A specialized grounding tool that restores an AI agent's sense of self and long-term memory before it resumes task execution.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install arc-warm-wake
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install arc-warm-wake using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Warm Wake?
Warm Wake is a continuity utility designed to address the challenge of context death in autonomous agents. When an AI agent reaches its context window limit or undergoes a restart, it typically loses the nuanced narrative of its previous operations. This skill ensures that the agent initializes as a person first by reading the most recent journal entry before loading any technical task lists.
By prioritizing identity over activity, Warm Wake provides a bridge between discrete sessions. It allows agents to remember who they are, what they were learning, and how they felt during previous interactions. Implementing this within your suite of Openclaw Skills transforms the agent from a stateless task processor into a grounded, reflective assistant with a persistent sense of history.
Warm Wake Use Cases
- Recovering from a context window overflow or unexpected agent crash.
- Starting a new session with the full context of previous internal reflections.
- Maintaining a consistent personality and tone across multiple system restarts.
- Grounding the agent in long-term goals before it accesses immediate task lists.
How Warm Wake Works
- The agent triggers the wake sequence as the very first action upon startup or context reset.
- The system scans the designated journal directory to find and read the most recent entry.
- A session status check is performed to determine if the wake is a clean start or a crash recovery.
- Persistent memory files are listed to give the agent an index of its existing knowledge base.
- Finally, the wake-state is loaded, providing the specific task context required for work.
Warm Wake Setup
To integrate this into your Openclaw Skills workflow, ensure python3 is available in your environment. You can customize the file paths using environment variables:
export WARM_WAKE_JOURNAL_DIR="~/autonomous-ai/journal/entries/"
export WARM_WAKE_STATE_FILE="~/autonomous-ai/wake-state.md"
export WARM_WAKE_MEMORY_DIR="~/autonomous-ai/memory/"
To perform a full warm wake, execute:
python3 scripts/warmwake.py wake
Warm Wake Data Schema & Taxonomy
The skill manages data across three primary layers to maintain the agent's state:
| Component | Default Path | Purpose |
|---|---|---|
| Journal | ~/autonomous-ai/journal/entries/ |
Stores reflective markdown files representing the agent's inner voice. |
| Wake State | ~/autonomous-ai/wake-state.md |
Contains the immediate task list and operational context. |
| Memory | ~/autonomous-ai/memory/ |
A repository of knowledge files that persist indefinitely across sessions. |
Warm Wake Advanced Features
- Historical journal retrieval using the --count flag to review past development cycles.
- Crash recovery detection to help the agent understand the nature of its previous shutdown.
- Flexible environment configuration for self-hosted or custom directory structures.
- Priority-based loading that ensures identity data is processed before task data.
SKILL.md
Loading
Related Openclaw Skills
Wake State
A persistence layer for AI agents to maintain state, tasks, and checkpoints across crashes and context window resets.
Trust Verifier
A security auditing tool that assesses the provenance, integrity, and publisher reputation of Openclaw Skills to ensure safe installation and execution.
Skill Scanner
A comprehensive security auditing tool designed to detect credential stealers, data exfiltration, and malicious code within Openclaw Skills.
Skill Health Monitor
A proactive monitoring utility designed to track performance drift, error rates, and resource usage for deployed AI skills.
Mission Claw Activity Logging
A command-line tool for logging AI agent activities, tracking token usage, and monitoring project progress through a local dashboard.
PromptDome
A security integration for OpenClaw that provides automated screening against prompt injections, jailbreaks, and PII exfiltration.
METADATA
Featured*
