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 agentmods add skills/tmcfarlane/oh-my-cursor/cursor-image-generationnpx skills add tmcfarlane/oh-my-cursor --skill cursor-image-generationgit clone --depth 1 https://github.com/tmcfarlane/oh-my-cursorWrote 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/tmcfarlane/oh-my-cursor/cursor-image-generation)<a href="https://agentmods.dev/skills/tmcfarlane/oh-my-cursor/cursor-image-generation"><img src="https://agentmods.dev/badge/skills/tmcfarlane/oh-my-cursor/cursor-image-generation.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.01674 |
| Opus 5 | $0.00024 | $0.00837 |
| Sonnet 5 | $0.00010 | $0.00335 |
| Haiku 4.5 | $0.00005 | $0.00167 |
Grade A, and why
cursor-image-generation 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 5d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor image generation (Nano Banana Pro)
Generate images in the Cursor agent using the GenerateImage tool. Image generation is backed by Google Nano Banana Pro. Previews are saved under assets/ by default unless you specify otherwise.
This skill is about prompting and workflow, not about replacing Figma or vector code (use other skills for those).
Rough prompt in, strong prompt out
The user may give a short or vague request (“a hero for the login page”, “cyberpunk icon”). Do not pass that string raw to GenerateImage when it lacks the layers this skill describes. Instead:
- Infer or ask for missing constraints (medium, aspect ratio, style, brand colors, text to render).
- Rewrite the ask into one structured prompt (or a tight second pass) using the principles below.
- Call GenerateImage with the rewritten prompt only.
The skill is the contract: the agent’s job is to expand and sharpen the user’s intent before generation, then iterate with deltas.
When to use this skill
- User asks for an image, icon, hero visual, diagram look, mockup still, or iteration on an existing generated image.
- You need text in the image (titles, labels, buttons in a mockup).
- User uploads a reference image and wants a variation or edit-style direction.
Core principles (Nano Banana / Gemini image family)
The bullets below are a condensed synthesis of common guidance for Nano Banana Pro / Gemini image models — not verbatim quotes. For authoritative wording and edge cases, use the References below.
They align with the spirit of Google’s public guides (prompt tips, Google Cloud guide, DeepMind prompt guide):
- Brief a human artist — Use clear, grammatical sentences. Avoid keyword soup (
"cyber, 4k, hdr, epic") unless you deliberately want a tag-like aesthetic. - Layer the description — Subject → action/pose → environment → camera (wide shot, isometric, macro) → lighting (soft window light, neon rim, overcast) → materials (brushed aluminum, matte paper, glass) → style (editorial photo, flat illustration, low-poly 3D render).
- Text in images — Put exact wording in double quotes and specify typography feel (e.g.
"bold geometric sans","narrow serif for headlines"). Ask for legibility and high contrast if the text is important. - Aspect ratio and framing — State orientation (square, 16:9 landscape, 9:16 story) and safe margins if the asset will be cropped (e.g. app icon: centered subject, padding).
- Edit, don't always re-roll — If the image is roughly right, ask for specific changes (
"change the background to warm beige","make the logo 20% larger","remove the extra person on the left") instead of a full new prompt. - Reference images — When the user supplies a reference, describe what to keep (palette, mood, composition) and what to change so the model does not drift.
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.
- 5d ago First seen · 100 lines · 48 tokens per session scan A 93a5f622d2d7
cursor-image-generation is a skill published in the GitHub repository tmcfarlane/oh-my-cursor (108 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,674 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…