winter-super-cli 2026.5.15

package/resources/local/codex/skills/.system/imagegen/SKILL.md

@@ -0,0 +1,356 @@
+---
+name: "imagegen"
+description: "Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas."
+---
+
+# Image Generation Skill
+
+Generates or edits images for the current project (for example website assets, game assets, UI mockups, product mockups, wireframes, logo design, photorealistic images, or infographics).
+
+## Top-level modes and rules
+
+This skill has exactly two top-level modes:
+
+- **Default built-in tool mode (preferred):** built-in `image_gen` tool for normal image generation, editing, and simple transparent-image requests. Does not require `OPENAI_API_KEY`.
+- **Fallback CLI mode:** `scripts/image_gen.py` CLI. Use when the user explicitly asks for the CLI/API/model path, or after the user explicitly confirms a true model-native transparency fallback with `gpt-image-1.5`. Requires `OPENAI_API_KEY`.
+
+Within CLI fallback, the CLI exposes three subcommands:
+
+- `generate`
+- `edit`
+- `generate-batch`
+
+Rules:
+- Use the built-in `image_gen` tool by default for normal image generation and editing requests.
+- Do not switch to CLI fallback for ordinary quality, size, or file-path control.
+- If the user explicitly asks for a transparent image/background, stay on built-in `image_gen` first: prompt for a flat removable chroma-key background, then remove it locally with the installed helper at `$CODEX_HOME/skills/.system/imagegen/scripts/remove_chroma_key.py`.
+- Never silently switch from built-in `image_gen` or CLI `gpt-image-2` to CLI `gpt-image-1.5`. Treat this as a model/path downgrade and ask the user before doing it, unless the user has already explicitly requested `gpt-image-1.5`, `scripts/image_gen.py`, or CLI fallback.
+- If a transparent request appears too complex for clean chroma-key removal, asks for true/native transparency, or local removal fails validation, explain that true transparency requires CLI `gpt-image-1.5 --background transparent --output-format png` because `gpt-image-2` does not support `background=transparent`, then ask whether to proceed. Run the CLI fallback only after the user confirms.
+- The word `batch` by itself does not mean CLI fallback. If the user asks for many assets or says to batch-generate assets without explicitly asking for CLI/API/model controls, stay on the built-in path and issue one built-in call per requested asset or variant.
+- If the built-in tool fails or is unavailable, tell the user the CLI fallback exists and that it requires `OPENAI_API_KEY`. Proceed only if the user explicitly asks for that fallback.
+- If the user explicitly asks for CLI mode, use the bundled `scripts/image_gen.py` workflow. Do not create one-off SDK runners.
+- Never modify `scripts/image_gen.py`. If something is missing, ask the user before doing anything else.
+
+Built-in save-path policy:
+- In built-in tool mode, Codex saves generated images under `$CODEX_HOME/*` by default.
+- Do not describe or rely on OS temp as the default built-in destination.
+- Do not describe or rely on a destination-path argument (if any) on the built-in `image_gen` tool. If a specific location is needed, generate first and then move or copy the selected output from `$CODEX_HOME/generated_images/...`.
+- Save-path precedence in built-in mode:
+  1. If the user names a destination, move or copy the selected output there.
+  2. If the image is meant for the current project, move or copy the final selected image into the workspace before finishing.
+  3. If the image is only for preview or brainstorming, render it inline; the underlying file can remain at the default `$CODEX_HOME/*` path.
+- Never leave a project-referenced asset only at the default `$CODEX_HOME/*` path.
+- Do not overwrite an existing asset unless the user explicitly asked for replacement; otherwise create a sibling versioned filename such as `hero-v2.png` or `item-icon-edited.png`.
+
+Shared prompt guidance for both modes lives in `references/prompting.md` and `references/sample-prompts.md`.
+
+Fallback-only docs/resources for CLI mode:
+- `references/cli.md`
+- `references/image-api.md`
+- `references/codex-network.md`
+- `scripts/image_gen.py`
+
+Local post-processing helper:
+- `$CODEX_HOME/skills/.system/imagegen/scripts/remove_chroma_key.py`: removes a flat chroma-key background from a generated image and writes a PNG/WebP with alpha. Prefer auto-key sampling, soft matte, and despill for antialiased edges.
+
+## When to use
+- Generate a new image (concept art, product shot, cover, website hero)
+- Generate a new image using one or more reference images for style, composition, or mood
+- Edit an existing image (inpainting, lighting or weather transformations, background replacement, object removal, compositing, transparent background)
+- Produce many assets or variants for one task
+
+## When not to use
+- Extending or matching an existing SVG/vector icon set, logo system, or illustration library inside the repo
+- Creating simple shapes, diagrams, wireframes, or icons that are better produced directly in SVG, HTML/CSS, or canvas
+- Making a small project-local asset edit when the source file already exists in an editable native format
+- Any task where the user clearly wants deterministic code-native output instead of a generated bitmap
+
+## Decision tree
+
+Think about two separate questions:
+
+1. **Intent:** is this a new image or an edit of an existing image?
+2. **Execution strategy:** is this one asset or many assets/variants?
+
+Intent:
+- If the user wants to modify an existing image while preserving parts of it, treat the request as **edit**.
+- If the user provides images only as references for style, composition, mood, or subject guidance, treat the request as **generate**.
+- If the user provides no images, treat the request as **generate**.
+
+Built-in edit semantics:
+- Built-in edit mode is for images already visible in the conversation context, such as attached images or images generated earlier in the thread.
+- If the user wants to edit a local image file with the built-in tool, first load it with built-in `view_image` tool so the image is visible in the conversation context, then proceed with the built-in edit flow.
+- Do not promise arbitrary filesystem-path editing through the built-in tool.
+- If a local file still needs direct file-path control, masks, or other explicit CLI-only parameters, use the explicit CLI fallback only when the user asks for it.
+- For edits, preserve invariants aggressively and save non-destructively by default.
+
+Execution strategy:
+- In the built-in default path, produce many assets or variants by issuing one `image_gen` call per requested asset or variant.
+- In the CLI fallback path, use the CLI `generate-batch` subcommand only when the user explicitly chose CLI mode and needs many prompts/assets.
+- For many distinct assets, do not use `n` as a substitute for separate prompts. `n` is for variants of one prompt; distinct assets need distinct built-in calls or distinct CLI `generate-batch` jobs.
+
+Assume the user wants a new image unless they clearly ask to change an existing one.
+
+## Workflow
+1. Decide the top-level mode: built-in by default, including simple transparent-output requests; fallback CLI only if explicitly requested or after the user explicitly confirms a transparent-output fallback.
+2. Decide the intent: `generate` or `edit`.
+3. Decide whether the output is preview-only or meant to be consumed by the current project.
+4. Decide the execution strategy: single asset vs repeated built-in calls vs CLI `generate-batch`.
+5. Collect inputs up front: prompt(s), exact text (verbatim), constraints/avoid list, and any input images.
+6. For every input image, label its role explicitly:
+   - reference image
+   - edit target
+   - supporting insert/style/compositing input
+7. If the edit target is only on the local filesystem and you are staying on the built-in path, inspect it with `view_image` first so the image is available in conversation context.
+8. If the user asked for a photo, illustration, sprite, product image, banner, or other explicitly raster-style asset, use `image_gen` rather than substituting SVG/HTML/CSS placeholders. If the request is for an icon, logo, or UI graphic that should match existing repo-native SVG/vector/code assets, prefer editing those directly instead.
+9. Augment the prompt based on specificity:
+   - If the user's prompt is already specific and detailed, normalize it into a clear spec without adding creative requirements.
+   - If the user's prompt is generic, add tasteful augmentation only when it materially improves output quality.
+10. Use the built-in `image_gen` tool by default.
+11. For transparent-output requests, follow the transparent image guidance below: generate with built-in `image_gen` on a flat chroma-key background, copy the selected output into the workspace or `tmp/imagegen/`, run the installed `$CODEX_HOME/skills/.system/imagegen/scripts/remove_chroma_key.py` helper, and validate the alpha result before using it. If this path looks unsuitable or fails, ask before switching to CLI `gpt-image-1.5`.
+12. Inspect outputs and validate: subject, style, composition, text accuracy, and invariants/avoid items.
+13. Iterate with a single targeted change, then re-check.
+14. For preview-only work, render the image inline; the underlying file may remain at the default `$CODEX_HOME/generated_images/...` path.
+15. For project-bound work, move or copy the selected artifact into the workspace and update any consuming code or references. Never leave a project-referenced asset only at the default `$CODEX_HOME/generated_images/...` path.
+16. For batches or multi-asset requests, persist every requested deliverable final in the workspace unless the user explicitly asked to keep outputs preview-only. Discarded variants do not need to be kept unless requested.
+17. If the user explicitly chooses or confirms the CLI fallback, then use the fallback-only docs for model, quality, size, `input_fidelity`, masks, output format, output paths, and network setup.
+18. Always report the final saved path(s) for any workspace-bound asset(s), plus the final prompt or prompt set and whether the built-in tool or fallback CLI mode was used.
+
+## Transparent image requests
+
+Transparent-image requests still use built-in `image_gen` first. Because the built-in tool does not expose a true transparent-background control, create a removable chroma-key source image and then convert the key color to alpha locally.
+
+Default sequence:
+1. Use built-in `image_gen` to generate the requested subject on a perfectly flat solid chroma-key background.
+2. Choose a key color that is unlikely to appear in the subject: default `#00ff00`, use `#ff00ff` for green subjects, and avoid `#0000ff` for blue subjects.
+3. After generation, move or copy the selected source image from `$CODEX_HOME/generated_images/...` into the workspace or `tmp/imagegen/`.
+4. Run the installed helper path, not a project-relative script path:
+   ```bash
+   python "${CODEX_HOME:-$HOME/.codex}/skills/.system/imagegen/scripts/remove_chroma_key.py" \
+     --input <source> \
+     --out <final.png> \
+     --auto-key border \
+     --soft-matte \
+     --transparent-threshold 12 \
+     --opaque-threshold 220 \
+     --despill
+   ```
+5. Validate that the output has an alpha channel, transparent corners, plausible subject coverage, and no obvious key-color fringe. If a thin fringe remains, retry once with `--edge-contract 1`; use `--edge-feather 0.25` only when the edge is visibly stair-stepped and the subject is not shiny or reflective.
+6. Save the final alpha PNG/WebP in the project if the asset is project-bound. Never leave a project-referenced transparent asset only under `$CODEX_HOME/*`.
+
+Prompt transparent requests like this:
+
+```text
+Create the requested subject on a perfectly flat solid #00ff00 chroma-key background for background removal.
+The background must be one uniform color with no shadows, gradients, texture, reflections, floor plane, or lighting variation.
+Keep the subject fully separated from the background with crisp edges and generous padding.
+Do not use #00ff00 anywhere in the subject.
+No cast shadow, no contact shadow, no reflection, no watermark, and no text unless explicitly requested.
+```
+
+Do not automatically use CLI `gpt-image-1.5 --background transparent --output-format png` instead of chroma keying. Ask the user first when the user asks for true/native transparency, when local removal fails validation, or when the requested image is complex: hair, fur, feathers, smoke, glass, liquids, translucent materials, reflective objects, soft shadows, realistic product grounding, or subject colors that conflict with all practical key colors.
+
+Use a concise confirmation like:
+
+```text
+This likely needs true native transparency. The default built-in path uses a chroma-key background plus local removal, but true transparency requires the CLI fallback with gpt-image-1.5 because gpt-image-2 does not support background=transparent. It also requires OPENAI_API_KEY. Should I proceed with that CLI fallback?
+```
+
+## Prompt augmentation
+
+Reformat user prompts into a structured, production-oriented spec. Make the user's goal clearer and more actionable, but do not blindly add detail.
+
+Treat this as prompt-shaping guidance, not a closed schema. Use only the lines that help, and add a short extra labeled line when it materially improves clarity.
+
+### Specificity policy
+
+Use the user's prompt specificity to decide how much augmentation is appropriate:
+
+- If the prompt is already specific and detailed, preserve that specificity and only normalize/structure it.
+- If the prompt is generic, you may add tasteful augmentation when it will materially improve the result.
+
+Allowed augmentations:
+- composition or framing hints
+- polish level or intended-use hints
+- practical layout guidance
+- reasonable scene concreteness that supports the stated request
+
+Not allowed augmentations:
+- extra characters or objects that are not implied by the request
+- brand names, slogans, palettes, or narrative beats that are not implied
+- arbitrary side-specific placement unless the surrounding layout supports it
+
+## Use-case taxonomy (exact slugs)
+
+Classify each request into one of these buckets and keep the slug consistent across prompts and references.
+
+Generate:
+- photorealistic-natural — candid/editorial lifestyle scenes with real texture and natural lighting.
+- product-mockup — product/packaging shots, catalog imagery, merch concepts.
+- ui-mockup — app/web interface mockups and wireframes; specify the desired fidelity.
+- infographic-diagram — diagrams/infographics with structured layout and text.
+- scientific-educational — classroom explainers, scientific diagrams, and learning visuals with required labels and accuracy constraints.
+- ads-marketing — campaign concepts and ad creatives with audience, brand position, scene, and exact tagline/copy.
+- productivity-visual — slide, chart, workflow, and data-heavy business visuals.
+- logo-brand — logo/mark exploration, vector-friendly.
+- illustration-story — comics, children’s book art, narrative scenes.
+- stylized-concept — style-driven concept art, 3D/stylized renders.
+- historical-scene — period-accurate/world-knowledge scenes.
+
+Edit:
+- text-localization — translate/replace in-image text, preserve layout.
+- identity-preserve — try-on, person-in-scene; lock face/body/pose.
+- precise-object-edit — remove/replace a specific element (including interior swaps).
+- lighting-weather — time-of-day/season/atmosphere changes only.
+- background-extraction — transparent background / clean cutout. Use built-in `image_gen` with chroma-key removal first for simple opaque subjects; ask before using CLI true transparency for complex subjects.
+- style-transfer — apply reference style while changing subject/scene.
+- compositing — multi-image insert/merge with matched lighting/perspective.
+- sketch-to-render — drawing/line art to photoreal render.
+
+## Shared prompt schema
+
+Use the following labeled spec as shared prompt scaffolding for both top-level modes:
+
+```text
+Use case: <taxonomy slug>
+Asset type: <where the asset will be used>
+Primary request: <user's main prompt>
+Input images: <Image 1: role; Image 2: role> (optional)
+Scene/backdrop: <environment>
+Subject: <main subject>
+Style/medium: <photo/illustration/3D/etc>
+Composition/framing: <wide/close/top-down; placement>
+Lighting/mood: <lighting + mood>
+Color palette: <palette notes>
+Materials/textures: <surface details>
+Text (verbatim): "<exact text>"
+Constraints: <must keep/must avoid>
+Avoid: <negative constraints>
+```
+
+Notes:
+- `Asset type` and `Input images` are prompt scaffolding, not dedicated CLI flags.
+- `Scene/backdrop` refers to the visual setting. It is not the same as the fallback CLI `background` parameter, which controls output transparency behavior.
+- Fallback-only execution notes such as `Quality:`, `Input fidelity:`, masks, output format, and output paths belong in the CLI path only. Do not treat them as built-in `image_gen` tool arguments.
+
+Augmentation rules:
+- Keep it short.
+- Add only the details needed to improve the prompt materially.
+- For edits, explicitly list invariants (`change only X; keep Y unchanged`).
+- If any critical detail is missing and blocks success, ask a question; otherwise proceed.
+
+## Examples
+
+### Generation example (hero image)
+```text
+Use case: product-mockup
+Asset type: landing page hero
+Primary request: a minimal hero image of a ceramic coffee mug
+Style/medium: clean product photography
+Composition/framing: wide composition with usable negative space for page copy if needed
+Lighting/mood: soft studio lighting
+Constraints: no logos, no text, no watermark
+```
+
+### Edit example (invariants)
+```text
+Use case: precise-object-edit
+Asset type: product photo background replacement
+Primary request: replace only the background with a warm sunset gradient
+Constraints: change only the background; keep the product and its edges unchanged; no text; no watermark
+```
+
+## Prompting best practices
+- Structure prompt as scene/backdrop -> subject -> details -> constraints.
+- Include intended use (ad, UI mock, infographic) to set the mode and polish level.
+- Use camera/composition language for photorealism.
+- Only use SVG/vector stand-ins when the user explicitly asked for vector output or a non-image placeholder.
+- Quote exact text and specify typography + placement.
+- For tricky words, spell them letter-by-letter and require verbatim rendering.
+- For multi-image inputs, reference images by index and describe how they should be used.
+- For edits, repeat invariants every iteration to reduce drift.
+- Iterate with single-change follow-ups.
+- If the prompt is generic, add only the extra detail that will materially help.
+- If the prompt is already detailed, normalize it instead of expanding it.
+- For CLI fallback only, see `references/cli.md` and `references/image-api.md` for model, `quality`, `input_fidelity`, masks, output format, and output-path guidance.
+- For transparent images, use the built-in-first chroma-key workflow unless the request is complex enough to need true CLI transparency; ask before switching to CLI `gpt-image-1.5`.
+
+More principles shared by both modes: `references/prompting.md`.
+Copy/paste specs shared by both modes: `references/sample-prompts.md`.
+
+## Guidance by asset type
+Asset-type templates (website assets, game assets, wireframes, logo) are consolidated in `references/sample-prompts.md`.
+
+## gpt-image-2 guidance for CLI fallback
+
+The fallback CLI defaults to `gpt-image-2`.
+
+- Use `gpt-image-2` for new CLI/API workflows unless the request needs true model-native transparent output.
+- If a transparent request may need CLI fallback, ask before using `gpt-image-1.5` unless the user already explicitly requested `gpt-image-1.5`, `scripts/image_gen.py`, or CLI fallback. Explain that the built-in chroma-key path is the default, but true transparency requires `gpt-image-1.5` because `gpt-image-2` does not support `background=transparent`.
+- `gpt-image-2` always uses high fidelity for image inputs; do not set `input_fidelity` with this model.
+- `gpt-image-2` supports `quality` values `low`, `medium`, `high`, and `auto`.
+- Use `quality low` for fast drafts, thumbnails, and quick iterations. Use `medium`, `high`, or `auto` for final assets, dense text, diagrams, identity-sensitive edits, or high-resolution outputs.
+- Square images are typically fastest to generate. Use `1024x1024` for fast square drafts.
+- If the user asks for 4K-style output, use `3840x2160` for landscape or `2160x3840` for portrait.
+- `gpt-image-2` size may be `auto` or `WIDTHxHEIGHT` if all constraints hold: max edge `<= 3840px`, both edges multiples of `16px`, long-to-short ratio `<= 3:1`, total pixels between `655,360` and `8,294,400`.
+
+Popular `gpt-image-2` sizes:
+- `1024x1024` square
+- `1536x1024` landscape
+- `1024x1536` portrait
+- `2048x2048` 2K square
+- `2048x1152` 2K landscape
+- `3840x2160` 4K landscape
+- `2160x3840` 4K portrait
+- `auto`
+
+## Fallback CLI mode only
+
+### Temp and output conventions
+These conventions apply only to the CLI fallback. They do not describe built-in `image_gen` output behavior.
+- Use `tmp/imagegen/` for intermediate files (for example JSONL batches); delete them when done.
+- Write final artifacts under `output/imagegen/`.
+- Use `--out` or `--out-dir` to control output paths; keep filenames stable and descriptive.
+
+### Dependencies
+Prefer `uv` for dependency management in this repo.
+
+Required Python package:
+```bash
+uv pip install openai
+```
+
+Required for local chroma-key removal and optional downscaling:
+```bash
+uv pip install pillow
+```
+
+Portability note:
+- If you are using the installed skill outside this repo, install dependencies into that environment with its package manager.
+- In uv-managed environments, `uv pip install ...` remains the preferred path.
+
+### Environment
+- `OPENAI_API_KEY` must be set for live API calls.
+- Do not ask the user for `OPENAI_API_KEY` when using the built-in `image_gen` tool.
+- Never ask the user to paste the full key in chat. Ask them to set it locally and confirm when ready.
+
+If the key is missing, give the user these steps:
+1. Create an API key in the OpenAI platform UI: https://platform.openai.com/api-keys
+2. Set `OPENAI_API_KEY` as an environment variable in their system.
+3. Offer to guide them through setting the environment variable for their OS/shell if needed.
+
+If installation is not possible in this environment, tell the user which dependency is missing and how to install it into their active environment.
+
+### Script-mode notes
+- CLI commands + examples: `references/cli.md`
+- API parameter quick reference: `references/image-api.md`
+- Network approvals / sandbox settings for CLI mode: `references/codex-network.md`
+
+## Reference map
+- `references/prompting.md`: shared prompting principles for both modes.
+- `references/sample-prompts.md`: shared copy/paste prompt recipes for both modes.
+- `references/cli.md`: fallback-only CLI usage via `scripts/image_gen.py`.
+- `references/image-api.md`: fallback-only API/CLI parameter reference.
+- `references/codex-network.md`: fallback-only network/sandbox troubleshooting for CLI mode.
+- `scripts/image_gen.py`: fallback-only CLI implementation. Do not load or use it unless the user explicitly chooses CLI mode or explicitly confirms a transparent request's true CLI transparency fallback.
+- `$CODEX_HOME/skills/.system/imagegen/scripts/remove_chroma_key.py`: local post-processing helper for built-in transparent-image requests.

package/resources/local/codex/skills/.system/imagegen/agents/openai.yaml

@@ -0,0 +1,6 @@
+interface:
+  display_name: "Image Gen"
+  short_description: "Generate or edit images for websites, games, and more"
+  icon_small: "./assets/imagegen-small.svg"
+  icon_large: "./assets/imagegen.png"
+  default_prompt: "Use $imagegen to make or edit an image for this project."

package/resources/local/codex/skills/.system/imagegen/assets/imagegen-small.svg

@@ -0,0 +1,5 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" viewBox="0 0 16 16">
+  <path fill="currentColor" d="M7.51 6.827a1 1 0 1 1 .278 1.982 1 1 0 0 1-.278-1.982Z"/>
+  <path fill="currentColor" fill-rule="evenodd" d="M8.31 4.47c.368-.016.699.008 1.016.124l.186.075c.423.194.786.5 1.047.888l.067.107c.148.253.235.533.3.848.073.354.126.797.193 1.343l.277 2.25.088.745c.024.224.041.425.049.605.013.322-.004.615-.085.896l-.04.12a2.53 2.53 0 0 1-.802 1.115l-.16.118c-.281.189-.596.292-.956.366a9.46 9.46 0 0 1-.6.1l-.743.094-2.25.277c-.547.067-.99.121-1.35.136a2.765 2.765 0 0 1-.896-.085l-.12-.039a2.533 2.533 0 0 1-1.115-.802l-.118-.161c-.189-.28-.292-.596-.366-.956a9.42 9.42 0 0 1-.1-.599l-.094-.744-.276-2.25a17.884 17.884 0 0 1-.137-1.35c-.015-.367.009-.698.124-1.015l.076-.185c.193-.423.5-.787.887-1.048l.107-.067c.253-.148.534-.234.849-.3.354-.073.796-.126 1.343-.193l2.25-.277.744-.088c.224-.024.425-.041.606-.049Zm-2.905 5.978a1.47 1.47 0 0 0-.875.074c-.127.052-.267.146-.475.344-.212.204-.462.484-.822.889l-.314.351c.018.115.036.219.055.313.061.295.127.458.206.575l.07.094c.167.211.39.372.645.465l.109.032c.119.027.273.038.499.029.308-.013.7-.06 1.264-.13l2.25-.275.727-.093.198-.03-2.05-1.64a16.848 16.848 0 0 0-.96-.738c-.18-.121-.31-.19-.421-.23l-.106-.03Zm2.95-4.915c-.154.006-.33.021-.536.043l-.729.086-2.25.276c-.564.07-.956.118-1.257.18a1.937 1.937 0 0 0-.478.15l-.097.057a1.47 1.47 0 0 0-.515.608l-.044.107c-.048.133-.073.307-.06.608.012.307.06.7.129 1.264l.22 1.8.178-.197c.145-.159.278-.298.403-.418.255-.243.507-.437.809-.56l.181-.067a2.526 2.526 0 0 1 1.328-.06l.118.029c.27.079.517.215.772.387.287.194.619.46 1.03.789l2.52 2.016c.146-.148.26-.326.332-.524l.031-.109c.027-.119.039-.273.03-.499a8.311 8.311 0 0 0-.044-.536l-.086-.728-.276-2.25c-.07-.564-.118-.956-.18-1.258a1.935 1.935 0 0 0-.15-.477l-.057-.098a1.468 1.468 0 0 0-.608-.515l-.107-.043c-.133-.049-.306-.074-.607-.061Z" clip-rule="evenodd"/>
+  <path fill="currentColor" d="M7.783 1.272c.36.014.803.07 1.35.136l2.25.277.743.095c.224.03.423.062.6.099.36.074.675.177.955.366l.161.118c.364.29.642.675.802 1.115l.04.12c.081.28.098.574.085.896a9.42 9.42 0 0 1-.05.605l-.087.745-.277 2.25c-.067.547-.12.989-.193 1.343a2.765 2.765 0 0 1-.3.848l-.067.107a2.534 2.534 0 0 1-.415.474l-.086.064a.532.532 0 0 1-.622-.858l.13-.13c.04-.046.077-.094.111-.145l.057-.098c.055-.109.104-.256.15-.477.062-.302.11-.694.18-1.258l.276-2.25.086-.728c.022-.207.037-.382.043-.536.01-.226-.002-.38-.029-.5l-.032-.108a1.469 1.469 0 0 0-.464-.646l-.094-.069c-.118-.08-.28-.145-.575-.206a8.285 8.285 0 0 0-.53-.088l-.728-.092-2.25-.276c-.565-.07-.956-.117-1.264-.13a1.94 1.94 0 0 0-.5.029l-.108.032a1.469 1.469 0 0 0-.647.465l-.068.094c-.054.08-.102.18-.146.33l-.04.1a.533.533 0 0 1-.98-.403l.055-.166c.059-.162.133-.314.23-.457l.117-.16c.29-.365.675-.643 1.115-.803l.12-.04c.28-.08.574-.097.896-.084Z"/>
+</svg>

package/resources/local/codex/skills/.system/imagegen/references/cli.md

@@ -0,0 +1,242 @@
+# CLI reference (`scripts/image_gen.py`)
+
+This file is for the fallback CLI mode only. Read it when the user explicitly asks to use `scripts/image_gen.py` / CLI / API / model controls, or after the user explicitly confirms that a transparent-output request should use the `gpt-image-1.5` true-transparency fallback path.
+
+`generate-batch` is a CLI subcommand in this fallback path. It is not a top-level mode of the skill.
+The word `batch` in a user request is not CLI opt-in by itself.
+
+## What this CLI does
+- `generate`: generate a new image from a prompt
+- `edit`: edit one or more existing images
+- `generate-batch`: run many generation jobs from a JSONL file after the user explicitly chooses CLI/API/model controls
+
+Real API calls require **network access** + `OPENAI_API_KEY`. `--dry-run` does not.
+
+## Quick start (works from any repo)
+Set a stable path to the skill CLI (default `CODEX_HOME` is `~/.codex`):
+
+```
+export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
+export IMAGE_GEN="$CODEX_HOME/skills/.system/imagegen/scripts/image_gen.py"
+```
+
+Install dependencies into that environment with its package manager. In uv-managed environments, `uv pip install ...` remains the preferred path.
+
+## Quick start
+
+Dry-run (no API call; no network required; does not require the `openai` package):
+
+```bash
+python "$IMAGE_GEN" generate \
+  --prompt "Test" \
+  --out output/imagegen/test.png \
+  --dry-run
+```
+
+Notes:
+- One-off dry-runs print the API payload and the computed output path(s).
+- Repo-local finals should live under `output/imagegen/`.
+
+Generate (requires `OPENAI_API_KEY` + network):
+
+```bash
+python "$IMAGE_GEN" generate \
+  --prompt "A cozy alpine cabin at dawn" \
+  --size 1024x1024 \
+  --out output/imagegen/alpine-cabin.png
+```
+
+Edit:
+
+```bash
+python "$IMAGE_GEN" edit \
+  --image input.png \
+  --prompt "Replace only the background with a warm sunset" \
+  --out output/imagegen/sunset-edit.png
+```
+
+## Guardrails
+- Use the bundled CLI directly (`python "$IMAGE_GEN" ...`) after activating the correct environment.
+- Do **not** create one-off runners (for example `gen_images.py`) unless the user explicitly asks for a custom wrapper.
+- **Never modify** `scripts/image_gen.py`. If something is missing, ask the user before doing anything else.
+- Do not silently downgrade from CLI `gpt-image-2` or built-in `image_gen` to CLI `gpt-image-1.5`; ask first unless the user already explicitly requested `gpt-image-1.5`, `scripts/image_gen.py`, or CLI fallback.
+
+## Defaults
+- Model: `gpt-image-2`
+- Supported model family for this CLI: GPT Image models (`gpt-image-*`)
+- Size: `auto`
+- Quality: `medium`
+- Output format: `png`
+- Default one-off output path: `output/imagegen/output.png`
+- Background: unspecified unless `--background` is set
+
+## gpt-image-2 size and model guidance
+
+`gpt-image-2` is the default model for new CLI fallback work.
+
+- Use `--quality low` for fast drafts, thumbnails, and quick iterations.
+- Use `--quality medium`, `--quality high`, or `--quality auto` for final assets, dense text, diagrams, identity-sensitive edits, and high-resolution outputs.
+- Square images are typically fastest. Use `--size 1024x1024` for quick square drafts.
+- If the user asks for 4K-style output, use `--size 3840x2160` for landscape or `--size 2160x3840` for portrait.
+- Do not pass `--input-fidelity` with `gpt-image-2`; this model always uses high fidelity for image inputs.
+- Do not use `--background transparent` with `gpt-image-2`; the default transparent-image workflow uses built-in `image_gen` on a flat chroma-key background plus local removal. Use `gpt-image-1.5` only after the user explicitly confirms the true-transparent CLI fallback, unless they already requested `gpt-image-1.5`, `scripts/image_gen.py`, or CLI fallback.
+
+Popular `gpt-image-2` sizes:
+- `1024x1024`
+- `1536x1024`
+- `1024x1536`
+- `2048x2048`
+- `2048x1152`
+- `3840x2160`
+- `2160x3840`
+- `auto`
+
+`gpt-image-2` size constraints:
+- max edge `<= 3840px`
+- both edges multiples of `16px`
+- long edge to short edge ratio `<= 3:1`
+- total pixels between `655,360` and `8,294,400`
+- outputs above `2560x1440` total pixels are experimental
+
+Fast draft:
+
+```bash
+python "$IMAGE_GEN" generate \
+  --prompt "A product thumbnail of a matte ceramic mug on a stone surface" \
+  --quality low \
+  --size 1024x1024 \
+  --out output/imagegen/mug-draft.png
+```
+
+Final 2K landscape:
+
+```bash
+python "$IMAGE_GEN" generate \
+  --prompt "A polished landing-page hero image of a matte ceramic mug on a stone surface" \
+  --quality high \
+  --size 2048x1152 \
+  --out output/imagegen/mug-hero.png
+```
+
+4K landscape:
+
+```bash
+python "$IMAGE_GEN" generate \
+  --prompt "A detailed architectural visualization at golden hour" \
+  --size 3840x2160 \
+  --quality high \
+  --out output/imagegen/architecture-4k.png
+```
+
+True transparent fallback request:
+
+Ask for confirmation before using this command unless the user already explicitly requested `gpt-image-1.5`, `scripts/image_gen.py`, or CLI fallback.
+
+```bash
+python "$IMAGE_GEN" generate \
+  --model gpt-image-1.5 \
+  --prompt "A clean product cutout on a transparent background" \
+  --background transparent \
+  --output-format png \
+  --out output/imagegen/product-cutout.png
+```
+
+When using this path, explain briefly that built-in `image_gen` plus chroma-key removal is the default transparent-image path, but this request needs true model-native transparency. `gpt-image-2` does not support `background=transparent`, so `gpt-image-1.5` is required for this confirmed fallback.
+
+## Quality, input fidelity, and masks (CLI fallback only)
+These are explicit CLI controls. They are not built-in `image_gen` tool arguments.
+
+- `--quality` works for `generate`, `edit`, and `generate-batch`: `low|medium|high|auto`
+- `--input-fidelity` is **edit-only** and validated as `low|high`; it is not supported for `gpt-image-2`
+- `--mask` is **edit-only**
+
+Example:
+
+```bash
+python "$IMAGE_GEN" edit \
+  --model gpt-image-1.5 \
+  --image input.png \
+  --prompt "Change only the background" \
+  --quality high \
+  --input-fidelity high \
+  --out output/imagegen/background-edit.png
+```
+
+Mask notes:
+- For multi-image edits, pass repeated `--image` flags. Their order is meaningful, so describe each image by index and role in the prompt.
+- The CLI accepts a single `--mask`.
+- Image and mask must be the same size and format and each under 50MB.
+- Masks must include an alpha channel.
+- If multiple input images are provided, the mask applies to the first image.
+- Masking is prompt-guided; do not promise exact pixel-perfect mask boundaries.
+- Use a PNG mask when possible; the script treats mask handling as best-effort and does not perform full preflight validation beyond file checks/warnings.
+- In the edit prompt, repeat invariants (`change only the background; keep the subject unchanged`) to reduce drift.
+
+## Output handling
+- Use `tmp/imagegen/` for temporary JSONL inputs or scratch files.
+- Use `output/imagegen/` for final outputs.
+- Reruns fail if a target file already exists unless you pass `--force`.
+- `--out-dir` changes one-off naming to `image_1.<ext>`, `image_2.<ext>`, and so on.
+- Downscaled copies use the default suffix `-web` unless you override it.
+
+## Common recipes
+
+Generate with augmentation fields:
+
+```bash
+python "$IMAGE_GEN" generate \
+  --prompt "A minimal hero image of a ceramic coffee mug" \
+  --use-case "product-mockup" \
+  --style "clean product photography" \
+  --composition "wide product shot with usable negative space for page copy" \
+  --constraints "no logos, no text" \
+  --out output/imagegen/mug-hero.png
+```
+
+Generate + also write a downscaled copy for fast web loading:
+
+```bash
+python "$IMAGE_GEN" generate \
+  --prompt "A cozy alpine cabin at dawn" \
+  --size 1024x1024 \
+  --downscale-max-dim 1024 \
+  --out output/imagegen/alpine-cabin.png
+```
+
+Generate multiple prompts concurrently (async batch):
+
+```bash
+mkdir -p tmp/imagegen output/imagegen/batch
+cat > tmp/imagegen/prompts.jsonl << 'EOF'
+{"prompt":"Cavernous hangar interior with a compact shuttle parked near the center","use_case":"stylized-concept","composition":"wide-angle, low-angle","lighting":"volumetric light rays through drifting fog","constraints":"no logos or trademarks; no watermark","size":"1536x1024"}
+{"prompt":"Gray wolf in profile in a snowy forest","use_case":"photorealistic-natural","composition":"eye-level","constraints":"no logos or trademarks; no watermark","size":"1024x1024"}
+EOF
+
+python "$IMAGE_GEN" generate-batch \
+  --input tmp/imagegen/prompts.jsonl \
+  --out-dir output/imagegen/batch \
+  --concurrency 5
+
+rm -f tmp/imagegen/prompts.jsonl
+```
+
+Notes:
+- `generate-batch` requires `--out-dir`.
+- generate-batch requires --out-dir.
+- Use `--concurrency` to control parallelism (default `5`).
+- Per-job overrides are supported in JSONL (for example `size`, `quality`, `background`, `output_format`, `output_compression`, `moderation`, `n`, `model`, `out`, and prompt-augmentation fields).
+- `--n` generates multiple variants for a single prompt; `generate-batch` is for many different prompts.
+- In batch mode, per-job `out` is treated as a filename under `--out-dir`.
+- For many requested deliverable assets, provide one prompt/job per distinct asset and use semantic filenames when possible.
+
+## CLI notes
+- Supported sizes depend on the model. `gpt-image-2` supports flexible constrained sizes; older GPT Image models support `1024x1024`, `1536x1024`, `1024x1536`, or `auto`.
+- True transparent CLI outputs require `output_format` to be `png` or `webp` and are not supported by `gpt-image-2`.
+- `--prompt-file`, `--output-compression`, `--moderation`, `--max-attempts`, `--fail-fast`, `--force`, and `--no-augment` are supported.
+- This CLI is intended for GPT Image models. Do not assume older non-GPT image-model behavior applies here.
+
+## See also
+- API parameter quick reference for fallback CLI mode: `references/image-api.md`
+- Prompt examples shared across both top-level modes: `references/sample-prompts.md`
+- Network/sandbox notes for fallback CLI mode: `references/codex-network.md`
+- Built-in-first transparent image workflow: `SKILL.md` and `$CODEX_HOME/skills/.system/imagegen/scripts/remove_chroma_key.py`

package/resources/local/codex/skills/.system/imagegen/references/codex-network.md

@@ -0,0 +1,33 @@
+# Codex network approvals / sandbox notes
+
+This file is for the fallback CLI mode only. Read it when the user explicitly asks to use `scripts/image_gen.py` / CLI / API / model controls, or after the user explicitly confirms that a transparent-output request should use the `gpt-image-1.5` true-transparency fallback path.
+
+This guidance is intentionally isolated from `SKILL.md` because it can vary by environment and may become stale. Prefer the defaults in your environment when in doubt.
+
+## Why am I asked to approve image generation calls?
+The fallback CLI uses the OpenAI Image API, so it needs outbound network access. In many Codex setups, network access is disabled by default and/or the approval policy requires confirmation before networked commands run.
+
+## Important note about approvals vs network
+- `--ask-for-approval never` suppresses approval prompts.
+- It does **not** by itself enable network access.
+- In `workspace-write`, network access still depends on your Codex configuration (for example `[sandbox_workspace_write] network_access = true`).
+
+## How do I reduce repeated approval prompts?
+If you trust the repo and want fewer prompts, use a configuration or profile that both:
+- enables network for the sandbox mode you plan to use
+- sets an approval policy that matches your risk tolerance
+
+Example `~/.codex/config.toml` pattern:
+
+```toml
+approval_policy = "on-request"
+sandbox_mode = "workspace-write"
+
+[sandbox_workspace_write]
+network_access = true
+```
+
+If you want quieter automation after network is enabled, you can choose a stricter approval policy, but do that intentionally and with care.
+
+## Safety note
+Enabling network and reducing approvals lowers friction, but increases risk if you run untrusted code or work in an untrusted repository.