From oh-my-agent
Runs exec-verify-fix loops until acceptance criteria pass or blockers identified, producing loop status, evidence table, remaining todos, and next command.
npx claudepluginhub sswym/oh-my-agent --plugin oh-my-agent运行 oma `loop` 强制执行。 上下文: $ARGUMENTS 协议: 1. 从前一阶段的输出中读取当前验收标准和开放的待办列表。 2. 构建下一个最小的循环范围。 3. 执行一个严格的循环:`team-exec -> team-verify -> team-fix`(仅在验证失败时修复)。 4. 当存在未解决的阻塞或主要项目时,不要声明完成。 5. 仅在以下情况下停止: - 所有标准通过(完成), - 存在硬阻塞(被阻塞), - 达到最大循环次数(升级)。 6. 最大循环次数:从 `.oma/state/config.json` 读取(`loopLimits.speed` 或 `loopLimits.default`),如果未配置则回退到 3。 7. 如果文件系统工具可用,更新 `.oma/state/workflow.md` 和 `.oma/state/checkpoint.md`。 输出格式: ## 循环状态 - 循环: - 状态:继续 / 完成 / 被阻塞 - 剩余阻塞: ## 循环证据 | 阶段 | 结果 | 证据 | 下一步 | | --- | --- | --- | --- | ## 剩余待办列表 1. ... 2. ... ## 下一个命令 - ...
/loopExecutes tasks in iterative loops with conditions, max iterations (up to 20), stall detection, progress tracking, and metric verification until goals met.
/loopParses natural language task into components (task, max iterations, completion condition) and sets up repeating AI execution loop via bash script.
/loopStarts iterative dev loop on PROMPT with optional --max-iterations N and --completion-promise TEXT. Persists work in files and git history across iterations until complete.
/loopRuns self-sustaining development loop in Researcher (explore/plan/specs) or Implementor (code/tests/docs) mode with git workflow, context options, directions, and iteration count.
/loopBenchmarks and evolves prompt assets like skills and commands in isolated branches using loop suites. Supports list-suites, show-suite, run with targets/budget/parallel/generations, and resume subcommands.
/loopExecutes hotl-workflow-*.md files using loop execution mode with auto-approval via the hotl:loop-execution skill.
运行 oma loop 强制执行。
上下文: $ARGUMENTS
协议:
team-exec -> team-verify -> team-fix(仅在验证失败时修复)。.oma/state/config.json 读取(loopLimits.speed 或 loopLimits.default),如果未配置则回退到 3。.oma/state/workflow.md 和 .oma/state/checkpoint.md。输出格式:
| 阶段 | 结果 | 证据 | 下一步 |
|---|