Image Agent - Multi-Vendor Image Router

Scheduling

Goal

Generate images and visual assets through authenticated multi-vendor routing while preserving prompt clarity, reference-guided regeneration, cost controls, and reproducible output manifests.

Intent signature

• User asks to generate images, visual assets, illustrations, product photos, concept art, mockups, or AI art.
• Another skill needs shared image-generation infrastructure.
• User provides reference images for a new generated variation or asks for vendor comparison.

When to use

• Generating images, visual assets, illustrations, product photos, concept art
• Comparing output between multiple image models for the same prompt
• Producing images from prompts within editor workflows (Claude Code, Codex, Gemini CLI)
• Other skills needing image generation infrastructure (shared invocation)
• Regenerating a new image that follows a supplied reference's subject, style, lighting, or composition

When NOT to use

• Pixel-level editing, masking, inpainting, object removal, compositing, cropping, resizing, or format conversion -> out of scope; use an image editor or a tool that explicitly supports that operation.
• Generating videos or audio -> out of scope
• Inline vector art / SVG composition from structured data -> use a templating skill
• Simple asset resizing or format conversion -> use a dedicated image library

Expected inputs

• Image prompt or creative brief
• Optional vendor, size, quality, count, output directory, and reference images
• Authentication/environment state for Codex, Pollinations, or Gemini

Expected outputs

• Generated image files under .agents/results/images/ or requested output directory
• manifest.json with prompt, vendor, model, and reproducibility metadata
• Vendor comparison outputs when --vendor all is used

Dependencies

• oma image generate CLI and vendor authentication
• Codex image generation, Pollinations API, or Gemini API/CLI strategy
• resources/vendor-matrix.md, resources/prompt-tips.md, and the image: section of .agents/oma-config.yaml

Control-flow features

• Branches by prompt ambiguity, vendor auth, cost threshold, reference-guided regeneration support, path safety, and safety/timeout exit codes
• Calls external vendor APIs/CLIs
• Reads reference images and writes generated images plus manifests

Structural Flow

Entry

1. Validate that the request contains enough subject, setting, style, usage, and aspect-ratio signal.
2. Classify a supplied image as a reference for a newly generated variation, or as a request for unsupported pixel/mask editing.
3. Check authentication, cost guardrails, output path, and count limits.

Scenes

1. PREPARE: Clarify or amplify prompt and choose vendor strategy.
2. ACQUIRE: Validate auth, references, output path, and provider availability.
3. ACT: Invoke oma image generate with selected vendor(s), prompt, references, and options.
4. VERIFY: Check manifest, output files, exit code, and provider result.
5. FINALIZE: Return output paths and relevant warnings.

Transitions

• If prompt lacks required signal, clarify or show amplified prompt before generation.
• If --vendor all is requested, require every requested vendor to be available.
• If the request is reference-guided regeneration and the selected vendor supports references, pass it automatically.
• If the request requires pixel, mask, crop, resize, or format editing, stop before generation and name the unsupported operation and an appropriate editor route.
• If estimated cost exceeds guardrail, require confirmation unless bypassed.

Failure and recovery

• If auth is missing, report vendor-specific authentication requirement.
• If reference support is unavailable for the selected vendor, reject with actionable guidance.
• If local CLI is outdated, ask user to run oma update.
• If generation times out or is blocked, surface exit code and provider status.

Exit

• Success: images and manifest exist in the output directory.
• Partial success: some vendors fail in comparison mode and failures are reported.
• Failure: no image is produced and the route/cost/auth/safety blocker is explicit.

Logical Operations

Actions

Tools and instruments

• oma image generate, oma image doctor, oma image vendor list
• Codex, Pollinations, and Gemini provider paths
• Prompt tips, vendor matrix, and image config

Canonical command path

oma image doctor
oma image generate "<prompt>" --vendor auto --size auto --quality auto --output json

With reference images:

oma image generate --reference "<absolute-path>" --vendor codex "<prompt>"

Resource scope

Preconditions

• Prompt is sufficiently specified or user approves amplification.
• Required vendor auth and output permissions exist.
• Reference paths are accessible when used.

Effects and side effects

• Creates image files and manifests.
• May call paid or rate-limited provider APIs.
• May read attached/reference images.

Guardrails

1. Clarify before invoking: if the user's request is ambiguous about subject, style, composition, or usage context, ask the user first or amplify the prompt explicitly (showing the user the expanded version for approval). Do NOT silently generate from a vague prompt. See Clarification Protocol below.
2. Authentication-aware dispatch: detect which vendor CLIs are available and run only those; with --vendor all, every requested vendor must be available (strict). Caveat: the antigravity health check verifies installation only (agy --version) — a signed-out agy passes health and fails at generate time with agy's own error.
3. Cost guardrail: confirm before executing runs whose estimated cost is ≥ $0.20 (configurable). --yes / OMA_IMAGE_YES=1 bypass. Default vendors pollinations (flux/zimage) and antigravity (nano-banana via Gemini Code Assist) are free, so auto-triggering on keywords is safe. Non-interactive contexts (agents, CI — no TTY on stdin): the CLI cannot prompt, so a run at/over the threshold exits 1 with a message naming --yes. Calling agents must confirm the estimated cost with the user in-conversation (use --dry-run to get the estimate), then re-run with -y.
4. Path safety: output paths outside $PWD require --allow-external-out.
5. Cancellable: SIGINT/SIGTERM aborts in-flight provider calls and the orchestrator.
6. Deterministic outputs: every run writes manifest.json next to the images for reproducibility.
7. Max n = 5: wall-time bound.
8. Exit codes align with oma search fetch (0, 1, 2=safety, 3=not-found, 4=invalid-input, 5=auth-required, 6=timeout).

Clarification Protocol

Before invoking oma image generate, the calling agent runs this checklist against the user's request. If any answer is "no / unknown", clarify with the user first.

Required signal (must be present or inferable):

• Subject: what is the primary thing in the image? (object, person, scene)
• Setting / backdrop: where is it? (context, environment)

Strongly recommended (ask if absent AND not inferable from context):

• Style: photorealistic, illustration, 3D render, oil painting, concept art, flat vector, …?
• Mood / lighting: bright vs moody, warm vs cool, dramatic vs minimal
• Usage context: hero image, icon, thumbnail, product shot, poster? (dictates aspect ratio + composition)
• Aspect ratio / resolution: any WxH where each edge is a multiple of 16 between 16 and 3840 and aspect ∈ [1:3, 3:1] (e.g. 1024x1024 square, 2048x1152 16:9, 3840x2160 4K UHD, 1024x1536 portrait), or auto.

Amplification shortcut. For brief prompts (e.g. "a red apple"), do not pop clarifying questions if the request is genuinely that simple. Instead amplify inline and show the user the expanded version before invoking:

User: "a red apple" Agent: "I'll generate this as: a single glossy red apple centered on a clean white background, soft studio lighting, photorealistic, shallow depth of field, 1024×1024. Shall I proceed, or would you like a different style/composition?"

Skip both clarification and amplification when the user has clearly authored a full creative brief (≥ 2 of: subject + style + lighting + composition). Respect their prompt verbatim.

Category-specific briefs (app mockup, poster, thumbnail, infographic, comic panel, avatar): consult resources/prompt-tips.md → External Prompt Libraries.

Output language. Generation prompts are sent to the provider in English (image models are trained predominantly on English captions). Translate the user's request if they wrote in another language, and show them the translated version during amplification so they can correct misreadings.

Vendors

This skill follows oh-my-agent's CLI-first concept: whenever a vendor's native CLI can drive generation (and return raw bytes), the subprocess path is preferred over direct API keys. Direct API is only used as a fallback for vendors whose CLI can't yet emit raw image bytes.

The direct Gemini path (gemini -p stream, generativelanguage.googleapis.com API) is deprecated. agy is the supported Gemini image route — it's free with Gemini Code Assist and doesn't require billing on AI Studio.

Invocation

Standalone

/oma-image a red apple on white background
/oma-image --vendor all --size 1536x1024 jeju coastline at sunset
/oma-image -n 3 --quality high --out ./hero "minimalist dashboard hero illustration"

Shell CLI

oma image generate "<prompt>" [--vendor auto|codex|pollinations|antigravity|all] [-n 1..5] \
                             [--size WxH|auto] \
                             [--quality low|medium|high|auto] \
                             [--model <name>] \
                             [--output-dir <dir>] [--allow-external-output] \
                             [-r <path>]... \
                             [--timeout 180] [-y] [--no-prompt-in-manifest] \
                             [--dry-run] [--output text|json]
oma image doctor
oma image vendor list

--model <name> overrides the vendor's default model for this run — e.g. --vendor pollinations --model zimage, or a credit-gated Pollinations model like gpt-image-2. It applies to every vendor in the run set, so combine it with an explicit --vendor; antigravity ignores it (agy picks its model internally).

Reference-guided regeneration (-r, --reference)

Attach up to 10 reference images (PNG/JPEG/GIF/WebP, ≤ 5MB each) to guide a newly generated image's style, subject identity, lighting, or composition. Repeatable or comma-separated. The output is a new generation, not a pixel-preserving edit of the input.

oma image generate -r ~/Downloads/otter.jpeg "same otter in dramatic lighting"
oma image generate -r a.png -r b.png "blend these two styles"

Supported vendors:

Paths: absolute or relative to $CWD. Host CLIs usually expose attached images via:

• Claude Code: ~/.claude/image-cache/<session>/N.png (surfaced in system messages as [Image: source: <path>])
• Antigravity: workspace upload directory (exact path shown in IDE)
• Codex CLI as host: user must pass the filesystem path explicitly; in-conversation attachments are not forwarded

Agent Behavior: Auto-forward Attached References (MANDATORY)

When ALL of the following are true, the calling agent MUST pass the attached image via --reference <path> automatically. Never describe the image in prose as a workaround.

1. The user asks for a new generated variation (for example, "same subject in dramatic lighting", "make a new illustration in this style", or "regenerate this at a different angle").
2. A host-surfaced attached image is visible to the agent (e.g. a Claude Code system message with [Image: source: <path>], or an Antigravity workspace upload path, or an explicit filesystem path in the user's message).
3. The selected vendor supports references (codex or antigravity).

Required action: invoke oma image generate --reference <absolute-path> --vendor <codex|antigravity> "<prompt>". If the user didn't specify a vendor, default to codex (CLI-first, widest availability). Do NOT:

• Fall back to prose description ("I'll describe the otter's appearance...").
• Ask the user to re-type or re-attach the path.
• Claim the CLI doesn't support references without first running oma image generate --help to verify.

If the local CLI is outdated (--reference is missing from --help): tell the user to run oma update once, then retry. Do not silently degrade to prose.

If the reference path is from Claude Code's image-cache: note to the user that the path is session-scoped and suggest copying the file to a durable location if they want to reuse it later. Still proceed with the generation.

Unsupported edit requests: Do not route requests such as "remove this object", "change only the background", "paint inside this mask", "keep every pixel except", "crop", "resize", or "convert this file" through --reference. They need pixel/mask editing or deterministic image processing, neither of which this CLI provides. Say whether the request can instead be phrased as a reference-guided regeneration; otherwise route to an appropriate image editor or processing tool.

Shared Infrastructure (from other skills)

Other skills call oma image generate --output json and parse the JSON manifest from stdout.

Output Layout

Filenames follow <vendor>[-<model>]-<shortid>[-<n>].<ext> — the model segment is omitted for antigravity (opaque model), the extension reflects the sniffed format (JPEG is common), and -<n> appears only when -n > 1.

.agents/results/images/
├── 20260424-143052-ab12cd/                    # single-vendor run
│   ├── pollinations-flux-ab12cd.jpg
│   │   (or codex-gpt-image-2-ab12cd.png, antigravity-ab12cd.jpg)
│   └── manifest.json
└── 20260424-143122-7z9kqw-compare/            # --vendor all run
    ├── codex-gpt-image-2-7z9kqw.png
    ├── pollinations-flux-7z9kqw.jpg
    ├── antigravity-7z9kqw.jpg
    └── manifest.json

References

Configuration

Project-specific settings: the image: section of .agents/oma-config.yaml, which oma update preserves. Shipped defaults live in the CLI (DEFAULTS in cli/commands/image/config.ts) — write only the keys you change. The legacy config/image-config.yaml is no longer read by the CLI; migration 022 moves anything you had changed there into oma-config (and deletes the file when it was never edited). Env vars: OMA_IMAGE_DEFAULT_VENDOR, OMA_IMAGE_DEFAULT_OUT, OMA_IMAGE_YES, POLLINATIONS_API_KEY.

• Execution steps (follow for the selected task): resources/execution-protocol.md
• Vendor matrix: resources/vendor-matrix.md
• Prompt tips: resources/prompt-tips.md
• Checklist (run before handoff): resources/checklist.md
• Context loading: ../_shared/core/context-loading.md