Skip to content

aiskillstore/marketplace / pending/cagdasyurekli/agy-worker

agy-worker

Unverified

Use when Codex or Claude Code should delegate repository exploration or implementation to Google Antigravity CLI (agy), then review, verify, repair, and deliver the result.

FileKindSize
README.mdmarkdown3.7 KB
SKILL.mdskill md12.5 KB
agents/openai.yamlconfig397 B
references/PROJECT_LIFECYCLE_AND_VERIFICATION.mdmarkdown25.6 KB
references/SECURITY_AND_COMPATIBILITY.mdmarkdown16.9 KB
references/TROUBLESHOOTING.mdmarkdown13.3 KB
runtime/agy-worker.shexecutablescript58.1 KB
runtime/delegation-policy.shexecutablescript293 B
runtime/doctor.shexecutablescript16.5 KB
runtime/evidence-report.shexecutablescript267 B
runtime/ground-truth.shexecutablescript2.9 KB
runtime/job.shexecutablescript266 B
runtime/model-selection.shexecutablescript262 B
runtime/qa-gate.shexecutablescript28.7 KB
runtime/schemas/delegation-policy.schema.jsonconfig2.6 KB
runtime/schemas/evidence-receipt.schema.jsonconfig2.5 KB
runtime/schemas/job-state.schema.jsonconfig3.6 KB
runtime/schemas/model-selection.schema.jsonconfig8.3 KB
runtime/schemas/worker-result.provider.schema.jsonconfig2.1 KB
runtime/schemas/worker-result.schema.jsonconfig3.0 KB
runtime/schemas/workflow-state.schema.jsonconfig3.7 KB
runtime/scripts/agy_dispatch.pyexecutablescript344.5 KB
runtime/scripts/agy_dispatch_containment.pyscript51.4 KB
runtime/scripts/agy_dispatch_verification.pyscript33.9 KB
runtime/scripts/agy_dispatch_worktree.pyscript220.6 KB
runtime/scripts/candidate_state.pyexecutablescript47.4 KB
runtime/scripts/delegation_policy.pyexecutablescript12.8 KB
runtime/scripts/evidence_receipt.pyexecutablescript52.9 KB
runtime/scripts/evidence_report.pyexecutablescript17.7 KB
runtime/scripts/job_lifecycle.pyexecutablescript89.0 KB
runtime/scripts/launch_authority.pyscript27.4 KB
runtime/scripts/model_selection.pyexecutablescript38.8 KB
runtime/scripts/transmission_preview.pyexecutablescript744 B
runtime/scripts/validate-envelope.pyexecutablescript6.5 KB
runtime/scripts/workflow.pyexecutablescript89.2 KB
runtime/verify-job.shexecutablescript261 B
runtime/workflow.shexecutablescript239 B
scripts/resolve-pipeline.shexecutablescript5.9 KB
skill-report.jsonconfig552.7 KB
# agy-worker package

`agy-worker` is an Agent Skill for delegating repository exploration and
implementation to Google Antigravity CLI (`agy`) while keeping acceptance with
the driver. The package includes its complete portable core runtime, so an installed
skill does not need a repository checkout or a network fetch for ordinary workflows.
Maintenance tools require a repository checkout.

Use it when a repository task benefits from delegated discovery or edits and the driver
can independently inspect the candidate and run the relevant project checks. It is
not a general-purpose provider client, a security sandbox, or evidence that worker
output is correct.

## Requirements

- OpenAI Codex CLI or Claude Code
- Bash, Python 3, and Git
- `agy` on `PATH` with provider access for live dispatch
- A branch-backed disposable Git worktree whose complete provider-readable content
  has been reviewed and approved

A provider model slug containing `claude` does not establish driver-host support.

## Start from your driver

After installing the skill, start a new driver session and make the scope and checks
concrete. For example:

> Use the agy-worker skill to add parser error-path tests in this repository. Allow
> edits only under tests, verify with the existing parser test suite, and preserve
> useful partial work if a check fails.

Before a live dispatch, the driver must show the owner the exact task and selected
settings beside the content digest; a later provider notice may use a public-safe
summary. Obtain any missing provider-transmission approval, and ensure secrets,
denied paths, and unrelated private files are absent from the disposable worktree.
Installation alone grants none of those permissions.

Prefer selected-content `--provider-scope` for bounded jobs. Whole-worktree dispatch
remains an explicit content-bound exception, and neither the ordinary facade nor the
advanced raw initial launch has an implicit transmission mode.

## Resolve the bundled runtime

`SKILL_ROOT` is the directory containing `SKILL.md`; Claude Code substitutes
`${CLAUDE_SKILL_DIR}` in skill content. Set it explicitly in each Bash call; do not
read a Claude path variable from the environment. Resolve the runtime
instead of assuming a repository path:

```bash
PIPELINE="$(bash "$SKILL_ROOT/scripts/resolve-pipeline.sh")" || exit $?
"$PIPELINE/doctor.sh" --repo /absolute/path/to/target
```

The resolver accepts a complete plugin, an explicit standalone installation marker,
or this folder with its bundled `runtime/`. It fails closed when required components
are missing. `doctor.sh` is an offline prerequisite check; `ready` does not prove
provider authentication or future job success.

For ordinary work, the driver uses the resolved `workflow.sh` facade to preview the
provider-readable path boundary, run an approved workflow, inspect status, and bind
driver-owned verification before finalization. The lower-level dispatcher, lifecycle,
gate, and receipt commands remain advanced recovery surfaces.

## Package guide

- [Skill router](SKILL.md): when to use the skill, workflow selection, dispatch
  notices, hard stops, and delivery rules.
- [Project lifecycle and verification](references/PROJECT_LIFECYCLE_AND_VERIFICATION.md):
  preview, run/status/finalize, Verification v2, isolated verification copies, and
  bounded repair.
- [Security and compatibility](references/SECURITY_AND_COMPATIBILITY.md): provider
  transmission, environment, verifier, host, and distribution boundaries.
- [Troubleshooting](references/TROUBLESHOOTING.md): actionable preflight, provider,
  lifecycle, candidate, and verification failures.

These package-owned links work in a standalone copy. Repository release notes,
contributor history, and public-site material intentionally remain outside this
runtime guide.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexUnverifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall