agy-worker

agy-worker is a skill for Codex from cagdasyurekli/codex-agy-worker. It costs 54 tokens per session (2,423 once invoked), scanned A, original, MIT.

A skill that lets Codex use Google's Antigravity command-line tool to explore a repository and carry out bounded implementation work. The worker can investigate, build, or repair code while Codex reviews the changes and verifies the result.

In plain words
What is it for?
Use it for repository exploration, feature implementation, or repairs when an external coding worker is appropriate and you have approved sending the relevant worktree content to Google/Gemini.
Why use it?
It can delegate repository-scale work while keeping review, testing, and delivery decisions with Codex.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Good fit Use it for repository exploration, feature implementation, or repairs when an external coding worker is appropriate and you have approved sending the relevant worktree content to Google/Gemini.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cagdasyurekli/codex-agy-worker/agy-worker
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 cagdasyurekli/codex-agy-worker --skill agy-worker
Clone the repo
git clone --depth 1 https://github.com/cagdasyurekli/codex-agy-worker

Made for: 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.

agentmods badge for agy-worker

README.md
[![agentmods](https://agentmods.dev/badge/skills/cagdasyurekli/codex-agy-worker/agy-worker.svg)](https://agentmods.dev/skills/cagdasyurekli/codex-agy-worker/agy-worker)
Your own site
<a href="https://agentmods.dev/skills/cagdasyurekli/codex-agy-worker/agy-worker"><img src="https://agentmods.dev/badge/skills/cagdasyurekli/codex-agy-worker/agy-worker.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,423 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.02423
Opus 5 $0.00027 $0.01211
Sonnet 5 $0.00011 $0.00485
Haiku 4.5 $0.00005 $0.00242

Measured yesterday against content hash 2454a73046ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 yesterday.

The scan reads SKILL.md. This mod also ships 14 executable files (runtime/agy-worker.sh, runtime/benchmark.sh, runtime/codex-usage-report.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegate repository work and verify the result

Use this skill for useful repository exploration, bounded implementation, or broad project work through agy. The worker discovers ordinary structure and proposes or makes changes; Codex remains responsible for scope, diff review, driver-owned checks, repair decisions, and the final assurance label.

Resolve the installed package instead of guessing a checkout path:

PIPELINE="$(bash "$SKILL_ROOT/scripts/resolve-pipeline.sh")" || exit $?

Optionally check offline prerequisites before spending provider quota:

"$PIPELINE/doctor.sh" --repo /absolute/path/to/target

ready covers offline prerequisites only. It does not prove authentication, provider availability, task quality, or future job success. For installation and package orientation, read Package README.

Before every provider launch

Obtain explicit approval for the exact transmission mode, repository content, and task being sent unless that exact provider transmission was already approved.

For an ordinary job, prepare one concrete approval package covering foreseeable provider work, readable/writable scope, derived repair feedback, model, and budgets. Reuse that authority while it remains applicable. Fresh state hashes and internal candidate checks are mechanical bindings, not requests for another human approval. Ask again only for a material change in authority, content exposure, destination, or budget. Minimize approvals without treating exactly one approval as a hard requirement. Prepare manifests and private paths for the user; ordinary jobs require neither hand-authored JSON nor a Goal.

Prefer --provider-scope FILE --approve-transmission-sha SHA256 for bounded jobs. It binds exact reviewed read entries, their selected-content digest, and a write subset, then stages only selected entries in a fresh owner-private mode-0700 Gitless provider cwd. Whole-worktree dispatch remains an explicit exception. Treat the entire disposable worktree passed as --workdir as worker-readable and potentially transmissible to Google/Gemini, regardless of requested edit paths; --add-dir, prompt denylist instructions, qa-gate --only, and --allow do not narrow that read boundary. Neither workflow.sh run nor the advanced agy-worker.sh initial dispatch has an implicit transmission mode: launch requires either --approve-whole-worktree LAUNCH_APPROVAL_SHA256 or the scoped pair above. The deprecated facade-only --approve-preview-sha spelling cannot launch by itself and remains temporarily available only with --legacy-preview-approval. New jobs default to --provider-isolation session, which uses the existing AGY session without AGY sandbox or native host containment. AGY has normal user filesystem/network authority; selected-file staging and reconciliation are not host isolation. Include this execution mode in the initial approval alongside task/content, then reuse that approval while its scope remains unchanged. Explicit --provider-isolation native retains supported macOS scoped containment with private HOME/TMP and reviewed network/Keychain access; it never falls back to session mode. The native /usr/bin/security exception allows broader same-user Keychain operations, and its listener rule permits wildcard binds. Read Security and compatibility for those limits. Preserve the job's selected mode across continuation and repair. Provider-scope approval grants neither provider execution, Git action, driver acceptance, nor publication. Before each launch, ensure secrets, credentials, private keys, user-denied paths, and unrelated private files are absent from every entry approved for provider transmission; telling the worker not to read an approved entry is not a control.

Read the full file on GitHub · 173 lines

Files

What ships with it

60 files 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.

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.

  1. yesterday Changed · -250 lines scan C → A 2454a73046ae
  2. 7d ago First seen · 423 lines · 54 tokens per session scan C 36254bec4593

Subscribe to this mod's changes

agy-worker is a skill published in the GitHub repository cagdasyurekli/codex-agy-worker (2 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 2,423 once invoked, about $0.0003 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

gemini-prompting

Internal guidance for composing Gemini and AGY prompts for coding, review, diagnosis, and research tasks inside the Gemini Claude Code plugin.

arcobaleno64/agy-plugin-cc · 31 tokens

agy-delegate

Use when doing web searches, looking up current or latest info, researching online, or delegating analysis/review tasks to agy (Google Antigravity CLI). Prefer the WebSearch tool for general web search; use agy for grounded source-cited, current, or second-opinion queries. Triggers on: agy, antigravity, search for…

davdittrich/delegate-agy · 0 tokens

gemini-3-prompting

How to write effective prompts when delegating to or reviewing with agy (Gemini via the Antigravity CLI). Use when constructing an agy-bridge prompt for --type search/code/analysis/review/implement, when a delegated result comes back off-target, or when writing an adversarial review brief for Gemini. Triggers on…

davdittrich/delegate-agy · 0 tokens

gemini-result-handling

Internal guidance for presenting Gemini helper output back to the user.

arcobaleno64/agy-plugin-cc · 17 tokens

git-workflow

This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…

Galaxy-Dawn/claude-scholar · 64 tokens

daily-paper-generator

Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.

Galaxy-Dawn/claude-scholar · 47 tokens