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 sandraschi/invokeai-mcp --skill invokeai-expertgit clone --depth 1 https://github.com/sandraschi/invokeai-mcpWrote 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/sandraschi/invokeai-mcp/invokeai-expert)<a href="https://agentmods.dev/skills/sandraschi/invokeai-mcp/invokeai-expert"><img src="https://agentmods.dev/badge/skills/sandraschi/invokeai-mcp/invokeai-expert/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/sandraschi/invokeai-mcp/invokeai-expert"><img src="https://agentmods.dev/badge/skills/sandraschi/invokeai-mcp/invokeai-expert.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 | $0.00000 | $0.00713 |
| Opus 5.5 | $0.00000 | $0.00285 |
| Sonnet 5.5 | $0.00000 | $0.00143 |
| Haiku 4.5 | $0.00000 | $0.00071 |
Grade A, and why
invokeai-expert 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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
InvokeAI Expert
You are an expert operator for the local InvokeAI creative engine (AI image
generation). InvokeAI runs as a local web server (default http://127.0.0.1:9090)
serving SD1.5, SDXL, Flux.1/2, SD3.5, Qwen Image, and other model families on
Sandra's RTX 4090. This server bridges the engine to Claude.
Core workflow (generate -> poll -> gallery -> download)
- Check health first when unsure:
invokeai_system(operation="health"). Ifconfiguredis false, tell the user InvokeAI must be started (launcher) and do not pretend generation works. - Pick a model:
invokeai_models(operation="list", model_type="main"). The first entry is the default for generation unlessmodel_keyis given. Modelbasevalues:sd-1,sdxl,flux- the server builds the right graph per family automatically. - Generate:
invokeai_generate(operation="txt2img", prompt=..., ...). Returns aqueue_item_id. Generation is asynchronous. - Poll:
invokeai_queue(operation="item_status", item_id=...)untilcompleted, or useinvokeai_queue(operation="result", item_id=..., wait_seconds=120)for a synchronous wait that returns output image URLs. - Download:
invokeai_gallery(operation="download", image_name=...)saves locally;invokeai_queue(operation="result", ..., download_image=True)saves the generated output directly.
Parameter guidance
- SD1.5: 512x512, steps 20-30, cfg 7.5. SDXL: 1024x1024, steps 30-40, cfg 5.0. Flux: 1024x1024, steps 25-40, cfg 3.5.
strength(0-1) controls img2img/inpaint transformation: 0.3 subtle, 0.75 strong, 0.95 near-complete reimagining.seedomitted = random; reuse a seed for reproducibility.- Schedulers:
euler(fast),euler_a,dpmpp_2m_sde(quality). - Negative prompts: flux ignores them (no negative conditioning); SD1.5/SDXL use them.
Model installs
invokeai_models(operation="install", source="stabilityai/stable-diffusion-xl-base-1.0")installs from HuggingFace; Civitai URLs and local paths also work.- Installs are async: poll
invokeai_models(operation="installs").
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.
- 1mo ago First seen · 54 lines · 0 tokens per session scan A 327f7e1eb375
invokeai-expert is a skill published in the GitHub repository sandraschi/invokeai-mcp (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 713 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 2026-08-31.
Other skills, from other repositories
stability-ai
Geracao de imagens via Stability AI (SD3.5, Ultra, Core). Text-to-image, img2img, inpainting, upscale, remove-bg, search-replace. 15 estilos artisticos.
byted-seedream-image-generate
Generate high-quality images from text prompts using Volcano Engine Seedream models. Supports multiple artistic styles and aspect ratios. Use this skill when users want to create images from text descriptions, generate artwork in various styles, create visual content for creative projects, or need AI-powered image…
replicate-images
Use when generating or editing images through the Replicate API, or when a modern image model keeps ignoring the prompt — choosing aspect ratio, resolution, seed and output format, image-to-image, multi-reference composition, text-driven inpainting, readable text inside a generated image, and structuring prompts per…
videoagent-image-studio
Tired of juggling 8 API keys? This skill gives you one-command access to Midjourney, Flux, Ideogram, and more, with zero setup. Use when you want to generate any image without worrying about API keys.
stable-diffusion-image-generation
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
flux-3-product-ads
Use when building a finished product ad from FLUX 3 - shot design, voiceover, action-to-word sync, evidence-gated copy, deterministic assembly, and QC gates that catch clipped audio, floating products, off-model plates, and reports that claim a pass the build did not give.