Use when deploying Modal workers, checking Modal logs, managing Modal secrets, or configuring GPU endpoints. Triggers on modal deploy, Modal worker, Modal app, Modal logs, Modal secret, modal run, Modal endpoint, keep_warm, cold start, Modal proxy token, wk- ws- token, 8-endpoint limit, Modal GPU, memory sizing, deploy_all.py, Modal Python worker.
From george-setupnpx claudepluginhub george11642/george-plugins --plugin george-setupThis skill uses the workspace's default tool permissions.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Check project CLAUDE.md for worker paths and deploy entry points.
| Task | Command |
|---|---|
| Deploy app | modal deploy path/to/app.py |
| List apps | modal app list |
| View logs | modal app logs app-name |
| Set secret | modal secret create name KEY=value |
| Run ad-hoc | modal run path/to/script.py |
wk-*/ws-*) differ from CLI tokens (ak-*/as-*) — Convex env vars use proxy tokenskeep_warm=1 for latency-sensitive endpointsapp = modal.App("worker-name")
image = modal.Image.debian_slim().pip_install(...)
@app.function(image=image, memory=512)
@modal.web_endpoint(method="POST")
def endpoint(request: dict):
...