letsping

\r \r

Install (runtime)\r

\r This registry entry is instruction-only. The letsping_ask runtime is provided by the npm package @letsping/openclaw-skill. Use one of:\r \r

• npm: npm install @letsping/openclaw-skill (then register the skill in your OpenClaw workspace so it loads letsping_ask).\r
• Clone: git clone https://github.com/CordiaLabs/openclaw-skill ~/.openclaw/workspace/skills/letsping && cd ~/.openclaw/workspace/skills/letsping && npm install.\r \r Set LETSPING_API_KEY (your LetsPing agent key, e.g. lp_live_...) in the skill's env. Obtain it at https://letsping.co/openclaw/pair or via LetsPing's Agent Credentials API. Treat this key as highly sensitive; use a dedicated agent key and revoke if compromised.\r \r

Usage\r

\r This skill provides the letsping_ask tool, a secure escalation point for high risk actions. The agent calls it, blocks until your approval/patch/reject via the LetsPing PWA, then resumes with the authorized payload only.\r \r Critical: Use frontier models (e.g., Claude Opus, GPT-4o or better) to minimize prompt bypass risk. Smaller models are vulnerable to drift/injection.\r \r Copy-paste this into your workspace TOOLS.md or AGENTS.md (or append to system prompt):\r \r

You have full autonomous authority for **SAFE** actions only: reading files/logs, web searches, viewing/analyzing data without side effects.\r
\r
You **MUST** call `letsping_ask` **BEFORE** any **HIGH-RISK** action—and **NEVER** execute the action directly. High-risk includes:\r
- Financial: Any spending, transactions, bookings > $10\r
- Destructive: Deleting/overwriting files, DB rows, configs\r
- Social: Posting publicly, sending DMs/emails to new contacts, or group chats\r
- Infrastructure: Modifying DNS, env vars, deployments, infra APIs, or permissions\r
\r
When escalating:\r
- Provide tool_name (exact tool, e.g., "system_run")\r
- args_json: Stringified JSON of the original arguments\r
- risk_reason: Clear, concise justification (e.g., "Potential file deletion")\r
\r
After the call returns:\r
- If APPROVED: Use **ONLY** the `executed_payload` / authorized payload (patched if edited)\r
- If REJECTED or TIMEOUT: Abort the action, retry with safer plan, or ask user for guidance\r
\r
Few-shot examples:\r
1. Safe (no call): browser_search(query: "current weather in NYC")\r
2. Risky deploy: letsping_ask(tool_name: "vercel_deploy", args_json: "{\"project\":\"my-app\",\"env\":\"production\",\"force\":true}", risk_reason: "Production deployment with force flag")\r
3. Risky delete: letsping_ask(tool_name: "system_run", args_json: "{\"cmd\":\"rm -rf /important/folder\"}", risk_reason: "Destructive file deletion")\r
4. Risky post: letsping_ask(tool_name: "discord_send", args_json: "{\"channel\":\"general\",\"message\":\"Accidental dump: ls ~\"}", risk_reason: "Potential data leak in public channel")\r
```\r
\r
**Test thoroughly in a sandbox session first**: simulate high risk plans and verify escalation rate (~90-95% reliable on strong models/prompts). If the agent skips calls, add more examples or tighten language.\r
\r
**Troubleshooting:**\r
\r
* **Agent ignores rule?** Strengthen with more few-shots or "ALWAYS escalate if any risk category matches."\r
* **Timeout/reject?** Agent prompt should handle gracefully (e.g., "If rejected, propose alternative").\r