Overview
The Zhentan agent is an OpenClaw skill pack. It holds the 2nd signing key on the Safe 2-of-2 and is the only component that communicates with the user via Telegram. The server handles deterministic screening — the agent handles everything interactive.
AI models: Qwen3-235B / Claude Sonnet 4.5 via OpenRouter
Setup
Symlink the skills into OpenClaw's workspace
mkdir -p ~/.openclaw/workspace/skills
ln -sf "$(pwd)/agent" ~/.openclaw/workspace/skills/zhentan
Restart the OpenClaw gateway
Skills
| Script | What it does |
|---|
check-pending.js | Monitors the pending queue for new transactions |
analyze-risk.js | Pattern-based risk scoring |
deep-analyze.js | GoPlus + Honeypot.is external security analysis |
sign-and-execute.js | Co-signs 2-of-2 and submits the UserOperation to Pimlico |
mark-review.js | Marks a transaction as pending review |
reject-tx.js | Rejects a transaction |
record-pattern.js | Records confirmed transaction into the behavioral profile |
toggle-screening.js | Toggles screening on/off |
queue-invoice.js | Queues an invoice for dashboard review |
get-status.js | Returns current screening mode and recent decisions |
Running Skills Directly
pnpm --filter zhentan-agent check-pending
pnpm --filter zhentan-agent analyze-risk
pnpm --filter zhentan-agent sign-and-execute
Telegram Commands
| Command | Action |
|---|
approve <tx-id> | Sign 2-of-2, execute, record pattern, update TG message with txHash |
reject <tx-id> | Reject, update TG message |
analyze <tx-id> | Run deep analysis (GoPlus + Honeypot.is) on demand |
get-status [safeAddress] | Current screening mode and recent decisions |
screening on / screening off | Toggle screening mode |
Transaction Lifecycle
pending → in_review → executed
→ rejected
| Status | Description |
|---|
pending | Queued by the client, risk score assigned |
in_review | Sent to Telegram, awaiting user response |
executed | Agent signed 2-of-2, UserOperation confirmed on-chain |
rejected | Blocked (score > 70) or rejected by the user |
Environment Variables
AGENT_PRIVATE_KEY=0xYourAgentPrivateKey
PIMLICO_API_KEY=your_pimlico_api_key
QUEUE_PATH=./pending-queue.json
STATE_PATH=./state.json
PATTERNS_PATH=./patterns.json
Queue file paths default to ~/.openclaw/workspace/skills/zhentan/pending-queue.json. Override with QUEUE_PATH.
