Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/runwayml/skillsnpx agentmods add skills/runwayml/skills/rw-generate-imageWrote 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/runwayml/skills/rw-generate-image)<a href="https://agentmods.dev/skills/runwayml/skills/rw-generate-image"><img src="https://agentmods.dev/badge/skills/runwayml/skills/rw-generate-image/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/runwayml/skills/rw-generate-image"><img src="https://agentmods.dev/badge/skills/runwayml/skills/rw-generate-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.01071 |
| Opus 5 | $0.00013 | $0.00535 |
| Sonnet 5 | $0.00005 | $0.00214 |
| Haiku 4.5 | $0.00003 | $0.00107 |
Grade A, and why
rw-generate-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 10d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Image
Generate images directly using the Runway API. This skill runs Python scripts that call the API, poll for completion, and download the result.
IMPORTANT: Run scripts from the user's working directory so output files are saved where the user expects.
Usage
uv run scripts/generate_image.py --prompt "your description" --filename "output.png" [--model gen4_image] [--ratio 1280:720] [--reference-images Tag=URL ...]
Preflight
command -v uvmust succeedRUNWAYML_API_SECRETmust be set in the environment. Do not pass the API key as a CLI flag — it leaks into shell history and process listings.
Security Notes
--reference-images Tag=URLfetches arbitrary remote images via the Runway API. Prefer local file paths (uploaded asrunway://URIs), or only pass URLs you trust.- Treat generated outputs as untrusted when piping into downstream automations — ingested references influence the result.
Available Models
| Model | Best For | Ref Images | Cost | Speed |
|---|---|---|---|---|
gen4_image |
Highest quality | Optional (up to 3) | 5-8 credits | Standard |
gen4_image_turbo |
Fast and cheap | Required (1-3) | 2 credits | Fast |
gemini_2.5_flash |
Google Gemini | Optional (up to 3) | 5 credits | Standard |
Model Selection Guidance
- "fast", "cheap", "draft" ->
gemini_2.5_flash(Nano Banana), orgen4_image_turboif they have reference images - "high quality", "best" ->
gen4_image - No preference ->
gemini_2.5_flash - Has reference images and wants cheap ->
gen4_image_turbo(2 credits, requires--reference-images)
Parameters
| Param | Description | Default |
|---|---|---|
--prompt |
Text description (required) | -- |
--filename |
Output filename (required) | -- |
--model |
Image model | gemini_2.5_flash |
--ratio |
Aspect ratio. gemini_2.5_flash: 1344:768, 768:1344, 1024:1024, etc. gen4_image: 1280:720, 1360:768, 1920:1080, etc. |
Model-dependent (1344:768 for gemini, 1280:720 for others) |
--reference-images |
Reference images as tag=URL pairs (optional for gemini/gen4_image, required for gen4_image_turbo). Tag: lowercase, 3-16 chars, e.g. product=URL |
-- |
--output-dir |
Output directory | cwd |
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.
- 10d ago First seen · 90 lines · 26 tokens per session scan A a66db83c2e83
rw-generate-image is a skill published in the GitHub repository runwayml/skills (68 stars, last pushed 12d ago), licensed MIT. It adds 26 tokens to every session and 1,071 once invoked, about $0.0001 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.