A worker integration that lets an orchestrating agent delegate coding and shell tasks to Google Antigravity, a separate execution agent. The orchestrator remains responsible for the overall plan while the worker performs concrete tasks.

Use it to send a self-contained task to an installed Antigravity command-line tool, continue an existing worker conversation, or supervise delegated work.

It reduces the amount of file editing, test running, directory exploration, and command execution the main agent must handle itself.

agy-worker — Skill for Claude Code and Codex by 02loveslollipop

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add 02loveslollipop/OpenCROW --skill agy-worker

Clone the repo

git clone --depth 1 https://github.com/02loveslollipop/OpenCROW

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/02loveslollipop/opencrow/agy-worker/github.svg)](https://agentmods.dev/skills/02loveslollipop/opencrow/agy-worker)

Your own site

<a href="https://agentmods.dev/skills/02loveslollipop/opencrow/agy-worker"><img src="https://agentmods.dev/badge/skills/02loveslollipop/opencrow/agy-worker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/02loveslollipop/opencrow/agy-worker"><img src="https://agentmods.dev/badge/skills/02loveslollipop/opencrow/agy-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 699 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00058	$0.00699
Opus 5.5	$0.00023	$0.00280
Sonnet 5.5	$0.00012	$0.00140
Haiku 4.5	$0.00006	$0.00070

Measured 1mo ago against content hash 7ebd219c3019, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agy-worker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/agy-worker/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenCROW Runner - AGY Worker

For asynchronous supervision, durable questions/replies, worktrees, and additional providers, use agent-worker with opencrow-worker-mcp. The tools below retain their synchronous behavior.

Runtime preflight

Probe required commands with command -v before use. The Antigravity CLI (agy) must be installed in PATH. If missing, report that agy is not installed on the host.

Use this skill when you are acting as the primary orchestrator, planner, or strategist, and need to delegate concrete execution subtasks to agy to preserve your attention and context window.

MCP First

Prefer the opencrow-agy-mcp server tools for delegation:

Call toolbox_info, toolbox_verify, and toolbox_capabilities first.
Call agy_execute to dispatch a self-contained task or ticket to agy:
- task: Clear, unambiguous prompt specifying goals, target files, and acceptance criteria.
- workspace: Directory where agy should execute.
- conversation_id: Pass an existing conversation ID to continue an ongoing thread, or leave empty for a fresh thread.
- mode: Default is accept-edits.
Call agy_chat when you need to provide corrective feedback, share test errors, or request follow-up refinements in the same conversation thread.
Call agy_session_status to view active session turns and metadata.
Call agy_session_stop to unregister finished sessions.

Quick Start

Start the MCP server directly or via the OpenCROW launcher:

opencrow-agy-mcp

Or execute an inline task via CLI:

agy --dangerously-skip-permissions --output-format json --print="Create hello.py and run it"

Workflow

Strategic Planning: Break the overall problem down into discrete, testable subtasks. Do not give agy underspecified, multi-objective epics.
Dispatch Subtask: Call agy_execute with target directory and explicit verification criteria (e.g., "Implement function foo in bar.py and ensure pytest tests/test_bar.py passes").
Inspect Output: Review the returned response, tool summary, and git status.
Follow-Up or Correct: If the worker encountered errors or missed an edge case, call agy_chat with the error output and corrective guidance.
Finalize: Unregister the session with agy_session_stop and integrate the completed work into your plan.

Read the full file on GitHub · 60 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/orchestration.md 2.2 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 60 lines · 58 tokens per session scan A 7ebd219c3019

Subscribe to this mod's changes

agy-worker is a skill published in the GitHub repository 02loveslollipop/OpenCROW (10 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 699 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.

Building agents agent-orchestration agent-runtime agentic-ai ai-agents ctf cybersecurity

agy-worker

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

OpenCROW Runner - AGY Worker

Runtime preflight

MCP First

Quick Start

Workflow

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

dd-synthesis

dd-report-format

dd-risk-scoring

dd-sourcing

dd-verification

agentmail