Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add iurysza/android-use --skill chatgpt-imagegengit clone --depth 1 https://github.com/iurysza/android-useWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/iurysza/android-use/chatgpt-imagegen)<a href="https://agentmods.dev/skills/iurysza/android-use/chatgpt-imagegen"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/chatgpt-imagegen/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/iurysza/android-use/chatgpt-imagegen"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/chatgpt-imagegen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00706 |
| Opus 5.5 | $0.00016 | $0.00282 |
| Sonnet 5.5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
chatgpt-imagegen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChatGPT Image Generation
Use the bundled chatgpt-img CLI for generation and edits. Resolve its path relative to this SKILL.md.
Setup
python3 -m pip install -r <skill-directory>/requirements.txt
export OPENAI_API_KEY='...'
OPENCODE_OPENAI_API_KEY is accepted as a fallback. CHATGPT_IMAGE_DEFAULT overrides the default model.
Image requests cost money. Confirm scope before generating many images or using high quality repeatedly.
Generate
<skill-directory>/scripts/chatgpt-img \
'A linocut illustration of a lighthouse in heavy rain' \
./lighthouse.png \
--size 1536x1024 \
--quality high
Edit
Single reference:
<skill-directory>/scripts/chatgpt-img edit \
./portrait.png \
'Use warm editorial lighting; preserve identity, pose, and clothing' \
./portrait-edited.png \
--quality high
Multiple references:
<skill-directory>/scripts/chatgpt-img \
--input ./portrait.png \
--input ./moodboard.png \
'Apply the moodboard lighting and palette while preserving the portrait identity' \
./portrait-styled.png
Optional masked edit:
<skill-directory>/scripts/chatgpt-img edit \
./input.png \
'Replace the masked background with a cloudy coastline' \
./output.png \
--mask ./mask.png
Important options
--model: defaults togpt-image-2--size: supported dimensions orauto--quality: GPT Image usesauto,low,medium, orhigh--background:auto,transparent, oropaque--format:png,jpeg, orwebp--compression:0through100for JPEG/WebP--num: number of outputs--input: repeatable reference image for edit mode--mask: optional edit mask--input-fidelity: supported by selected older GPT Image models, notgpt-image-2
Use --help and edit --help for the complete interface.
Prompting edits
State both the change and the invariants. For example, name the identity, geometry, text, logos, pose, camera angle, or materials that must remain unchanged. Describe lighting, palette, composition, and finish positively instead of relying on long negative lists.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 93 lines · 41 tokens per session scan A a4df84c29256
chatgpt-imagegen is a skill published in the GitHub repository iurysza/android-use (21 stars, last pushed 16d ago), licensed MIT. It adds 41 tokens to every session and 706 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-15.
Other skills, from other repositories
babysit
Use when a user asks to babysit, monitor, keep checking, keep an eye on, or report when a pull request, CI run, ticket, deployment, or other changing target reaches an outcome.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
browser-qa
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
code-review
Reviewing code for defects: diff-first reading, severity classification, evidence over inference, finding caps, and terminal verdicts. Use when reviewing a diff, PR, or patch, or auditing someone else's work.