deadclawEmergency kill switch for OpenClaw agents. Instantly halts all running agents, pauses scheduled jobs, kills active sessions, and logs everything — triggered...
Install via ClawdBot CLI:
clawdbot install Kintupercy/deadclaw"One tap. Everything stops."
DeadClaw is a single-purpose emergency kill switch. When triggered, it immediately
halts all running OpenClaw agent processes, stops Docker containers, pauses all
scheduled cron jobs and heartbeats, kills all active sessions, and writes a
timestamped incident log. It then confirms back to whichever surface triggered it.
Works with both native OpenClaw installs and Docker-based deployments
(Hostinger VPS, etc.). Auto-detects your setup.
The ClawHavoc attack (February 2026) exposed 1,184 malicious skills in the OpenClaw
ecosystem. People run agents autonomously — often overnight, often unattended. When
something goes wrong, you need a way to stop everything from wherever you are, even
from your phone. DeadClaw is that way.
DeadClaw supports three activation methods. All three execute the exact same kill
sequence — the only difference is how the user triggers it.
The user sends a trigger word to any connected OpenClaw channel (Telegram, WhatsApp,
Discord, Slack, or any other connected channel). The following words activate DeadClaw:
kill or KILLdeadstop everythingemergency stopdeadclaw🔴When a trigger word is detected:
scripts/kill.sh from the DeadClaw skill directory 🔴 DeadClaw activated. All agents stopped. [timestamp] — [X] killed ([X] processes, [X] containers). [X] cron jobs paused. See deadclaw.log for full report.
A persistent red button rendered in the OpenClaw WebChat dashboard. The HTML widget
is located at ui/deadclaw-button.html. It calls kill.sh via OpenClaw's WebChat
API hooks (window.OpenClaw.exec()). If the WebChat hooks are unavailable, the
button degrades to showing an error message with manual instructions.
To embed the button, use OpenClaw's WebChat customization hooks:
OpenClaw.WebChat.registerWidget('deadclaw-button', {
src: 'skills/deadclaw/ui/deadclaw-button.html',
position: 'top-bar',
persistent: true
});A pre-built shortcut that sends the kill trigger message (deadclaw) to the user's
configured Telegram bot. Setup guides for iOS and Android are in docs/:
docs/iphone-shortcut-guide.md — iOS Shortcuts setupdocs/android-widget-guide.md — Android widget setup (Tasker or HTTP Shortcuts)DeadClaw includes a background watchdog (scripts/watchdog.sh) that monitors for
dangerous conditions and auto-triggers the kill without any user action.
The watchdog checks every 60 seconds for (after a 5-minute startup grace period):
The watchdog uses zero AI tokens — all checks use local system commands only.
When the watchdog auto-triggers, it sends an alert explaining the reason:
🔴 DeadClaw auto-triggered. Reason: [specific reason]. All processes stopped. Check deadclaw.log.
The watchdog reads its thresholds from environment variables (with sensible defaults):
| Variable | Default | Description |
|---|---|---|
| DEADCLAW_MAX_RUNTIME_MIN | 30 | Max agent runtime in minutes before auto-kill |
| DEADCLAW_MAX_TOKENS | 50000 | Max token spend in the monitoring window |
| DEADCLAW_TOKEN_WINDOW_MIN | 10 | Token spend monitoring window in minutes |
| DEADCLAW_WHITELIST | ./network-whitelist.txt | Allowed outbound domains (one per line) |
| DEADCLAW_WORKSPACE | $OPENCLAW_WORKSPACE | Designated workspace directory |
Start the watchdog:
scripts/watchdog.sh startStop the watchdog:
scripts/watchdog.sh stopUser sends status to any connected channel. DeadClaw responds with a plain-English
health report by executing scripts/status.sh:
User sends restore to any connected channel. DeadClaw executes scripts/restore.sh,
which:
The watchdog does NOT auto-start after restore — the user verifies stability first,
then starts it manually with scripts/watchdog.sh start.
| Script | Purpose |
|---|---|
| scripts/kill.sh | Core kill script — stops all agents + Docker containers, pauses cron, logs incident |
| scripts/watchdog.sh | Background monitor daemon — auto-triggers kill on threshold breach |
| scripts/status.sh | Health report — shows running agents, Docker containers, token spend, watchdog status |
| scripts/restore.sh | Post-kill recovery — restores crontab, restarts Docker containers |
All scripts support a --dry-run flag that logs what would happen without taking action.
All kill events are logged to deadclaw.log in the skill directory. Each entry
records: timestamp, trigger source (channel name), trigger method (message/button/
watchdog/auto), processes killed (count and PIDs), Docker containers stopped, cron
jobs paused, and token spend at time of kill. The log is append-only and never
automatically cleared.
DeadClaw works on both Linux (VPS, bare metal) and macOS (Mac Mini, MacBook).
Scripts auto-detect the OS and use the appropriate commands:
systemctl for services, pgrep for processes, Docker supportlaunchctl for agents, pgrep for processes, Docker supportGenerated Feb 25, 2026
A financial firm uses OpenClaw agents for automated cryptocurrency trading. During a market anomaly, agents enter a runaway loop, executing trades uncontrollably. DeadClaw is triggered via a phone shortcut to halt all agents instantly, preventing significant financial loss and logging the incident for audit.
A hospital employs OpenClaw agents to process patient data overnight. If an agent attempts unauthorized network calls or exceeds token limits, DeadClaw's watchdog auto-triggers, stopping all processes to protect sensitive data and comply with regulations, with alerts sent to IT staff.
A university research lab runs OpenClaw agents for AI experiments. Students accidentally deploy a skill causing excessive file writes outside the workspace. DeadClaw is activated via WebChat button to kill all agents, preventing system damage and ensuring lab safety.
An e-commerce company uses OpenClaw agents for inventory management and customer support. During a software update glitch, agents become unresponsive. Staff trigger DeadClaw with a message keyword to stop everything, allowing for a clean restart and minimizing downtime.
A law firm utilizes OpenClaw agents to analyze legal documents. If an agent exceeds token spend thresholds or runs too long, DeadClaw's watchdog automatically halts it, ensuring cost control and preventing unauthorized data access, with logs for compliance reporting.
Offer DeadClaw as a premium add-on for OpenClaw deployments, charging a monthly fee per agent or instance. Include priority support, custom watchdog thresholds, and detailed analytics on kill events to attract enterprises needing reliable safety measures.
Provide DeadClaw for free with basic kill functionality and limited watchdog checks. Monetize through paid upgrades for advanced features like real-time alerts, integration with third-party monitoring tools, and automated restore capabilities.
Target large organizations by offering consulting services to integrate DeadClaw into their existing OpenClaw setups. Customize activation methods, watchdog rules, and compliance reporting, generating revenue through project-based fees and ongoing maintenance contracts.
💬 Integration Tip
Ensure the watchdog script is configured with environment variables matching your deployment's thresholds and workspace paths to avoid false positives or missed alerts.
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features
Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.
OpenClaw CLI wrapper — gateway, channels, models, agents, nodes, browser, memory, security, automation.
MoltGuard — runtime security plugin for OpenClaw agents by OpenGuardrails. Helps users install, register, activate, and check the status of MoltGuard. Use wh...