openclaw-agent-architect
by ghively
Design, build, tweak, and audit OpenClaw (Molty / Clawdbot) agents end-to-end — SOUL.md, AGENTS.md, workspace bootstrap, memory, skills, plugins, tool policy, multi-agent routing, sandbox and exec approvals, heartbeats, standing orders, and security audits of community skills or plugins from ClawHub or npm. Trigger on any OpenClaw-related work, on edits to persona / operating-instruction / SOUL / AGENTS / MEMORY / HEARTBEAT files, on SKILL.md authoring, on audits of third-party skills or plugins, and whenever a user is building or debugging a self-hosted chat-based AI agent on WhatsApp / Telegram / Discord / Slack. Do not answer from training memory — this system evolves rapidly with non-obvious precedence rules.