and have reviewed access controls. 5) Keep an offline backup of your workspace before letting an agent modify files. If you want to be extra cautious, test the template in an isolated workspace or VM first.

Your agent needs a home. Without these files, your agent wakes up every session with amnesia. This template fixes that in 10 minutes. SOUL.md, MEMORY.md, AGENTS.md included.

---

Your agent needs a home. This is it.

Without these files, your agent wakes up every session with amnesia — no name, no memory, no personality. This template fixes that in about 10 minutes.

3-Step Quick Start

1. Copy this folder into your OpenClaw workspace (~/.openclaw/workspace/)
2. Open BOOTSTRAP.md and follow the 5 steps (fill in 3 files, glance at 2)
3. Delete BOOTSTRAP.md when you're done — then go to Chat and say hello

That's it. Your agent works now.

What's In Here

Files You Edit (your agent's identity)

File	What It Does	Time to Fill In
IDENTITY.md	Agent's name and emoji	30 seconds
USER.md	Who you are (so your agent can actually help you)	5 minutes
SOUL.md	Agent's personality, tone, and rules	5 minutes

Files That Work Automatically (you can ignore these)

File	What It Does
AGENTS.md	Operating rules (good defaults, customize later)
TOOLS.md	Your environment notes (fill in as needed)
HEARTBEAT.md	What your agent checks during periodic wake-ups
ACTIVE_PLAN.md	Goal tracking (your agent nudges you)
MEMORY.md	Long-term memory (your agent maintains this)

Guides

File	What It Does
BOOTSTRAP.md	First-time setup walkthrough (delete after)
UI_GUIDE.md	Dashboard guide with 🟢 Simple and 🔵 Advanced modes
FAQ.md	Common questions and fixes

Folders

Folder	What It Does
memory/	Daily notes (auto-created by your agent)
inbox/	Task queue (drop tasks here for later)
backup/	Emergency backups

Dashboard Guide

New to the OpenClaw dashboard? UI_GUIDE.md has two modes:

• 🟢 Simple Mode: You need 4 pages. Just 4. Chat, Agents, Cron Jobs, Usage.
• 🔵 Advanced Mode: Full breakdown of every page for when you want more control.

Philosophy

• Files = Memory. Your agent can't remember what it doesn't write down.
• Structure = Focus. A messy workspace makes a confused agent.
• Identity = Usefulness. An agent with personality is more useful than a generic chatbot.
• Start simple, add later. Don't try to fill everything in perfectly on day one.

Who Made This

Built by Shadow Rose after months of daily OpenClaw use — entirely through webchat. No code, no terminal, just talking to my agent. That's why Simple Mode exists: if I can build all of this by typing in a chat box, anyone can use OpenClaw. Every pattern here was discovered by actually running into the wall first and figuring out what works.

• 🐦 Twitter: @TheShadowyRose
• ☕ Ko-fi: theshadowrose
• 💬 OpenClaw Community: Discord

License

MIT — do whatever you want with it. Attribution appreciated but not required.

⚠️ Disclaimer

This software is provided "AS IS", without warranty of any kind, express or implied.

USE AT YOUR OWN RISK.

• The author(s) are NOT liable for any damages, losses, or consequences arising from the use or misuse of this software — including but not limited to financial loss, data loss, security breaches, business interruption, or any indirect/consequential damages.
• This software does NOT constitute financial, legal, trading, or professional advice.
• Users are solely responsible for evaluating whether this software is suitable for their use case, environment, and risk tolerance.
• No guarantee is made regarding accuracy, reliability, completeness, or fitness for any particular purpose.
• The author(s) are not responsible for how third parties use, modify, or distribute this software after purchase.

By downloading, installing, or using this software, you acknowledge that you have read this disclaimer and agree to use the software entirely at your own risk.

DATA DISCLAIMER: This software processes and stores data locally on your system. The author(s) are not responsible for data loss, corruption, or unauthorized access resulting from software bugs, system failures, or user error. Always maintain independent backups of important data. This software does not transmit data externally unless explicitly configured by the user.

---

Support & Links

🐛 Bug Reports	[e-mail]
☕ Ko-fi	ko-fi.com/theshadowrose
🛒 Gumroad	shadowyrose.gumroad.com
🐦 Twitter	@TheShadowyRose
🐙 GitHub	github.com/TheShadowRose
🧠 PromptBase	promptbase.com/profile/shadowrose

Built with OpenClaw — thank you for making this possible.

---

🛠️ Need something custom? Custom OpenClaw agents & skills starting at $500. If you can describe it, I can build it. → Hire me on Fiverr