VerifiedPlugin
openclaw-skill
A comprehensive Agent Skill for installing, configuring, operating, and troubleshooting OpenClaw — a self-hosted, multi-channel AI agent gateway.
1 skill
@win4rAgent Memory
Plugin
openclaw-workspace
A Claude Code skill for maintaining and optimizing OpenClaw workspace files — the markdown files that form an AI agent's soul, memory, and operating procedures.
Plugin Signal44/100Fair
maintained34
capable14
documented100
adopted52
Install
$ npx -y skills add win4r/openclaw-workspace --agent claude-code
What's inside
README
openclaw-workspace
A Claude Code skill for maintaining and optimizing OpenClaw workspace files — the markdown files that form an AI agent's soul, memory, and operating procedures.
What is this?
OpenClaw is a self-hosted, multi-channel AI agent gateway (WhatsApp, Telegram, Discord, Slack, and more). Every OpenClaw agent has a workspace — a directory of markdown files that are injected into the system prompt on each turn, giving the agent its identity, behavioral rules, environmental knowledge, and long-term memory.
These workspace files are powerful but require careful management:
- Too much content wastes tokens on every single turn
- Redundancy between files creates confusion and contradictions
- Stale content (old SSH hosts, deprecated rules, finished tasks) silently degrades agent quality
- Missing security gates can leak private memory into group chats
This skill gives Claude Code the knowledge to audit, optimize, and build OpenClaw workspace files correctly.
Workspace Files Overview
| File | Purpose | Loaded When | Visible to Sub-agents? |
|---|---|---|---|
AGENTS.md | Boot sequence, checklists, behavioral rules | Every turn (all agents) | Yes |
SOUL.md | Persona, tone, values, continuity philosophy | Every turn (all agents) | Yes |
TOOLS.md | Env-specific notes (SSH, TTS, cameras, devices) | Every turn (main + sub-agents) | Yes |
USER.md | Human profile, preferences, relationship context | Every turn (main sessions only) | No |
IDENTITY.md | Name, emoji, avatar, self-description | Every turn | Yes |
HEARTBEAT.md | Periodic check tasks and health routines | Every heartbeat turn | Depends |
BOOT.md | Startup actions (hooks.internal.enabled required) | On gateway startup | No |
BOOTSTRAP.md | First-time onboarding script — delete after use | New workspaces only | No |
MEMORY.md | Long-term curated facts and iron-law rules | Main sessions only | Never |
memory/YYYY-MM-DD.md | Daily session logs | Per AGENTS.md boot sequence | No |
checklists/*.md | Step-by-step ops guides | On demand (referenced from AGENTS.md) | No |
Token Budget
| Constraint | Limit |
|---|---|
| Per file hard cap | 20,000 chars (truncated if exceeded) |
| Total across all bootstrap files | ~150,000 chars |
| Recommended target per file | 10,000–15,000 chars |
Security Rule
MEMORY.mdmust NEVER be loaded in group chats or sub-agent sessions. It contains private user context that must not leak. The boot sequence inAGENTS.mdmust gate its loading explicitly:"Main session only: Read MEMORY.md".
Workspace Directory Structure
~/.openclaw/workspace/
├── AGENTS.md # Operating manual — boot sequence, rules, checklists table
├── SOUL.md # Persona, tone, values
├── TOOLS.md # Env-specific: SSH hosts, TTS voices, camera IDs
├── USER.md # Human profile (main sessions only)
├── IDENTITY.md # Name, emoji, avatar
├── HEARTBEAT.md # Periodic task instructions
├── BOOT.md # Startup hook actions
├── BOOTSTRAP.md # First-run onboarding (delete after use)
├── MEMORY.md # Iron-law rules (main sessions only)
├── memory/
│ ├── 2026-03-10.md # Daily session logs
│ └── archive/ # Old logs (> 30 days)
├── checklists/
│ ├── deploy-agent.md
│ ├── gateway-restart.md
│ └── config-patch.md
└── docs/ # On-demand docs (NOT auto-loaded every turn)
├── agent-rules-detail.md
└── ssh-reference.md
What This Skill Does
When invoked, this skill guides Claude Code through five main workflows:
1. Audit Existing Workspace
Reads all workspace files, checks character counts, identifies bloat, spots redundancy between files, finds stale content, and proposes targeted edits.
# Quick size audit
wc -c ~/.openclaw/workspace/*.md
Files over 10,000 chars are prime candidates for trimming or moving content to docs/ (loaded on demand).
2. Set Up a New Workspace from Scratch
Creates workspace files in the correct order (SOUL → AGENTS → IDENTITY → USER → TOOLS → MEMORY → optional files). Ensures the boot sequence, security gates, and checklist table are all properly wired up.
Minimal viable workspace: AGENTS.md + SOUL.md + TOOLS.md. Everything else is optional.
3. Memory Distillation
Processes memory/YYYY-MM-DD.md daily logs into MEMORY.md. Promotes recurring mistakes and hard-won rules to iron-law format, archives old logs, and checks for rules that have matured enough to move to a skill's SKILL.md instead.
4. Add or Update Checklists
Creates checklists/<operation>.md files for high-risk operations (deploys, config changes, gateway restarts) and registers them in the AGENTS.md checklists routing table.
5. Update TOOLS.md
Adds new environment-specific entries (SSH hosts, TTS voices, camera/device IDs) and cleans out stale entries.
How to Install
This is a Claude Code skill. Place it in your skills directory:
# Clone into your Claude Code skills directory
git clone https://github.com/win4r/openclaw-workspace ~/.claude/skills/openclaw-workspace
Claude Code will automatically detect and register the skill. It will appear in the skill list as:
openclaw-workspace — Use when maintaining or optimizing OpenClaw workspace files...
Manual Installation
Copy the skill directory anywhere Claude Code looks for skills:
~/.claude/skills/openclaw-workspace/(recommended)- Per-project:
.claude/skills/openclaw-workspace/
How to Use
Once installed, Claude Code will automatically invoke this skill when you:
- "Review my AGENTS.md for token efficiency"
- "Help me set up a new OpenClaw workspace"
- "Distill my memory logs into MEMORY.md"
- "Add a checklist for gateway restarts"
- "Audit my workspace files for redundancy"
- "My MEMORY.md is getting too large, help me clean it up"
You can also explicitly ask: "Use the openclaw-workspace skill to..."
Common Issues
File exceeds token limit (> 20,000 chars)
Move content to docs/ (loaded on demand, not every turn). Keep only what needs to be in context on every single turn.
MEMORY.md leaking to group chats
Add explicit gating in AGENTS.md boot sequence: "2. Main session only: Read MEMORY.md". Without this gate, the agent may load it in any context.
Boot sequence not loading files
The agent follows AGENTS.md boot sequence instructions — it won't auto-discover files. Make sure each file is explicitly named in the boot sequence.
Workspace changes not taking effect
Workspace files are read at session start. Start a new session or restart the gateway for changes to apply.
MEMORY.md growing unbounded
Run memory distillation monthly. Promote mature rules to skill SKILL.md files (more appropriate home for stable, tool-specific rules). Delete rules about completed tasks.
File Reference
| File | Description |
|---|---|
SKILL.md | Main skill — all workflows, common issues, workspace paths |
references/workspace-files.md | Deep-dive on every workspace file: purpose, design principles, anti-patterns, section structure |
references/optimization-guide.md | Token efficiency strategies, audit commands, memory distillation process, redundancy audit table |
Related
- OpenClaw — the gateway this skill supports
- openclaw skill — gateway operations, channel setup, multi-agent routing (separate skill)
License
MIT
Buy Me a Coffee
My WeChat Group and My WeChat QR Code
File tree
win4r/openclaw-workspaceView on GitHub
README_CN.md README.md references/ optimization-guide.md workspace-files.md SKILL.md
More Flows by @win4r.
@win4rFAQ
openclaw-workspace is a Claude Code plugin with 1 hand-picked skill for agent memory work, indexed on Flowy. Install it with the command on its page. It includes openclaw-workspace. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is openclaw-workspace?
- A Claude Code skill for maintaining and optimizing OpenClaw workspace files — the markdown files that form an AI agent's soul, memory, and operating procedures.
- How do I install openclaw-workspace?
- Run these in Claude Code: npx -y skills add win4r/openclaw-workspace --agent claude-code. Then prompt normally.
- Does openclaw-workspace auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is openclaw-workspace free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.