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.
/plugin marketplace add huggingface/diffusersnpx agentmods add plugins/huggingface/diffusers/marketplacegit clone --depth 1 https://github.com/huggingface/diffusersGrade A, and why
diffusers-skills 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 yesterday.
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
{
"name": "diffusers-skills",
"description": "Agent plugins published from the diffusers repository",
"owner": {
"name": "The Hugging Face team"
},
"plugins": [
{
"name": "diffusers",
"source": "./.ai",
"description": "Conventions and task skills for contributing to diffusers"
}
]
}
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.
- yesterday First seen · 15 lines scan A 00c8e093dfc1
diffusers-skills is a plugin published in the GitHub repository huggingface/diffusers (34,407 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
illo-skill
Original editorial illustrations where a recurring mascot performs the idea — fourteen bundled looks, custom characters via a built-in character builder, palettes derived from your own site's colors. Ships the illo Agent Skill and its three-backend image engine: free generation through your Codex or Grok CLI…
runapi
RunAPI model discovery, pricing lookup, media task creation, polling, and balance checks for Claude Code.
codex-image
Generate and edit images from Claude Code by dispatching to Codex CLI's built-in imagegen skill.
higgsfield-brief-to-pipeline
Credit-aware orchestration for Higgsfield generative image/video batches — plan first, approve an HTML gate, then render with auto-verification.
higgsfield-brief-to-pipeline
Turns a brief plus a folder of reference images into an optimal, credit-aware Higgsfield pipeline. Shows an HTML process preview as a mandatory approval gate before spending any credits, then executes stage-by-stage with auto-verification, human gates, and zero-credit deterministic text/dimension overlays.
openrouter-genimage-kote
Generate new images and edit existing images through OpenRouter directly from Claude Code.