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 stevenke1981/coart --skill coart-image-gengit clone --depth 1 https://github.com/stevenke1981/coartWrote 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/stevenke1981/coart/coart-image-gen)<a href="https://agentmods.dev/skills/stevenke1981/coart/coart-image-gen"><img src="https://agentmods.dev/badge/skills/stevenke1981/coart/coart-image-gen/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/stevenke1981/coart/coart-image-gen"><img src="https://agentmods.dev/badge/skills/stevenke1981/coart/coart-image-gen.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 | $0.00024 | $0.00398 |
| Opus 5 | $0.00012 | $0.00199 |
| Sonnet 5 | $0.00005 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
coart-image-gen 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 12d 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
Coart Image Generation
Workflow
- Call
get_coart_pending_requestwhen the user says "繼續處理" after using the standalone editor; otherwise callget_coart_selectionfor the active project. - When exactly one selected shape has
meta.coartKind: "ai-image", treat itsprops.wandprops.has the generation contract. - Generate the bitmap with the available image generation capability. The prompt must state target width, height, and aspect ratio.
- Resolve the exact local output image created for this request. Never reuse an older unrelated generated file.
- When the user is asking to update an existing image shape, call
update_coart_imageso its shape, position, and display size remain stable:
{
"projectDir": "<active-project>",
"imagePath": "<exact-local-generated-image>",
"shapeId": "<selected-image-shape-id>"
}
For an AI image holder or a new image, call insert_coart_image:
{
"projectDir": "<active-project>",
"imagePath": "<exact-local-generated-image>",
"anchorShapeId": "<selected-holder-id>",
"replaceHolder": true
}
- When no AI image holder is selected, still generate and insert a standalone image. Use the current page and selected shape as placement context.
- Keep the original selected image and annotations when the request is an annotation-led revision; insert the new result beside them instead of replacing them.
- After handling a queued standalone request, call
clear_coart_pending_requestwith its request id. - Report the updated or inserted
shapeId, asset path, dimensions, and replaced holder id when applicable.
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.
- 12d ago First seen · 39 lines · 24 tokens per session scan A a985bad7386d
coart-image-gen is a skill published in the GitHub repository stevenke1981/coart (1 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 398 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 2026-08-31.
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…