菜单
Stop all running swarm agents and release their file reservations.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Relentless goal/design interview that sharpens framing and writes durable docs (brainstorm artifact, ADRs, glossary) as decisions crystallize. Use when refining a flywheel goal, pressure-testing scope, or "grill with docs".
Start or resume the full agentic coding flywheel. Drives the complete workflow: scan → discover → plan → implement → review.
Set up flywheel prerequisites for this project.
One-shot diagnostic of every flywheel dependency — MCP connectivity, Agent Mail liveness, br/bv/ntm/cm binaries, node version, git status, dist-drift, orphaned worktrees, and checkpoint validity. Use when debugging toolchain issues, before starting a new session, after /flywheel-cleanup, or as a CI gate.
Strategic gap analysis between vision (AGENTS.md / README.md / plan docs) and what's actually implemented. Converts gaps into beads, optionally launches a swarm. Use when "reality check", "where are we really", "gap analysis", "did we drift", or before declaring a long-running project done.
Launch a parallel swarm of agents to implement multiple beads simultaneously.
| name | flywheel-swarm-stop |
| description | Stop all running swarm agents and release their file reservations. |
Stop the swarm and clean up.
Fetch all active agents via fetch_inbox on the agent-mail MCP tool to identify who is running.
Call release_file_reservations via agent-mail MCP tool with project_key set to the current working directory to release all reservations.
Send a stop signal to each active agent individually via send_message in agent-mail (do NOT broadcast to "*" — structured messages cannot be broadcast):
send_message(to: "<name>", subject: "STOP — Swarm shutdown requested", body_md: "Please finish your current step, commit any partial work, and exit.", importance: "urgent")SendMessage(to: "<name>", message: {"type": "shutdown_request", "reason": "Swarm stopped by user."})TaskStop(task_id: "<id>") for agents that don't respond (use saved task IDs from when they were spawned).For beads still marked in_progress in br list --json, reset them to open:
Run br update <id> --status open via Bash for each.
Use TaskList to find active swarm tasks, then TaskUpdate each to status: "deleted".
Report: "Swarm stopped. N agents signaled to stop, N beads reset to open."