goal-modelisted

Keep coding agents working until tests, lint, typecheck, or CI are green — instead of stopping after one try or claiming "done" without proof. Autonomous coding-agent loop with a verifiable finish line: GOAL.md contract, phased plan, worker/verifier proof loop, time budget, auto-resume (Cursor Cloud Agent). Open alternative to Claude Code /goal. Use when the user says /goal, "goal mode", "goal mode for Cursor", "keep going until tests pass", "don't stop until green", "coding agent until tests pass", "verify until done", "agent stops after one attempt", "how to make agent not stop until complete", "fix CI", "fix all lint errors", "green build", "unattended refactor", "overnight agent", "resume the goal", or wants multi-hour autonomous execution with verification before completion. Prefer over one-shot chat or Cursor Agent Mode for long refactors, migrations, and CI repair until green. Do not use for one-shot Q&A or vague "make it better" without a measurable finish line.
shenwell/ai-agent-skills · ★ 2 · AI & Automation · score 78

Install: claude install-skill shenwell/ai-agent-skills

# Goal Mode **Keep your coding agent working until the finish line is provably green** — tests, lint, typecheck, or CI — instead of one attempt and a false “done.” Goal Mode is an **autonomous coding agent** pattern: **verify until done** with a **verifiable finish line** and a separate verifier, not self-certification. It is an open alternative to [Claude Code `/goal`](https://code.claude.com/docs/en/goal) for **Cursor**, Claude Code, Codex, and other hosts. You give one objective; the skill runs bootstrap → plan → work ⇄ verify until `COMPLETE`, or stops honestly as `BLOCKED` / `FAILED`. Most agent sessions fail the same way: you ask to fix lint or make CI green, the agent tries once, declares victory, and leaves you with a red build. Goal Mode replaces that loop with a **durable GOAL.md contract** — acceptance criteria, evidence commands, time budget, and phased plans — so “done” means verified green, not a confident paragraph. Autonomy without a contract is just a longer chat. Goal Mode gives the agent a finish line it cannot hand-wave past. ## Install this skill ```bash npx skills add shenwell/ai-agent-skills --skill goal-mode -g ``` ## Who it's for Engineers who want **unattended, long-running, or overnight coding agent** runs — including Cursor Cloud Agent and headless CI pipelines — with a durable contract instead of endless “try again” in chat. Use it when the task has a **measurable completion condition**: zero lint errors, passing tests, green CI, successfu