@olives/devos 2.1.0

package/.agents/skills/imagegen/SKILL.md

@@ -0,0 +1,279 @@
+---
+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 and editing. Does not require `OPENAI_API_KEY`.
+- **Fallback CLI mode (explicit-only):** `scripts/image_gen.py` CLI. Use only when the user explicitly asks for the CLI path. Requires `OPENAI_API_KEY`.
+
+Within the explicit CLI fallback only, the CLI exposes three subcommands:
+
+- `generate`
+- `edit`
+- `generate-batch`
+
+Rules:
+- Use the built-in `image_gen` tool by default for all normal image generation and editing requests.
+- Never switch to CLI fallback automatically.
+- 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`
+
+## 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 explicit CLI fallback path, use the CLI `generate-batch` subcommand only when the user explicitly chose CLI mode and needs many prompts/assets.
+
+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, fallback CLI only if explicitly requested.
+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. If the user explicitly chooses the CLI fallback, then and only then use the fallback-only docs for quality, `input_fidelity`, masks, output format, output paths, and network setup.
+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, persist only the selected finals in the workspace unless the user explicitly asked to keep discarded variants.
+17. Always report the final saved path for any workspace-bound asset, plus the final prompt and whether the built-in tool or fallback CLI mode was used.
+
+## 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.
+- 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.
+- 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 explicit 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 explicit CLI fallback only, see `references/cli.md` and `references/image-api.md` for `quality`, `input_fidelity`, masks, output format, and output-path guidance.
+
+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`.
+
+## Fallback CLI mode only
+
+### Temp and output conventions
+These conventions apply only to the explicit 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
+```
+
+Optional for downscaling only:
+```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.

package/.agents/skills/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: "Generate or edit the visual assets for this task with the built-in `image_gen` tool by default. First confirm that the task actually calls for a raster image; if the project already has SVG/vector/code-native assets and the user wants to extend or match those, do not use this skill. If the task includes reference images, treat them as references unless the user clearly wants an existing image modified. For multi-asset requests, loop built-in calls rather than treating batch as a separate top-level mode. Only use the fallback CLI if the user explicitly asks for it, and keep CLI-only controls such as `generate-batch`, `quality`, `input_fidelity`, masks, and output paths on that fallback path."

package/.agents/skills/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/.agents/skills/imagegen/references/cli.md

@@ -0,0 +1,160 @@
+# CLI reference (`scripts/image_gen.py`)
+
+This file is for the fallback CLI mode only. Read it only after the user explicitly asks to use `scripts/image_gen.py` instead of the built-in `image_gen` tool.
+
+`generate-batch` is a CLI subcommand in this fallback path. It is not a top-level mode of the skill.
+
+## 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
+
+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 "$IMAGE_GEN" ...`) after activating the correct environment.
+- Do **not** create one-off runners (for example `gen_images.py`) unless the user explicitly asks for a custom wrapper.
+- **Never modify** `scripts/image_gen.py`. If something is missing, ask the user before doing anything else.
+
+## Defaults
+- Model: `gpt-image-1.5`
+- Supported model family for this CLI: GPT Image models (`gpt-image-*`)
+- Size: `1024x1024`
+- Quality: `auto`
+- Output format: `png`
+- Default one-off output path: `output/imagegen/output.png`
+- Background: unspecified unless `--background` is set
+
+## Quality, input fidelity, and masks (CLI fallback only)
+These are explicit CLI controls. They are not built-in `image_gen` tool arguments.
+
+- `--quality` works for `generate`, `edit`, and `generate-batch`: `low|medium|high|auto`
+- `--input-fidelity` is **edit-only** and validated as `low|high`
+- `--mask` is **edit-only**
+
+Example:
+
+```bash
+python "$IMAGE_GEN" edit \
+  --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`.
+- 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`.
+
+## CLI notes
+- Supported sizes: `1024x1024`, `1536x1024`, `1024x1536`, or `auto`.
+- Transparent backgrounds require `output_format` to be `png` or `webp`.
+- `--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`

package/.agents/skills/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 only after the user explicitly asks to use `scripts/image_gen.py`.
+
+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.

package/.agents/skills/imagegen/references/image-api.md

@@ -0,0 +1,49 @@
+# Image API quick reference
+
+This file is for the fallback CLI mode only. Use it only after the user explicitly asks to use `scripts/image_gen.py` instead of the built-in `image_gen` tool.
+
+These parameters describe the Image API and bundled CLI fallback surface. Do not assume they are normal arguments on the built-in `image_gen` tool.
+
+## Scope
+- This fallback CLI is intended for GPT Image models (`gpt-image-1.5`, `gpt-image-1`, and `gpt-image-1-mini`).
+- The built-in `image_gen` tool and the fallback CLI do not expose the same controls.
+
+## Endpoints
+- Generate: `POST /v1/images/generations` (`client.images.generate(...)`)
+- Edit: `POST /v1/images/edits` (`client.images.edit(...)`)
+
+## Core parameters for GPT Image models
+- `prompt`: text prompt
+- `model`: image model
+- `n`: number of images (1-10)
+- `size`: `1024x1024`, `1536x1024`, `1024x1536`, or `auto`
+- `quality`: `low`, `medium`, `high`, or `auto`
+- `background`: output transparency behavior (`transparent`, `opaque`, or `auto`) for generated output; this is not the same thing as the prompt's visual scene/backdrop
+- `output_format`: `png` (default), `jpeg`, `webp`
+- `output_compression`: 0-100 (jpeg/webp only)
+- `moderation`: `auto` (default) or `low`
+
+## Edit-specific parameters
+- `image`: one or more input images. For GPT Image models, you can provide up to 16 images.
+- `mask`: optional mask image
+- `input_fidelity`: `low` (default) or `high`
+
+Model-specific note for `input_fidelity`:
+- `gpt-image-1` and `gpt-image-1-mini` preserve all input images, but the first image gets richer textures and finer details.
+- `gpt-image-1.5` preserves the first 5 input images with higher fidelity.
+
+## Output
+- `data[]` list with `b64_json` per image
+- The bundled `scripts/image_gen.py` CLI decodes `b64_json` and writes output files for you.
+
+## Limits and notes
+- Input images and masks must be under 50MB.
+- Use the edits endpoint when the user requests changes to an existing image.
+- Masking is prompt-guided; exact shapes are not guaranteed.
+- Large sizes and high quality increase latency and cost.
+- High `input_fidelity` can materially increase input token usage.
+- If a request fails because a specific option is unsupported by the selected GPT Image model, retry manually without that option.
+
+## Important boundary
+- `quality`, `input_fidelity`, explicit masks, `background`, `output_format`, and related parameters are fallback-only execution controls.
+- Do not assume they are built-in `image_gen` tool arguments.

package/.agents/skills/imagegen/references/prompting.md

@@ -0,0 +1,98 @@
+# Prompting best practices
+
+These prompting principles are shared by both top-level modes of the skill:
+- built-in `image_gen` tool (default)
+- explicit `scripts/image_gen.py` CLI fallback
+
+This file is about prompt structure, specificity, and iteration. Fallback-only execution controls such as `quality`, `input_fidelity`, masks, output format, and output paths live in the fallback docs.
+
+## Contents
+- [Structure](#structure)
+- [Specificity policy](#specificity-policy)
+- [Allowed and disallowed augmentation](#allowed-and-disallowed-augmentation)
+- [Composition and layout](#composition-and-layout)
+- [Constraints and invariants](#constraints-and-invariants)
+- [Text in images](#text-in-images)
+- [Input images and references](#input-images-and-references)
+- [Iterate deliberately](#iterate-deliberately)
+- [Fallback-only execution controls](#fallback-only-execution-controls)
+- [Use-case tips](#use-case-tips)
+- [Where to find copy/paste recipes](#where-to-find-copypaste-recipes)
+
+## Structure
+- Use a consistent order: scene/backdrop -> subject -> key details -> constraints -> output intent.
+- Include intended use (ad, UI mock, infographic) to set the level of polish.
+- For complex requests, use short labeled lines instead of one long paragraph.
+
+## Specificity policy
+- If the user prompt is already specific and detailed, normalize it into a clean spec without adding creative requirements.
+- If the prompt is generic, you may add tasteful detail when it materially improves the output.
+- Treat examples in `sample-prompts.md` as fully-authored recipes, not as the default amount of augmentation to add to every request.
+
+## Allowed and disallowed augmentation
+
+Allowed augmentation for generic prompts:
+- composition and framing cues
+- intended-use or polish-level hints
+- practical layout guidance
+- reasonable scene concreteness that supports the request
+
+Do not add:
+- extra characters, props, or objects that are not implied
+- brand palettes, slogans, or story beats that are not implied
+- arbitrary side-specific placement unless the surrounding layout supports it
+
+## Composition and layout
+- Specify framing and viewpoint (close-up, wide, top-down) and placement only when it materially helps.
+- Call out negative space if the asset clearly needs room for UI or copy.
+- Avoid making left/right layout decisions unless the user or surrounding layout supports them.
+
+## Constraints and invariants
+- State what must not change (`keep background unchanged`).
+- For edits, say `change only X; keep Y unchanged` and repeat invariants on every iteration to reduce drift.
+
+## Text in images
+- Put literal text in quotes or ALL CAPS and specify typography (font style, size, color, placement).
+- Spell uncommon words letter-by-letter if accuracy matters.
+- For in-image copy, require verbatim rendering and no extra characters.
+
+## Input images and references
+- Do not assume that every provided image is an edit target.
+- Label each image by index and role (`Image 1: edit target`, `Image 2: style reference`).
+- If the user provides images for style, composition, or mood guidance and does not ask to modify them, treat the request as generation with references.
+- If the user asks to preserve an existing image while changing specific parts, treat the request as an edit.
+- For compositing, describe how the images interact (`place the subject from Image 2 into Image 1`).
+
+## Iterate deliberately
+- Start with a clean base prompt, then make small single-change edits.
+- Re-specify critical constraints when you iterate.
+- Prefer one targeted follow-up at a time over rewriting the whole prompt.
+
+## Fallback-only execution controls
+- `quality`, `input_fidelity`, explicit masks, output format, and output paths are fallback-only execution controls.
+- Do not assume they are built-in `image_gen` tool arguments.
+- If the user explicitly chooses CLI fallback, see `references/cli.md` and `references/image-api.md` for those controls.
+
+## Use-case tips
+Generate:
+- photorealistic-natural: Prompt as if a real photo is captured in the moment; use photography language (lens, lighting, framing); call for real texture; avoid over-stylized polish unless requested.
+- product-mockup: Describe the product/packaging and materials; ensure clean silhouette and label clarity; if in-image text is needed, require verbatim rendering and specify typography.
+- ui-mockup: Describe the target fidelity first (shippable mockup or low-fi wireframe), then focus on layout, hierarchy, and practical UI elements; avoid concept-art language.
+- infographic-diagram: Define the audience and layout flow; label parts explicitly; require verbatim text.
+- logo-brand: Keep it simple and scalable; ask for a strong silhouette and balanced negative space; avoid decorative flourishes unless requested.
+- illustration-story: Define panels or scene beats; keep each action concrete.
+- stylized-concept: Specify style cues, material finish, and rendering approach (3D, painterly, clay) without inventing new story elements.
+- historical-scene: State the location/date and required period accuracy; constrain clothing, props, and environment to match the era.
+
+Edit:
+- text-localization: Change only the text; preserve layout, typography, spacing, and hierarchy; no extra words or reflow unless needed.
+- identity-preserve: Lock identity (face, body, pose, hair, expression); change only the specified elements; match lighting and shadows.
+- precise-object-edit: Specify exactly what to remove/replace; preserve surrounding texture and lighting; keep everything else unchanged.
+- lighting-weather: Change only environmental conditions (light, shadows, atmosphere, precipitation); keep geometry, framing, and subject identity.
+- background-extraction: Request a clean cutout; crisp silhouette; no halos; preserve label text exactly; no restyling.
+- style-transfer: Specify style cues to preserve (palette, texture, brushwork) and what must change; add `no extra elements` to prevent drift.
+- compositing: Reference inputs by index; specify what moves where; match lighting, perspective, and scale; keep the base framing unchanged.
+- sketch-to-render: Preserve layout, proportions, and perspective; choose materials and lighting that support the supplied sketch without adding new elements.
+
+## Where to find copy/paste recipes
+For copy/paste prompt specs (examples only), see `references/sample-prompts.md`. This file focuses on principles, specificity, and iteration patterns.