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

runtime/ground-truth.sh

View on GitHub
#!/usr/bin/env bash
# ground-truth.sh — emit bounded live interface facts about this agy install.
#
# WHY THIS EXISTS (the core finding of the 2026-08-01 research):
# When agy was asked to research its own CLI, it confidently invented `agy run`,
# `--headless`, `--slim`, `--no-prompt`, `--workspace` and an `agy auth status --json`
# OAuth introspection endpoint. None exist. The Codex agents that shelled out to
# `agy --help` got it right. Conclusion: a model's memory of its own tooling is
# unreliable, so any agent AUTHORING agy skills must read this output first and
# treat it — not its own recollection — as ground truth.
#
# The default interface phase is deliberately safe to run before a provider or
# account review: it invokes only `agy --version` and `agy --help`. The optional
# account phase is a separate explicit action because `models`, `agents`, plugin
# discovery, and the local settings file may inspect account-owned state.
#
# Feed only the phase you intentionally ran into a skill-authoring prompt.
set -euo pipefail

phase="interface"
case "$#" in
    0) ;;
    1)
        if [[ "${1:-}" == "--account" ]]; then
            phase="account"
        else
            printf '%s\n' 'usage: ground-truth.sh [--account]' >&2
            exit 64
        fi
        ;;
    *)
        printf '%s\n' 'usage: ground-truth.sh [--account]' >&2
        exit 64
        ;;
esac

echo "# agy ground truth — generated $(date -u +%Y-%m-%dT%H:%M:%SZ)"
echo
echo "## phase"
printf '%s\n' "$phase"
echo
echo "## bounded installed interface"
RUNTIME_DIR="$(CDPATH= cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)"
python3 -B "$RUNTIME_DIR/scripts/model_selection.py" --probe-interface

if [[ "$phase" == "account" ]]; then
    echo
    echo "## models available to --model (account phase)"
    agy models 2>&1 || echo "(agy models failed)"
    echo
    echo "## agents available to --agent (account phase)"
    agy agents 2>&1 || echo "(agy agents failed)"
    echo
    echo "## installed plugins (account phase)"
    agy plugin list 2>&1 || echo "(agy plugin list failed)"
    echo
    echo "## headless permission allowlist (account phase)"
    echo "Commands NOT in this list are auto-denied under 'agy -p' with no prompt."
    python3 - <<'PY' 2>&1 || echo "(could not read settings.json)"
import json, os
p = os.path.expanduser("~/.gemini/antigravity-cli/settings.json")
d = json.load(open(p))
perms = d.get("permissions", {})
for key in ("allow", "ask", "deny"):
    print(f"{key}: {perms.get(key)}")
PY
fi
echo
cat <<'EOF'
## interpretation limits

Required capabilities establish the local interface, not authentication, model
availability, permission, or task quality. Version text is diagnostic only.
The schema-validated answer is result.structured_output; result.json_schema is the
echoed schema. Exit zero alone is not success. Do not retry authentication,
permission, quota, or environment blockers automatically.
EOF
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 CodeCodexVerifiedInstall
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: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated 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: 323kUpdated Claude CodeCodexVerifiedInstall