Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From liminal-agents
The parallel per-agent swarm that beats cold-start — each bounded agent reads its canonical source (git/claude-code → Analyst, granola → SDR, cross-stream → Auditor) in parallel and posts a candidate (the one fact, commitment, or risk worth acting on) before any deliberation. Read-only, LLM-optional.
How this command is triggered — by the user, by Claude, or both
Slash command
/liminal-agents:onboard-swarmThe summary Claude sees in its command listing — used to decide when to auto-load this command
Invoke the `onboard-swarm` skill and follow its SKILL.md flow exactly: run the swarm, render the candidates grouped by the bounded agent that posted each (Analyst / SDR / Auditor), then print the close line — honest about cold-start when no source has signal and about fixture mode when no credential is available.
Invoke the onboard-swarm skill and follow its SKILL.md flow exactly: run the swarm, render the candidates grouped by the bounded agent that posted each (Analyst / SDR / Auditor), then print the close line — honest about cold-start when no source has signal and about fixture mode when no credential is available.
npx claudepluginhub maccabicapital/liminal-agents