Loading...
Loading...
Found 4 Skills
Explain and write effective instructions for the `/goal` feature — the persistent self-checking agent loop (plan → act → test → review → iterate), available in agents like Codex, Claude Code, and Hermes Agent. Use when the user mentions `/goal`, "goal loop", "Ralph loop", wants to kick off a long-running autonomous agent run, asks how to write a goal prompt, or wants a one-paragraph goal instruction drafted.
Use when the operator explicitly asks to iterate on a bounded objective until it is satisfied, such as a refactor, cleanup, documentation rewrite, non-ticket change, or ticket follow-up. Trigger on goal-loop, loop until done, iterate until clean, max rounds, or similar language. Do not self-trigger for ordinary implementation. Never commits.
Advance a concrete goal in bounded verified rounds.
GPT (GPT-6 Astra by default) as advisor, adversarial reviewer or judge through headless `codex exec`, always read-only; never an implementer. Modes: advise (independent read on a plan, diff or design, beside Claude's own view, with follow-ups), review (Codex's built-in reviewer on uncommitted work, a branch or a commit), adversarial (tries to break confidence in a change; optional parallel lenses; every finding verified by Claude before it is shown), judge (scores a reviewer's verdict for insistir and goal-loop). Trigger on "second opinion", "segunda opinión", "ask codex/GPT to review", "que codex lo revise", "revisión adversarial", "adversarial review", "que GPT ataque este cambio", "critica este plan", "challenge this design", "judge this review", "usa astra". Falls back to a Claude subagent, labelled same-provider, when Codex is unavailable. Not askcodex (one-shot text or images) and not for writing code.