From oh-my-agent
Runs autonomous multi-stage execution loops (team-plan, exec-verify-fix cycles) for complex tasks until acceptance criteria pass, blocker hit, or max loops. Tracks progress via checkpoints.
How this skill is triggered — by the user, by Claude, or both
Slash command
/oh-my-agent:autopilotThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
使用此技能在复杂任务上保持动力,而无需每轮手动提示阶段。
使用此技能在复杂任务上保持动力,而无需每轮手动提示阶段。
team-plan 和 team-prd 开始。team-exec -> team-verify -> team-fix。.oma/state/config.json 读取(loopLimits.autopilot 或 loopLimits.default),如果未配置则回退到 5。$cancel 或 /oma:stop 进行优雅停止。## 模式
- autopilot
## 循环板
| 循环 | 结果 | 剩余待办 | 阻塞 |
| --- | --- | --- | --- |
## 完成
- ...
## 后续操作
- ...
npx claudepluginhub sswym/oh-my-agent --plugin oh-my-agentOrchestrates multi-phase project execution by dispatching isolated persona agents for planning, execution, verification, integration, and review.
Executes the next TaskMaster task using the implementation plan with CDD verification. Dispatches a subagent to implement, verifies subtasks with evidence, and loops until all tasks are complete.
Executes implementation plans with progress tracking, checkpoint validation, and quality gates. Use after planning is complete and tasks are ready to implement.