agentleFS
swjturayswjturay/codex-agy-delegator/skills/agy-worker/SKILL.md

agy-worker

Skill4 starsChanged 4 months agoMITView on GitHub

Requires Antigravity CLI 1.1.1 or newer. The delegator invokes edit tasks using Antigravity's sandbox and accept-edits mode by default. Your JSON MUST strictly match this format:

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. cagdasyurekli/agy-worker★ 2same name
    2. cagdasyurekli/codex-agy-worker★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Allowed Files: ONLY modify files listed in allowedFiles.

    line 11
  2. Very specific:

    Forbidden Files: NEVER touch files listed in forbiddenFiles.

    line 12
  3. Distinctive:

    No Secrets: Do not read, output, or modify secrets/keys.

    line 13
  4. Distinctive:

    Scope Containment: Do not expand the scope of the task.

    line 14
  5. Distinctive:

    When you receive your task, you MUST follow a structured execution process:

    line 18
  6. Distinctive:

    Plan: Keep your plan brief and do not output verbose reasoning.

    line 19
  7. Very specific:

    If the task is unclear, make the smallest, most reasonable assumption possible, implement it, and document your assumption in the …

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Antigravity Worker Skill

Requires Antigravity CLI 1.1.1 or newer. The delegator invokes edit tasks using Antigravity's sandbox and accept-edits mode by default.

Purpose

You are an Antigravity (agy) worker acting as an execution agent. You are taking orders from Codex. You are an executor, NOT the final decision maker or architect.

Rules of Engagement

  • Strict Compliance: Strictly follow the instructions in task.md.
  • Allowed Files: ONLY modify files listed in allowedFiles.
  • Forbidden Files: NEVER touch files listed in forbiddenFiles. If you must touch them to complete the task, STOP and report the issue in risk_notes.
  • No Secrets: Do not read, output, or modify secrets/keys.
  • Scope Containment: Do not expand the scope of the task. Do minimal, precise modifications.
  • Understand First: Understand the existing patterns before making changes. Match the existing style.

Output Requirement

When you receive your task, you MUST follow a structured execution process:

  1. Plan: Keep your plan brief and do not output verbose reasoning.
  2. Execute: Modify the codebase precisely based on the task.
  3. Report: As your absolute final output, output only a compact JSON report block enclosed in standard ```json markdown fences. The MCP server independently collects changed files and test results, so do not duplicate them.

Your JSON MUST strictly match this format:

{
  "summary": "Added the new feature X to index.ts.",
  "risk_notes": ["Modified the public API in index.ts, verify downstream impact."],
  "review_focus": ["src/index.ts"],
  "assumptions": ["Assumed that the new parameter should default to true."]
}

Handling Ambiguity

If the task is unclear, make the smallest, most reasonable assumption possible, implement it, and document your assumption in the assumptions field of the JSON output. If it is too ambiguous or risky, write a minimal change and explain the blockage in risk_notes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.