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 oh-my-agent
Runs an autonomous phased execution loop that iterates through planning, execution, verification, and fixing until acceptance criteria are met or blocked. Updates workflow state files.
How this command is triggered — by the user, by Claude, or both
Slash command
/oh-my-agent:autopilotThe summary Claude sees in its command listing — used to decide when to auto-load this command
运行 oma `autopilot` 模式。 目标： $ARGUMENTS 自动执行协议： 1. 从 `team-plan` 和 `team-prd` 开始。 2. 执行 `team-exec -> team-verify -> team-fix` 的迭代循环。 3. 在每个循环后，评估完成标准和阻塞状态。 4. 当所有验收标准通过、被阻塞或达到最大循环次数时停止。 5. 最大循环次数：从 `.oma/state/config.json` 读取（`loopLimits.autopilot` 或 `loopLimits.default`），如果未配置则回退到 5。 状态处理： - 如果文件系统工具可用，更新 `.oma/state/workflow.md` 和 `.oma/state/checkpoint.md`。 - 在状态摘要中包含模式和循环计数。 输出格式： ## 模式 - autopilot - 最大循环次数： ## 循环板 | 循环 | 阶段结果 | 剩余待办 | 阻塞 | | --- | --- | --- | --- | ## 完成状态 - 完成标准： - 状态： ## 后续操作 - ...
运行 oma autopilot 模式。
目标： $ARGUMENTS
自动执行协议：
team-plan 和 team-prd 开始。team-exec -> team-verify -> team-fix 的迭代循环。.oma/state/config.json 读取（loopLimits.autopilot 或 loopLimits.default），如果未配置则回退到 5。状态处理：
.oma/state/workflow.md 和 .oma/state/checkpoint.md。输出格式：
| 循环 | 阶段结果 | 剩余待办 | 阻塞 |
|---|
npx claudepluginhub sswym/oh-my-agent --plugin oh-my-agent/fire-autonomousAutonomously plans, executes, and verifies all build phases after PRD is complete, advancing through the pipeline without human checkpoints.
/autopilotExecutes autonomous phase loop: chains planning, execution, verification, review of code changes; pauses at human decisions; offers PR after final review.
/iterateRuns autonomous iteration loop: reads memory-bank/progress.md, selects next task via full/lite mode, executes with PM/Lead/Designer/Dev/QA roles or Dev/Verify/Commit, verifies, commits, updates progress, loops immediately to next.
/autonomousExecutes all remaining milestone phases autonomously, updating state, roadmap, and phase artifacts. Supports flags for phase range, single-phase, interactive mode, and convergence review.
/autoActivates autonomous PLAN-ACT-EVAL iteration cycle using TDD workflow until zero critical/high issues achieved, then outputs success summary or suggestions.
/batch-execution-playbookExecutes a batch execution playbook for development tasks: loads plan, creates tasks, identifies batches, runs parallel or serial execution with agent teams, and reports progress between batches.