gpt-image

1# gpt-image
2 
3Agent runbook for GPT Image 2 / 2.5 / 2.6 generation/editing. Use the prompt library + packaged CLI. Do not reimplement image API code.
4 
5## Operating loop
6 
71. **Classify request and resolve model**: `generate`, `edit`, `inpaint`, or `multi-reference`; identify asset type, exact text, aspect ratio, references, safety constraints, and budget/quality. Apply the model-choice rules below before any API call.
82. **Choose the reference path**: Image 2 keeps the gallery-first workflow below. For 2.5/2.6, a precise brief needs no reference loading; otherwise choose one short task slice.
93. **Refine only as needed**: preserve the brief. Add a specific gallery case, craft section or template only to fill a concrete gap; do not load them as a bundle for 2.5/2.6.
104. **Confer when useful**: before costly/ambiguous/high-polish calls, present 1–3 matched directions plus planned size/quality; ask at most one concise question at a time. Skip long discussion for precise “generate now” requests with a resolved model.
115. **Preflight, no side effects**: use existing CLI/skill if present. Check command availability (`command -v gpt-image`), installed tool lists when the tool manager exists, or the runtime’s own skill registry when available. Do not assume a local home path in cloud/hosted runtimes.
126. **No blind setup**: do not reinstall, overwrite skill folders, create/modify `.env`, or write API keys unless the user explicitly requested setup. Global/shared installs are opt-in only.
13…