Agent skill

Agy Worker

by aiskillstore in aiskillstore/marketplace

A skill your agent uses when Codex should delegate repository exploration or implementation to Google Antigravity CLI (agy), then review, verify, repair, and deliver the result.

MITAuto-check passed

Install Agy Worker

skills CLI
$ npx skills add aiskillstore/marketplace --skill agy-worker -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aiskillstore/marketplace agy-worker --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aiskillstore/marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cagdasyurekli/agy-worker .claude/skills/agy-worker && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agy-worker
GitHub stars
430
Token cost
~2.5k tokens
SKILL.md length
1,171 words
Files
100 (incl. scripts, references)
Skills in repo
1,044
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when Codex should delegate repository exploration or implementation to Google Antigravity CLI (agy), then review, verify, repair, and deliver the result.

  • Codex should delegate repository exploration
  • SKILL.md covers Authorize provider work, Choose and run the workflow and Hard stops and delivery
  • Runs Shell scripts from its folder; calls bash
  • Implementation to Google Antigravity CLI (agy)

What it does

Agy Worker is an agent skill from aiskillstore/marketplace. Use when Codex should delegate repository exploration or implementation to Google Antigravity CLI (agy), then review, verify, repair, and deliver the result.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 106 other files, including scripts and reference files (for example `README.md`, `agents/openai.yaml` and `references/PROJECT_LIFECYCLE_AND_VERIFICATION.md`). Compatibility notes: Requires OpenAI Codex CLI, Bash, Python 3, git, and agy with provider network access. Claude and Claude Code hosts are not supported.

The repository describes itself as: Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified. The licence is MIT.

When your agent uses it

  • Codex should delegate repository exploration
  • Implementation to Google Antigravity CLI (agy)
  • Deliver the result

Example prompts

  • “/agy-worker”

Requirements

  • Python 3
  • A Bash shell
  • Compatibility (from SKILL.md): Requires OpenAI Codex CLI, Bash, Python 3, git, and agy with provider network access. Claude and Claude Code hosts are not supported.

What it can do on your machine

Read from SKILL.md and the folder at commit 755bc35. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • bash

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires OpenAI Codex CLI, Bash, Python 3, git, and agy with provider network access. Claude and Claude Code hosts are not supported.

    From compatibility in the SKILL.md frontmatter.

Context cost

Agy Worker loads about 2.5k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 42 tokens; SKILL.md has 1,171 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~14k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from aiskillstore/marketplace at commit 755bc35, republished under its MIT licence (© aiskillstore). 1,171 words, ~2,463 tokens.

Download SKILL.mdSave it as .claude/skills/agy-worker/SKILL.md (or your agent's skills folder). This skill also uses 99 other files; get the full folder from GitHub.
name
agy-worker
description
Use when Codex should delegate repository exploration or implementation to Google Antigravity CLI (agy), then review, verify, repair, and deliver the result.
compatibility
Requires OpenAI Codex CLI, Bash, Python 3, git, and agy with provider network access. Claude and Claude Code hosts are not supported.
license
MIT
metadata.author
cagdasyurekli
metadata.version
0.22.0

Delegate repository work and verify the result

Use this skill when agy can usefully explore a repository, implement bounded work, or help with broader project changes. In normal use, delegate substantial exploration and implementation to agy before Codex duplicates it. Codex reads only scope and authority necessities, then spot-checks material findings and reviews the actual diff. Codex retains responsibility for scope, diff review, driver-owned checks, repair decisions, and final independent acceptance.

Resolve the installed package instead of guessing a checkout path:

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

"$PIPELINE/doctor.sh" --repo /absolute/path/to/target can check offline prerequisites before provider use. ready does not prove authentication, provider availability, task quality, or future job success. For package orientation, read the Package README.

Authorize provider work

Before a provider launch, obtain explicit human approval for the exact provider-readable content, transmission and isolation mode, task, caller-selected model, and budget. One exact upfront approval may cover predictable same-scope repairs and mechanical digest/state refresh; provider-launch notices are status, not repeated permission requests. Use initial --allow-scoped-repair for approved multi-turn scoped work. Approval is a human decision. Preview, transmission, state, candidate, and dispatch SHA values are mechanical bindings to that decision; refreshing a still-applicable binding is not another approval request. New scope, content exposure, destination, isolation, permissions or budget still require authority. Preserve required current raw-help/semantic version preflight on each launch; add no cache or alternate controller. Ordinary jobs require neither hand-authored JSON nor Goal as a prerequisite (Goal remains an ordinary-use opt-in).

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. New approvals bind content, kinds, permissions, symlink targets, and execution mode; the controller rechecks this binding before provider start. Legacy records keep their original contracts. 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.

Keep raw worker logs and local controller state outside the worktree and out of prompts. Installation does not authorize provider transmission, Git actions, publication, or acceptance.

For the required user-facing provider-launch notice, including defaults, preflight failures, resumes, and continuation, read Project lifecycle and verification. Direct model and effort selection remain caller-owned; recommendations are advisory.

Show full SKILL.md (588 more words)Show less

Choose and run the workflow

User intentWorkflowDefault cycle budgetCodex responsibility
Explore, understand, review, or planexplore2Spot-check material claims and state coverage limits.
Implement a feature, refactor, tests, or bounded repairtask2Inspect the diff and run relevant project checks.
Build a project or perform broad audit-and-fix workproject5Review repo-wide changes and run applicable build, test, and lint checks.

explore and task accept 1..2 cycles; project accepts 1..5. Personas are optional prompt specializations, not capability, approval, routing, verification, or quality gates. The raw --boost profile is an advanced, separately acknowledged one-cycle task path; read Security and compatibility before using it.

For material UX, lifecycle, trust-boundary, security, data-semantics, or other domain plans, use the co-planning policy in Project lifecycle and verification. Purely mechanical changes are exempt.

Explicit delegation-first requires running the delegation-policy.sh evaluator before substantive repository work. The controller records are local: the runtime cannot infer prior work or approval and must never silently authorize direct-Codex fallback after a missing approval, hard stop, preflight failure, provider failure, or exhausted budget. Direct-Codex and second-eye work remain explicit policy choices.

Prefer workflow.sh for run --preview, approved run, read-only status, and verify-finalize. Review the content-free preview, then run with its exact approved whole-worktree or scoped binding. The facade does not choose a model, assurance label, repair, retry, Git action, or external write. Read the lifecycle guide for facade examples, low-level recovery, Verification v2, and required notices.

After a candidate arrives, inspect the actual Git diff; select and run checks yourself in an isolated verification copy, never an envelope's commands_run or tests_run; worker envelopes are not evidence. Reuse driver-owned checks only for identical candidate bytes and relevant environment; after changes rerun affected checks and run the required full suite once the final executable candidate is stable. Bind only sanitized driver findings to the current candidate; then finalize honestly or request a bounded same-conversation repair. Failed product checks return concrete sanitized feedback to the same AGY conversation for bounded repair; do not allow silent direct-Codex fallback after provider failure or exhausted budget. A scoped candidate can receive another provider turn only when initial dispatch included --allow-scoped-repair, which binds the same approved scope, selected model, conversation, and budgets. Preserve useful work when a check fails or the cycle budget ends; restart is an explicit user decision. See Project lifecycle and verification.

Hard stops and delivery

Do not dispatch or continue without exact provider approval; when approved provider-readable content contains secrets, denied paths, or unrelated private files; when writes can escape the disposable worktree, enter .git, or traverse a symlink boundary; with dangerous permission or approval-bypass flags; or when a Git action, publication, installation, account action, or other external write lacks its own authorization.

Unknown architecture, an unknown first test command, lack of a persona, or a failed first check are not hard stops. Existing self-verification is optional advisory feedback when a focused command is known; an unknown first command or architecture does not prohibit useful delegation. Discover what is needed, preserve the candidate, and report evidence limits. Keep final Codex independent acceptance. Before changing agy-facing flags or claims, run "$PIPELINE/ground-truth.sh" and inspect its current agy --help; consume result.structured_output when ordinary agy output is empty. Its default phase is version/help only; --account is a separate explicit action.

Before delivery, review the exact candidate bytes and run relevant driver-owned checks. Report only what those checks establish: verified, partially_verified, rejected, or blocked. Offline checks do not prove provider success, completeness, release state, security, or general correctness. Use Troubleshooting for actionable failures.

© aiskillstore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 99 other files (scripts, references) in skills/cagdasyurekli/agy-worker of aiskillstore/marketplace.

  • SKILL.md
  • README.md
  • agents/openai.yaml
  • references/PROJECT_LIFECYCLE_AND_VERIFICATION.md
  • references/SECURITY_AND_COMPATIBILITY.md
  • references/TROUBLESHOOTING.md
  • runtime/agents/bulk-test-writer.md
  • runtime/agents/diff-reviewer.md
  • runtime/agents/repo-inventory.md
  • runtime/agy-worker.sh
  • runtime/benchmark.sh
  • runtime/benchmarks/v1/manifest.json
  • runtime/benchmarks/v1/portable-source.json
  • runtime/benchmarks/v1/tasks/exact-edit
  • … and 86 more

Open the folder on GitHubat commit 755bc35

Compare with similar skills

Agy Worker next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agy Worker compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agy Worker this skillaiskillstore/marketplace430—~2.5kAutomated safety check: PassMIT
Agy Delegatesickn33/agentic-awesome-skills47k1 repos~2.2kAutomated safety check: PassMIT
Agy DelegateamElnagdy/delegate-skills2.3k—~2.5kAutomated safety check: PassMIT
Explorersupabase/supabase111k—~845Automated safety check: PassApache-2.0
Agy Autosickn33/agentic-awesome-skills47k1 repos~1.9kAutomated safety check: WarnMIT
Delegate Workpaperclipai/paperclip99k—~372Automated safety check: PassMIT

Similar skills

  • Agy Delegate

    sickn33/agentic-awesome-skills

    Delegate coding tasks to the Google Antigravity CLI (agy) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

    47k GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed
  • Agy Delegate

    amElnagdy/delegate-skills

    Delegate a coding task to the Google Antigravity CLI (agy) as a background implementer, then review its diff and land it yourself.

    2.3k GitHub stars~2.5k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Explorer

    supabase/supabase

    Official

    Build and modify Studio Explorer surfaces, including notebooks, chats, SQL snippets, query cells, and their shared toolbar patterns.

    111k GitHub stars~845 tokensUpdated today
    DatabasesAuto-check passed
  • Agy Auto

    sickn33/agentic-awesome-skills

    Configure agy-auto PreToolUse security gate to run Antigravity CLI (agy) unattended with layered policy controls instead of --dangerously-skip-permissions.

    47k GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check: warnings
  • Delegate Work

    paperclipai/paperclip

    Delegate user-requested work to an existing Paperclip agent, with a durable task reference and clear execution expectations.

    99k GitHub stars~372 tokensUpdated today
    Auto-check passed
  • Worker Visualizer

    nexu-io/open-design

    A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas…

    100k GitHub stars~998 tokensUpdated today
    Auto-check passed

More from aiskillstore/marketplace

All 1,044 skills in this repo
  • Code Stats

    aiskillstore/marketplace

    Analyze codebase with tokei (fast line counts by language) and difft (semantic AST-aware diffs).

    430 GitHub starsUsed in 1 repo~697 tokens
    Auto-check: notes
  • Data Processing

    aiskillstore/marketplace

    Process JSON with jq and YAML/TOML with yq. An agent skill from aiskillstore/marketplace.

    430 GitHub starsUsed in 1 repo~720 tokens
    Auto-check: notes
  • Doc Scanner

    aiskillstore/marketplace

    Scans for project documentation files (AGENTS.md, CLAUDE.md, GEMINI.md, COPILOT.md, CURSOR.md, WARP.md, and 15+ other formats) and synthesizes guidance.

    430 GitHub starsUsed in 1 repo~644 tokens
    Auto-check: notes
  • File Search

    aiskillstore/marketplace

    Modern file and content search using fd, ripgrep (rg), and fzf.

    430 GitHub starsUsed in 1 repo~598 tokens
    Auto-check: notes
  • Find Replace

    aiskillstore/marketplace

    Modern find-and-replace using sd (simpler than sed) and batch replacement patterns.

    430 GitHub starsUsed in 1 repo~527 tokens
    Auto-check: notes
  • Project Planner

    aiskillstore/marketplace

    Detects stale project plans and suggests session commands. An agent skill from aiskillstore/marketplace.

    430 GitHub starsUsed in 1 repo~504 tokens
    Auto-check passed

Questions about Agy Worker

What does Agy Worker do?

A skill your agent uses when Codex should delegate repository exploration or implementation to Google Antigravity CLI (agy), then review, verify, repair, and deliver the result. Agy Worker is an agent skill from aiskillstore/marketplace. Use when Codex should delegate repository exploration or implementation to Google Antigravity CLI (agy), then review, verify, repair, and deliver the result.

When should I use Agy Worker?

Agy Worker fits situations like: Codex should delegate repository exploration; implementation to Google Antigravity CLI (agy); deliver the result.

How do I install Agy Worker in Claude Code?

Run `npx skills add aiskillstore/marketplace --skill agy-worker -a claude-code`. Or copy the skill folder (skills/cagdasyurekli/agy-worker in aiskillstore/marketplace) into .claude/skills/agy-worker in your project. Claude Code loads it when a task matches its description.

How do I install Agy Worker in Codex?

Run `npx skills add aiskillstore/marketplace --skill agy-worker -a codex`. Or copy the skill folder (skills/cagdasyurekli/agy-worker in aiskillstore/marketplace) into .agents/skills/agy-worker in your project. Codex loads it when a task matches its description.

Can I use Agy Worker in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aiskillstore/marketplace --skill agy-worker -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agy-worker, .gemini/skills/agy-worker, .github/skills/agy-worker and .opencode/skills/agy-worker in your project.

What does Agy Worker need to run?

Going by SKILL.md and its folder, Agy Worker needs a shell for the scripts in its folder and the command-line tools its instructions call (bash). Our summary lists: Python 3; A Bash shell. Compatibility (from SKILL.md): Requires OpenAI Codex CLI, Bash, Python 3, git, and agy with provider network access. Claude and Claude Code hosts are not supported..

Does Agy Worker access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agy Worker safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Agy Worker use?

Agy Worker is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agy Worker use?

About 2.5k tokens (SKILL.md is roughly 9.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 11k tokens, read only when the agent opens those files.

What are the alternatives to Agy Worker?

Skills that share tags, products or a category with Agy Worker: Agy Delegate (sickn33/agentic-awesome-skills, 47k stars), Agy Delegate (amElnagdy/delegate-skills, 2.3k stars), Explorer (supabase/supabase, 111k stars) and Agy Auto (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agy Worker?

aiskillstore (a GitHub organization) maintains it in aiskillstore/marketplace, which has 430 GitHub stars. The repository holds 1,044 skills in this directory. The repository was last updated on October 9, 2026.

Source: aiskillstore/marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.