agy-delegate

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Antigravity Delegate

Antigravity 任务委托

You are the orchestrator. This skill lets you hand a bounded coding task to a separate implementer - the Google Antigravity CLI (

agy

) - then review what it produced and land it yourself. You write the brief and own the judgment; Antigravity does the typing in its own conversation; you verify and commit.

Nothing here is specific to one orchestrating agent. The loop needs only the ability to run a shell command and read a file, so any comparable agent can drive it. It is designed for and run on Claude Code; treat other orchestrators as designed-for, not yet proven.

你是协调者。此技能允许你将一个明确范围的编码任务交给独立的实现工具——Google Antigravity CLI（

agy

），然后审核其产出内容并自行完成提交。你撰写任务简报并负责判断；Antigravity在独立会话中完成代码编写；你进行验证并提交。

此处内容并不针对特定的协调Agent。该流程仅需具备执行shell命令和读取文件的能力，因此任何类似的Agent都可驱动它。它专为Claude Code设计并运行；其他协调工具虽适配设计，但尚未经过验证。

When NOT to use this

请勿使用此技能的场景

The task is small enough to just do inline - delegation overhead is not worth it.
The
```
agy
```
CLI is not installed or not authenticated. Install it from Antigravity's CLI docs and run the first-launch setup.
You want to write the code yourself, or you only need a review without edits. This relay does not expose a proven CLI-enforced read-only mode yet.

任务足够小，可以直接完成——委托的开销得不偿失。
未安装
```
agy
```
CLI或未完成身份验证。请从Antigravity的CLI文档安装它并完成首次启动设置。
你希望自行编写代码，或仅需审核而无需修改。此中继机制目前尚未提供经验证的CLI强制只读模式。

Prerequisites (check once)

前置条件（检查一次）

```
agy help
```
succeeds. If not, install the Antigravity CLI and complete first-launch setup.
```
agy models
```
succeeds. That proves the CLI can authenticate and list the available model labels.
You are in (or will point
```
--cd
```
at) the target git repository.

```
agy help
```
执行成功。若失败，请安装Antigravity CLI并完成首次启动设置。
```
agy models
```
执行成功。这证明CLI可完成身份验证并列出可用的模型标签。
你处于（或将
```
--cd
```
指向）目标git仓库。

Choose the implementer model

选择实现工具模型

agy

has a configured default model, so

--model

is optional. Use it when the human has a preferred Antigravity model label for the task. Otherwise let Antigravity use its own current default rather than guessing.

agy

有一个配置好的默认模型，因此

--model

参数为可选。当用户针对任务有偏好的Antigravity模型标签时使用该参数。否则，让Antigravity使用其当前默认模型，而非自行猜测。

The loop

执行流程

Run these five steps per task. Steps 1, 4, and 5 are your judgment; 2 and 3 are mechanical.

每个任务执行以下五个步骤。步骤1、4和5需要你的判断；步骤2和3为机械操作。

1. Write the brief

1. 撰写任务简报

Antigravity sees only the text you send plus what it can inspect in the workspace - no chat history, no shared context. Everything the task needs goes in the brief: the goal, the current state, what to change, what to leave untouched, the project's actual gate commands, and a report contract. Tell Antigravity it will not commit (you will). Keep one task per brief. Full guidance and a template: references/writing-the-brief.md.

Antigravity只能看到你发送的文本以及它可在工作区中检查的内容——无聊天历史，无共享上下文。任务所需的所有信息都需包含在简报中：目标、当前状态、需修改的内容、需保留的内容、项目的实际校验命令，以及报告约定。告知Antigravity它不会提交代码（由你完成）。每份简报对应一个任务。完整指南和模板：references/writing-the-brief.md。

2. Dispatch

2. 分发任务

Send the brief to Antigravity with the bundled helper. It wraps

agy --print

, captures the run, and writes a structured

result.json

- so your only job is "run a command, read a file." (

<skill-dir>

below is this skill's installed directory - the folder containing this

SKILL.md

bash

node "<skill-dir>/scripts/relay.mjs" --brief brief.txt --cd /path/to/repo

使用捆绑的辅助工具将简报发送给Antigravity。它封装了

agy --print

命令，捕获运行过程，并写入结构化的

result.json

文件——因此你的工作仅为“执行命令，读取文件”。（下方的

<skill-dir>

是此技能的安装目录——包含本

SKILL.md

文件的文件夹。）

bash

node "<skill-dir>/scripts/relay.mjs" --brief brief.txt --cd /path/to/repo

choose a model label: add --model "<label from agy models>"

选择模型标签：添加 --model "<label from agy models>"

enable Antigravity terminal sandbox: add --sandbox

启用Antigravity终端沙箱：添加 --sandbox

resume the most recent conversation: add --resume-last (delta brief only)

恢复最近一次对话：添加 --resume-last （仅需增量简报）

see all options: node .../relay.mjs --help

查看所有选项： node .../relay.mjs --help


The helper starts a fresh Antigravity project by default and passes `--add-dir <repo>` (the `--cd`
path, absolute) so `agy` has an explicit workspace. It does **not** pass `--dangerously-skip-permissions` by default.
Mechanics, flags, and the `result.json` shape: [references/dispatch-and-poll.md](references/dispatch-and-poll.md).


默认情况下，辅助工具会启动一个全新的Antigravity项目，并传递`--add-dir <repo>`（`--cd`指定的绝对路径），以便`agy`拥有明确的工作区。默认情况下**不会**传递`--dangerously-skip-permissions`参数。详细机制、标志和`result.json`结构：[references/dispatch-and-poll.md](references/dispatch-and-poll.md)。

3. Wait for completion

3. 等待完成

The helper blocks until Antigravity finishes, so back it with whatever your orchestrator offers and resume when it returns:

Claude Code: run the Bash call with
```
run_in_background: true
```
; you are notified on completion.
Plain shell / other agents: run it in the foreground for short tasks, or background it and poll the result file.

Do not trust progress trackers over reality: a run is finished when

result.json

is written and the process has exited. Read the working tree, not a status line.

辅助工具会阻塞直到Antigravity完成任务，因此请利用你的协调工具提供的后台运行能力，在任务完成后恢复操作：

Claude Code： 使用
```
run_in_background: true
```
执行Bash调用；完成后会收到通知。
普通shell / 其他Agent： 短任务可在前台运行，长任务可后台运行并轮询结果文件。

不要过度依赖进度追踪器：只有当

result.json

文件已写入且进程已退出时，任务才算完成。请查看工作树，而非状态行。

4. Review - do not trust the self-report

4. 审核——不要轻信自我报告

Antigravity's

result.json

includes its own final message and any gate claims. Re-verify, don't accept:

Re-run the project's gates yourself (the test/lint/build commands from step 1).
Read the diff against the brief: did Antigravity do what was asked, nothing more and nothing less?
```
touchedFiles
```
in the result is your starting point.
Run the relevant guard skills on the diff if you have them installed.
For schema/migration changes, round-trip them; for removals, grep for dangling references.

Full checklist: references/review-and-land.md.

Antigravity的

result.json

包含其最终消息和任何校验声明。请重新验证，不要直接接受：

自行重新运行项目的校验命令（步骤1中的测试/ lint/构建命令）。
对照简报查看代码差异： Antigravity是否完全按要求执行，不多不少？结果中的
```
touchedFiles
```
是你的检查起点。
如果已安装相关守护技能，请针对差异运行它们。
对于架构/迁移变更，请进行往返验证；对于删除操作，请搜索是否存在悬空引用。

完整检查清单：references/review-and-land.md。

5. Land it

5. 完成提交

The implementer edits the working tree; the orchestrator commits. Only after the gates pass and the diff holds:

Commit the verified work yourself, with a clear message.
If it needs changes, send a delta brief with
```
--resume-last
```
and review again.

实现工具会修改工作树；协调者负责提交。只有在校验通过且差异符合要求后：

自行提交已验证的工作，并附上清晰的提交信息。
如果需要修改，请使用
```
--resume-last
```
参数发送增量简报并再次审核。

Permission model

权限模型

Antigravity owns its own permission policy. The relay does not bypass it by default. Use

--dangerously-skip-permissions

only when the human explicitly accepts that Antigravity may auto-approve tool permission requests. Use

--sandbox

when you want Antigravity's terminal sandbox enabled for the run. Antigravity's own help says

--dangerously-skip-permissions

auto-approves all tool permission requests without prompting, including a request to act outside the sandbox. Do not treat

--sandbox

as an enforced boundary when the flags are combined; treat the run as full access.

Antigravity拥有自己的权限策略。默认情况下，中继机制不会绕过该策略。仅当用户明确同意Antigravity可自动批准工具权限请求时，才使用

--dangerously-skip-permissions

参数。当你希望为运行启用Antigravity终端沙箱时，使用

--sandbox

参数。Antigravity自身的帮助文档说明，

--dangerously-skip-permissions

会自动批准所有工具权限请求而无需提示，包括在沙箱外操作的请求。当这两个标志组合使用时，请勿将

--sandbox

视为强制边界；应将此次运行视为拥有完全访问权限。

Authorization model

授权模型

Delegation is something the human opts into. Once they have ("run this queue", "proceed"), committing verified, gate-passing work is the agreed contract. Two limits on that mandate: surface, don't absorb (report Antigravity's design decisions, defensible-but-unasked turns, and non-blocking nitpicks rather than silently keeping them) and stop for scope changes (if correct completion needs going beyond the brief, ask - don't expand the mandate yourself). The full treatment is in references/review-and-land.md.

委托是用户主动选择的操作。一旦用户确认（“运行此队列”、“继续”），提交已验证且通过校验的工作就是约定的内容。此授权有两个限制：透明化，不隐瞒（报告Antigravity的设计决策、合理但未被要求的变更，以及不影响功能的小问题，而非默默保留）；范围变更时停止（若正确完成任务需要超出简报范围的工作，请询问用户——不要自行扩大授权范围）。完整说明请见references/review-and-land.md。

References

参考资料

references/writing-the-brief.md - how to write a brief Antigravity can execute blind: structure, XML blocks, the report contract, and real gate commands.
references/dispatch-and-poll.md -
```
relay.mjs
```
flags, the
```
result.json
```
contract, backgrounding per orchestrator, and recovery when a run misbehaves.
references/review-and-land.md - the review checklist, the commit boundary, and the rework cycle via
```
--resume-last
```
.
references/multi-task-queues.md - running a sequential queue: carrying constraints forward, progress tracking, and the end-of-run coherence check.

references/writing-the-brief.md - 如何撰写Antigravity可独立执行的简报：结构、XML块、报告约定以及实际校验命令。
references/dispatch-and-poll.md -
```
relay.mjs
```
的标志、
```
result.json
```
的约定、各协调工具的后台运行方式，以及运行异常时的恢复方法。
references/review-and-land.md - 审核检查清单、提交边界，以及通过
```
--resume-last
```
进行返工的流程。
references/multi-task-queues.md - 运行顺序队列：传递约束条件、进度追踪，以及运行结束时的一致性检查。