Dispatch independent tasks to parallel workers or subagents without write collisions. Use when: running or planning agents in parallel, even two; check scopes before any launch.
中文简介正在准备中。当前显示原文说明。
Execute one bounded RED to GREEN experiment from bead or caller intent; return derived subject identity and check facts. Triggers: "implement", "implement this bead", "run the experiment". Full plan-to-validation requests route to rpi.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Execute exactly one bounded experiment described by the resolved bead or caller intent. Implement owns subject edits and factual evidence. It does not create a second planning record or a model-authored candidate packet.
subject-manifest.v1 from
the before/after subject. Do not make the model transcribe those facts.Specialists such as standards, domain, test, refactor, and security may provide advice. They are never hard dependencies and cannot add lifecycle authority.
During edits, run the smallest deterministic checks that can falsify the active change. Reuse exact-input receipts when their subject and tool identity still match. Run an expensive full-suite check at the integration boundary, or earlier only when the intent explicitly makes it the first acceptance check. Repeatedly replaying the full suite after every focused edit adds latency, not proof.
On discovering a live consumer of the change outside the declared write scope
— a test asserting the old path, a generated twin, a gate reading the moved
file — stop and report the exact file and line to the caller. Do not silently
expand scope to absorb it. One repair revision of the intent is the maximum
before escalating to the caller; the 2026-07-15 heal-skill fold took three
intent revisions (lineage under .agents/ao/intents/sha256/26a4f2be...eb48)
because hand-enumerated scope kept missing live consumers.
Before declaring GREEN, self-audit the diff for mocks, placeholders, TODO stubs, and hardcoded fixture values standing in for real behavior. A check that passes against a placeholder is not evidence for the acceptance criterion; either finish the behavior or report it as not built.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Dispatch independent tasks to parallel workers or subagents without write collisions. Use when: running or planning agents in parallel, even two; check scopes before any launch.
中文简介正在准备中。当前显示原文说明。
Run a supplied task in headless AGY (Antigravity, Gemini) and collect its result. Use when: AGY, Antigravity or Gemini is requested by name; never a fallback.
中文简介正在准备中。当前显示原文说明。
Compare interface designs and find structural friction. Use when: a change spreads across modules or a boundary is unclear. For code changes, use Refactor.
中文简介正在准备中。当前显示原文说明。
Run one prompt through headless Claude with scoped permissions and a time bound. Use when: scripting or automating a `claude -p` call, even a simple one.
中文简介正在准备中。当前显示原文说明。
Run one prompt through headless Codex and capture the result. Use when: wanting a one-shot `codex exec` run or CI step. Not for batches or retries.
中文简介正在准备中。当前显示原文说明。
Compare independent opinions from several models or contexts without inflating agreement. Use when: wanting a second opinion or debate, or summarizing several reviewers' results.
中文简介正在准备中。当前显示原文说明。