К основному содержанию
скилл Claude Code CX Codex Cursor GitHub Copilot

agy-delegate — скилл для Claude Code: делегировать код Antigravity

Отправьте задачу в Google Antigravity CLI, дождитесь результата и сами решите, коммитить ли. Скилл нужен, если хотите делегировать реализацию, а не писать сами.

Установить в Claude Code · Через Skills CLI (Vercel) Все способы и платформы ↓
npx skills add amElnagdy/delegate-skills --skill agy-delegate -a claude-code
Открыть на GitHub

Что делает agy-delegate

Когда пользователь просит «сделай это через Antigravity», «запусти через agy», «делегируй в Antigravity» — этот скилл берёт задачу, формирует краткий бриф и отправляет его на выполнение через Google Antigravity CLI. Сам Antigravity работает в отдельном диалоге и может редактировать файлы; вы остаётесь рецензентом.

Скилл описывает полный цикл: как написать бриф, чтобы Antigravity понял, что нужно; как запустить команду через helper-скрипт relay.mjs; как проверить результат и пересчитать ворота (тесты, линтер); как коммитить, если всё верно. Требует установленный и аутентифицированный agy CLI, Node.js и git.

Не используйте для задач, которые вы можете решить вхолодную за пару минут, или если нужна консультация Antigravity без правок кода. Требует, чтобы вы сами проверили diff и не полагались на отчёт Antigravity о прохождении ворот.

Какие задачи решает

  • делегировать реализацию большой фичи, пока вы занимаетесь другим
  • запустить очередь задач через Antigravity и остать рецензентом
  • отправить в Antigravity код, который нужно рефакторить или исправить
  • получить diff и проверить его перед тем, как коммитить

Примеры запросов агенту

  • Делегируй эту фичу Antigravity, я потом проверю
  • Запусти эту рефакторку через agy-delegate
  • Отправь исправление в Antigravity и дай мне результат

Как установить agy-delegate

1Через Skills CLI (Vercel)

npx skills add amElnagdy/delegate-skills --skill agy-delegate -a claude-code

2Вручную: положить файлы

~/.claude/skills/agy-delegate/SKILL.md

Папка скилла целиком; для одного проекта — .claude/skills/agy-delegate/

Из того же набора5

Весь набор →

Похожие

huggingface-trackio huggingface Скилл учит агента логировать метрики обучения ML через Trackio, отслеживать расхождения лосса и выгружать результаты через CLI. Пригодится для автономного перезапуска экспериментов. Claude Code CX Codex Cursor +1 1 900установок huggingface-local-models huggingface Находит на Hugging Face GGUF-репозиторий, подбирает квант под вашу память и поднимает модель через llama.cpp — с OpenAI-совместимым эндпоинтом, если нужен сервер. Claude Code CX Codex Cursor +1 1 900установок resolve-conflicts tailcallhq Разбирает Git-конфликты по плану: оценивает файлы, пересобирает lock-файлы, спасает правки из удалённых файлов и спрашивает вас о спорных местах. Claude Code CX Codex Cursor +1 683установок tamarind K-Dense-AI Запускает инструменты структурной биологии и молекулярного дизайна через REST API или MCP-сервер Tamarind Bio. Пригодится для облачных задач без локальных GPU. Claude Code CX Codex Cursor +1 1 100установок session-persist ruvnet Сохраняет состояние агента с снимком памяти, метрик и прогресса, чтобы потом восстановить работу в новой сессии без потери контекста. Claude Code CX Codex Cursor +1 774установок svelte vercel-labs Помогает собирать интерфейсы Svelte 5 из спецификаций json-render и связывать компоненты с состоянием, событиями и действиями. Claude Code CX Codex Cursor +1 1 200установок setup-matt-pocock-skills Matt Pocock Скилл настраивает репозиторий для инженерных скиллов Matt Pocock: задаёт трекер задач, метки триажа и расположение доменной документации. Запустите его перед первым использованием остальных скиллов. Claude Code 1 052 851установок to-tickets Matt Pocock Разбивает план, спецификацию или переписку на небольшие сквозные задачи и отмечает, какие из них блокируют остальные. Пригодится, когда нужно согласовать порядок работы до публикации задач в трекере. Claude Code 711 230установок

Вопросы о agy-delegate

Как установить agy-delegate?

Зависит от платформы. На Claude Code: npx skills add amElnagdy/delegate-skills --skill agy-delegate -a claude-code, потом найдите ~/.claude/skills/agy-delegate/SKILL.md. На Cursor: npx skills add amElnagdy/delegate-skills --skill agy-delegate -a cursor, файл будет в .cursor/skills/agy-delegate/SKILL.md. На GitHub Copilot: gh skill install amElnagdy/delegate-skills agy-delegate.

Когда использовать agy-delegate?

Когда пользователь хочет отдать задачу на реализацию Antigravity: «делегируй в agy», «запусти через Antigravity», «have Antigravity implement». Не используйте, если задача маленькая или нужно писать сам, а не делегировать.

Что нужно перед использованием?

agy CLI должен быть установлен и аутентифицирован. Проверьте: agy help и agy models должны работать. Нужны Node.js и git. Вы должны находиться в целевом репозитории.

Исходный текст

SKILL.md · MIT
---
name: agy-delegate
description: >-
  Delegate a coding task to the Google Antigravity CLI (`agy`) as a background implementer, then review
  its diff and land it yourself. Use this whenever the user wants to hand implementation work to
  Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through
  agy", or "use Antigravity to implement/fix/refactor" - or wants to run a queue of coding tasks
  through agy while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the
  user wants the code written directly without delegating.
license: MIT
compatibility: Requires the `agy` CLI installed and authenticated, Node.js, and git. The orchestrator must be able to run shell commands and read files. Shell examples assume bash/zsh (macOS/Linux, or Git Bash/WSL on Windows).
metadata:
  version: 0.5.0
---

# Antigravity Delegate

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.

## When NOT to use this

- 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 Antigravity's opinion on code you wrote (a
  `--read-only` dispatch covers review without edits, but a plain review may not need delegation at all).

## Prerequisites (check once)

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

These checks do not prove that a headless write will be approved. In `--print` mode, Antigravity
cannot prompt for a write permission and may auto-deny it. The relay detects that denial instead of
reporting completion.

## Choose the implementer model

`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.

## The loop

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

### 1. Write the brief

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](references/writing-the-brief.md).

### 2. Dispatch

For **Codex orchestration of background work**, install and configure the separate
**codex-background** support utility first. If its MCP tools or registry are missing, stop and
report the setup requirement; do not silently fall back to model-driven polling. Then invoke its
registered `delegate_run` MCP tool once in place of the shell example below.
Follow that skill for structured common arguments, unchanged provider flags and reattachment by
runId. Keep the request pending until completion, then continue this skill's review and landing
steps. Other orchestrators keep the shell workflow below.

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
# choose a model label:                 add --model "<label from agy models>"
# reasoning effort (low, medium, high): add --effort high
# read-only (sandbox — no edits):       add --read-only
# enable Antigravity terminal sandbox:  add --sandbox
# resume the most recent conversation:  add --resume-last  (delta brief only)
# see all options:                      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).

### 3. Wait for completion

Codex using codex-background keeps the original MCP request pending: no model-driven sleep,
status or log polling. Use `delegate_wait` only to reattach after an interrupted request.

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. The implementer's full report is
the `finalMessage` field in `result.json` (also printed in full on stdout between the report markers).

### 4. Review - do not trust the self-report

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](references/review-and-land.md).

### 5. Land it

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.

## Permission model

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. `--read-only` composes `--sandbox` with
`--dangerously-skip-permissions`: the sandbox is the enforcement — writes inside the workspace
are overlaid and discarded, and paths outside it fail with EPERM — while the auto-approve only
lets tools run inside it. As a user-facing flag it stays mutually exclusive with
`--dangerously-skip-permissions`, which alone (without the sandbox) is full access. Use
`--sandbox` on its own when you want the terminal sandbox enabled for a write run.
If headless `--print` auto-denies a write, the relay reports `status: "failed"` and exits non-zero.
The relay fingerprints the working tree before and after a `--read-only` run to report
`readOnlyViolation` in `result.json`. Settings allow-rules do apply to headless `--print` runs, but
their matching rules and config location vary by `agy` version and platform, so treat a denial as
something to measure on your install rather than assume. Two traps have been measured. First,
exact-match behavior: on Windows with agy 1.2.5, `command(<name>)` matched only a bare command with
no arguments — `command(git)` never allowed a real `git status`, and `command(regex:git .+)` was
required ([issue #614 comment](https://github.com/google-antigravity/antigravity-cli/issues/614#issuecomment-5466617752)).
On macOS with agy 1.2.0, that same bare `command(git)` rule *did* allow `git status`, so the
exact-match trap is not a constant across versions. Second, on Windows, an open
upstream defect in Antigravity's permission engine
([issue #614](https://github.com/google-antigravity/antigravity-cli/issues/614)) splits resolved paths
on whitespace, so a binary under `C:\Program Files\...` — which is where `git` itself commonly lives,
making this the single most common trigger for delegated coding tasks, not just node/npm — is matched
as its first fragment and no `command(<name>)` rule can match it. On which file agy reads: verified
live on Windows with agy 1.2.5, the effective rules were `userSettings.globalPermissionGrants.allow`
in `~/.gemini/config/config.json`, not the `permissions.allow` in
`~/.gemini/antigravity-cli/settings.json` that agy's own denial message points at; verified live on
macOS with agy 1.2.0, rules in `antigravity-cli/settings.json` took effect. Recheck both on your
version before relying on either file. See
[references/dispatch-and-poll.md](references/dispatch-and-poll.md) for the full writeup. Do not add
the bypass flag without explicit human approval.

## Authorization model

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](references/review-and-land.md).

## References

- [references/writing-the-brief.md](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](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](references/review-and-land.md) - the review checklist, the commit
  boundary, and the rework cycle via `--resume-last`.
- [references/multi-task-queues.md](references/multi-task-queues.md) - running a sequential queue:
  carrying constraints forward, progress tracking, and the end-of-run coherence check.

© amElnagdy · MIT · amElnagdy/delegate-skills

Смотрите также

Спонсоры проекта

Компании, которые помогают держать аналитику открытой