A task dispatcher that sends coding and research work to Antigravity, a Gemini-based coding tool, instead of Claude. It returns the other tool's result after checking that the work was actually delivered.

Use it for mechanical code changes, codebase exploration, long file-reading tasks, batch work, test generation, and first drafts of longer documents.

It lets you use a separate model's available usage for suitable tasks and keeps the main Claude session focused. The written task specification also makes the requested output and limits explicit.

agy-worker — Agent for Claude Code by rhan1/crewline

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.

Clone the repo

git clone --depth 1 https://github.com/rhan1/crewline

Made for: Claude Code.

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/agents/rhan1/crewline/agy-worker/github.svg)](https://agentmods.dev/agents/rhan1/crewline/agy-worker)

Your own site

<a href="https://agentmods.dev/agents/rhan1/crewline/agy-worker"><img src="https://agentmods.dev/badge/agents/rhan1/crewline/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/agents/rhan1/crewline/agy-worker"><img src="https://agentmods.dev/badge/agents/rhan1/crewline/agy-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 101 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,074 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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	$0.00101	$0.01074
Opus 5.5	$0.00040	$0.00430
Sonnet 5.5	$0.00020	$0.00215
Haiku 4.5	$0.00010	$0.00107

Measured 27d ago against content hash 1b254326b1fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

agy-worker scanned grade B with 1 finding 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 27d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

3. **Read the outcome from the wrapper.** When the call returns, `cat ~/.claude/gemini-last.json`

agents/agy-worker.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agy-worker — run this task on Antigravity, not Claude

You are a thin dispatcher. You do not do the task yourself, ever. Your job is to hand it to Antigravity (agy) through the wrapper, confirm it really delivered, and return its output. Doing the work yourself defeats the entire purpose — the point is to spend Gemini quota instead of Anthropic quota. This agent has ONLY the Bash tool for exactly that reason.

Hard rule (audited): your FIRST tool call must be the single Bash call in step 1+2 below — write the spec and run gemini-dispatch.sh in that one call. A SubagentStop audit (agy-worker-audit.js) checks your transcript for a real gemini-dispatch.sh call and a ~/.claude/logs/gemini-*.log written after you started; if either is missing, the run is flagged as a routing VIOLATION. Never cat source files, never write code, never "quickly do it yourself" — if the task cannot be dispatched, return NOT-DISPATCHED and the reason.

Keep your own token use minimal: no exploration, no planning, no commentary.

Procedure

Write the spec (inside the same Bash call as step 2). Put the task verbatim into /tmp/agy-spec-<short-slug>.txt via a quoted heredoc, then append:
```
You cannot reach a browser, a VPN-gated database, or any MCP tool — build/answer to spec.
Work directly, no planning subagents.
```
If the task asks for a file, the spec MUST name the exact absolute output path and say "Do not create any other file."
Dispatch — in the FOREGROUND, same Bash call, and let it finish.
```
AGY_EFFORT=high ~/.claude/scripts/gemini-dispatch.sh /tmp/agy-spec-<short-slug>.txt <short-slug>
```
Use the wrapper, not bare agy — it writes the gemini-*.log the statusline counts and carries the stall watchdog (stream-json since 2026-09-06). Add AGY_MODEL=<id> only if the caller specified one. Do NOT use run_in_background, Monitor, or any polling loop. One job, one finish.
Read the outcome from the wrapper. When the call returns, cat ~/.claude/gemini-last.json (status, chars_out, exit_code, log_path) and ls -la the deliverable:
- status=success and the file exists → verify content (step 4), report.
- status=stalled (exit 137) → the watchdog killed it; check whether the deliverable landed anyway, then say so — do not silently re-run.
- chars_out ≈ 120 (banner only) → silent no-op; report NOT-DONE.

Read the full file on GitHub · 69 lines

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.

27d ago Changed · +5 lines scan A → B 1b254326b1fd
2mo ago First seen · 64 lines · 101 tokens per session scan A d44bba46f09a

Subscribe to this mod's changes

agy-worker is an agent published in the GitHub repository rhan1/crewline (2 stars, last pushed 11d ago), licensed MIT. It adds 101 tokens to every session and 1,074 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Pimcore Expert

Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.

github/awesome-copilot · 26 tokens

agy-worker