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 IceWhaleTech/ZimaOS-Blue --skill mediagengit clone --depth 1 https://github.com/IceWhaleTech/ZimaOS-BlueWrote 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/icewhaletech/zimaos-blue/mediagen)<a href="https://agentmods.dev/skills/icewhaletech/zimaos-blue/mediagen"><img src="https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/mediagen/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/icewhaletech/zimaos-blue/mediagen"><img src="https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/mediagen.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 | $0.00043 | $0.00770 |
| Opus 5 | $0.00022 | $0.00385 |
| Sonnet 5 | $0.00009 | $0.00154 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
mediagen 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 11d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media Generation
Generate images and videos through the built-in media pipeline.
Setup
No external dependencies are required for the CLI surface itself. Availability still depends on configured media providers or enabled fallback engines in the running system.
Task Routing
| User Intent | Action |
|---|---|
| Explicitly generate an image or video from a prompt | blue media generate "..." --category ... |
| Check whether a submitted media task has finished | blue media status <task_id> |
| User wants image creation in normal chat and no special control is needed | The chat runtime may auto-route some image-generation intents directly to the media pipeline |
| User wants screenshot critique, accessibility review, or visual QA | Use research with mode=ui_review, not mediagen |
| User wants generic web/image search rather than generation | Use web_query or the built-in browser tool, not mediagen |
Command Usage
Generate media:
blue media generate "Draw a cat on a rainbow" --category t2i
blue media generate "Create a video of waves crashing at sunset" --category t2v
blue media generate "Animate this product photo" --category i2v --model <model>
blue media generate "Restyle this image as a watercolor painting" --category i2i --poll
Check status:
blue media status media-task-1
blue media status media-task-1 --json
Useful flags:
--category t2i|t2v|i2v|i2i--model <model>--size <width>x<height>--poll--poll-interval <seconds>
Supported Categories
| Category | Meaning |
|---|---|
t2i |
Text to image |
t2v |
Text to video |
i2v |
Image to video |
i2i |
Image editing or transformation |
Error Handling
| Error | Resolution |
|---|---|
| No provider available for the requested category/model | Check provider configuration or retry with a different category/model |
| Task remains pending/processing | Use blue media status <task_id> or --poll until completion |
| Generation failed or returned no results | Retry with a simpler prompt, different model, or different category |
| User asks for image review instead of generation | Route to research with mode=ui_review |
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.
- 11d ago First seen · 95 lines · 43 tokens per session scan A 994cadec54e8
mediagen is a skill published in the GitHub repository IceWhaleTech/ZimaOS-Blue (25 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 770 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
shortfilm-prompt
A five-part method for writing prompts for AI-generated videos, such as Sora or Seedance. It organizes each prompt into the subject, setting, visual style, camera movement, and timed shots with sound.
json-canvas
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
youtube-full
Use when YouTube is or could be relevant — even if not mentioned: pasted video/channel/playlist links, video IDs, @handles, creator lookups, video summaries, quotes, translations, topic research, tutorials, talks, lectures, expert discussions, product reviews, how-to guides, new product announcements, first looks, or…
captions
Use when captions, subtitles, or the spoken text of a YouTube video is needed — even if not explicitly requested: pasted video links or IDs, requests to read, quote, or translate a video, accessibility needs, deaf/HoH use cases, content review, or language learning. Fetches timestamped caption data from any YouTube…
video-transcript
Use when video content needs to be extracted as text: pasted YouTube links or IDs, requests to transcribe, summarize, quote, translate, convert video to text, or extract information from video content. Also use when a user shares a video URL without explanation and wants to know what it says. Not for uploads or…
design_creator
Structured workflow for creating professional designs — slide decks, documents, landing pages, app mockups, and motion storyboards.