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 commands/tmcfarlane/oh-my-cursor/imagegit clone --depth 1 https://github.com/tmcfarlane/oh-my-cursorWhat 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 | $0.00000 | $0.00252 |
| Opus 5 | $0.00000 | $0.00126 |
| Sonnet 5 | $0.00000 | $0.00050 |
| Haiku 4.5 | $0.00000 | $0.00025 |
Grade A, and why
image 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 2d 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.
What it actually says
Use Zuko (the visual specialist agent) with the cursor-image-generation skill for this task.
- Read the cursor-image-generation skill (
skills/cursor-image-generation/SKILL.md) and follow its workflow: expand a rough user brief into a full prompt before calling GenerateImage (layered prompts, iteration). - Clarify only what is blocking (asset type, aspect ratio, brand colors, reference image) if the user’s message is too vague to rewrite safely.
- Rewrite the ask into a strong prompt per the skill, then generate with the GenerateImage tool; save under
assets/(or the path the user requested) with descriptive filenames. - Iterate with targeted edits per the skill — do not re-roll the full prompt unless the direction is wrong.
- Return paths to saved files, the final prompt (or a clear summary), and optional next iterations.
If the task is implementation of a Figma file or code for UI, also use Zuko’s implementing-figma-designs or web-design-guidelines as appropriate.
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.
- 2d ago First seen · 10 lines · 0 tokens per session scan A 0a16cff7ce51
image is a command published in the GitHub repository tmcfarlane/oh-my-cursor (108 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 252 tokens. 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 commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
stt
Transcribe a local audio file or remote audio URL into text.
audition-voices
Generate voice audition samples for a character using Venice TTS.
review-video
Make a " Reviews" video — a fast, faceless VO montage of REAL, verified competitor reviews that names the recurring complaints and positions YOUR business as the alternative, then hands off to your own customer testimonials.
search
Search videos by text, image, or entity using TwelveLabs.
transcribe
Transcribe the file at $ARGUMENTS into Markdown using the Frenchie MCP server.