菜单
Check the status of running swarm agents and bead progress.
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-status |
| description | Check the status of running swarm agents and bead progress. |
Check swarm status.
Run br list --json via Bash. Display a status table:
ID | Title | Status | Updated
Highlight any beads in_progress.
Call fetch_inbox via agent-mail MCP tool. Display messages from running agents (sender, subject, time).
Flag beads that appear stuck: updated_at older than 30 minutes and still in_progress.
Show todo list status via TodoRead.
Recommend next action:
/agent-flywheel:flywheel-swarm-stop and restarting.in_progress rows tied to the active swarm AND completion messages received) → do not end here. Read skills/start/_review.md end-to-end and execute its Step 8 wave-completion review prompt: run §8.0a risky-bead detection, surface the consolidated AskUserQuestion with Looks good / Self review / Fresh-eyes (plus Duel review for risky beads), then route through flywheel_review. The swarm itself is not the terminal step — review/wrap-up still owes the user a turn.ScheduleWakeup per _implement.md cadence).