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 air-gapped/skillsnpx agentmods add plugins/air-gapped/skills/open-webuigit clone --depth 1 https://github.com/air-gapped/skillsWrote 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/plugins/air-gapped/skills/open-webui)<a href="https://agentmods.dev/plugins/air-gapped/skills/open-webui"><img src="https://agentmods.dev/badge/plugins/air-gapped/skills/open-webui.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
open-webui 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": "open-webui",
"source": "./",
"description": "Open WebUI operator suite — REST API administration (v0.10.x: user/group lifecycle, model catalog GitOps via models/sync, config-as-code, SCIM, event webhooks, the 0.10.0 access_control→access_grants break, auth traps), RAG pipeline wiring (HuggingFace embedding + reranker via LiteLLM in front of HuggingFace Text Embeddings Inference; exact wire shapes, LiteLLM ↔ TEI gotchas, TEI configuration cliffs, end-to-end production config; BGE-M3 + BGE-Reranker-v2-m3 worked examples) and multi-pod deployment with WebSockets + Valkey Sentinel at 1000+ user scale (the structural Socket.IO + Redis frame-amplification bug #23733 and the CHAT_RESPONSE_STREAM_DELTA_CHUNK_SIZE mitigation, all multi-pod env vars, custom-model-icon perf history, helm chart gaps, full known-issues catalog with fix status).",
"version": "0.20260819.31",
"author": {
"name": "Jörgen"
},
"license": "MIT",
"skills": [
"./.claude/skills/open-webui-api",
"./.claude/skills/open-webui-embeddings",
"./.claude/skills/open-webui-valkey-websocket"
],
"strict": false,
"category": "ai-workflow",
"tags": [
"open-webui",
"rest-api",
"administration",
"scim",
"gitops",
"rag",
"embeddings",
"reranker",
"litellm",
"tei",
"huggingface",
"bge-m3",
"websocket",
"valkey",
"redis",
"sentinel",
"multi-pod",
"kubernetes",
"socket-io",
"scaling"
]
}What it installs
The manifest is a name and a version. 3 skills travel with it, and installing the plugin installs all of them — 474 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside marketplace.json#open-webui in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 39 lines scan A ba6029bc98aa
open-webui is a plugin published in the GitHub repository air-gapped/skills (5 stars, last pushed 3d ago), licensed MIT. 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 2026-09-03.
Other plugins, from other repositories
rag-core
Document indexing and hybrid retrieval with heading-boundary chunking, FAISS vector store, and PageIndex tree filtering.
rag-reviewer
Agentic PR review: hybrid RAG + code graph via MCP, review skills for Claude Code.
veritasreason
Full-stack knowledge graph skills: semantic extraction, decision intelligence, context graphs, reasoning, explainability, ontology, provenance, deduplication, visualization, and multi-format export.
graph-source
Connect a property graph (knowledge graph, GraphRAG corpus, Apache AGE / openCypher data) to Skardi and query it through SQL, end to end: provision the AGE backend with a least-privilege role, declare the type: graph source and its views in context YAML, verify registration health, write correct queries (cypherquery.
Claude Dev Assistant marketplace
An intelligent development workflow featuring Socratic interviewing, dual-agent debate, expert team coordination, and RAG system design. Built on Claude Code for seamless AI-assisted development.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.