Respond First

Multi-agent dispatcher skill. Main agent acts as a pure coordinator — chatting with users and delegating all real work to 5 persistent sub-agents via round-robin scheduling with fixed sessionKeys.

This skill appears to do what it says (coordinate and delegate). Before installing or using it: 1) Treat the sub-agents as separate recipients — any user content you put into tasks will be forwarded to those sub-agents and may be retained by them. Avoid sending sensitive secrets or private data unless you confirm how session memory is handled. 2) Ask the platform or skill proprietor whether the persistent sessionKeys retain conversation history across tasks and whether you can clear or isolate that memory. 3) Test with non-sensitive inputs to observe behavior (who gets spawned, what the spawn payload looks like in logs). 4) Confirm platform audit/logging and revocation procedures in case you need to stop sub-agents or delete retained data. If you require strict data isolation or must not forward user context to other agents, do not use this skill.

Type: OpenClaw Skill Name: respond-first Version: 11.0.0 The skill is designed as a multi-agent dispatcher, explicitly prohibiting the main agent from using `exec`, file read/write, search, or any execution tools. Its sole function is to delegate tasks to pre-defined sub-agents via `sessions_spawn` with strict parameters. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts against the main agent within the provided `SKILL.md` instructions or other metadata files. The instructions clearly define a constrained, coordinating role for the agent.