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 naveedharri/benai-skills --skill install-openwebuigit clone --depth 1 https://github.com/naveedharri/benai-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/skills/naveedharri/benai-skills/install-openwebui)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/install-openwebui"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/install-openwebui/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/naveedharri/benai-skills/install-openwebui"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/install-openwebui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00152 | $0.01058 |
| Opus 5 | $0.00076 | $0.00529 |
| Sonnet 5 | $0.00030 | $0.00212 |
| Haiku 4.5 | $0.00015 | $0.00106 |
Grade A, and why
install-openwebui 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 5d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Open WebUI
Turns the most technical local AI option into the easiest one. Ends with a working chat in the browser, not a list of commands.
Before you start
Run the check in references/environment-check.md first. These skills need a shell on the user's own machine. If the environment is a sandbox or container, stop and tell the user to run this in Claude Code on the computer they want to set up. Do not report detected specs from a sandbox: wrong specs are worse than none.
Steps
Track progress:
Task Progress:
- [ ] 1. Check what is already there
- [ ] 2. Get consent, with sizes
- [ ] 3. Install and start
- [ ] 4. Wire the connection
- [ ] 5. Prove it works
- [ ] 6. Render the handover report
1. Check what is already there
Run the preflight block in references/install-steps.md. Establish: is Ollama installed and running, which models are pulled, is Open WebUI installed, is anything already on port 8080. Never install something that is already present.
If the user already ran /scan-my-machine, reuse that result instead of re-detecting.
2. Get consent, with sizes
Before installing or downloading anything, tell the user in one message: what will be installed, the download size in gigabytes, and roughly how long it will take. Then stop and wait for a yes.
Never skip this. A silent multi-gigabyte download is the single worst failure mode for this skill.
3. Install and start
Follow references/install-steps.md in order: Ollama, then a model chosen for their hardware, then Open WebUI, then start the server. Run the server detached so it survives the session. Report the log path.
4. Wire the connection
Set the Ollama connection to http://localhost:11434. Read the "Which URL goes where" section of references/install-steps.md before touching any connection setting, because the two ports are easy to swap and the failure is silent.
5. Prove it works
Send one real prompt through the stack and show the reply. Do not report success on an HTTP 200 alone. Then give the user the URL and stop.
What ships with it
4 files beside SKILL.md 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.
- 5d ago First seen · 76 lines · 152 tokens per session scan A a0be4d236de1
install-openwebui is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed 6d ago), licensed MIT. It adds 152 tokens to every session and 1,058 once invoked, about $0.0008 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 2026-09-05.
Other skills, from other repositories
ai-prompting-basics
A practical guide to writing clearer requests for Claude, an AI assistant, by adding context, examples, roles, and output rules.
openrouter-models
Choose among the hosted models the shared router serves — discover current ids and prices from the public catalog, self-enforce a spend budget the router does not meter for you, respect the free-tier prompt-logging caveat, and request onboarding of a model the router does not serve yet.
llm-router-ops
Operate a self-hosted OpenAI-compatible LLM router/proxy (e.g. LiteLLM) in front of one or more backends — the minimal client-wiring block for every client type, the context-window advertisement gotcha, the env-vs-persisted-config gotcha, and why an unauthenticated health probe should 401, not 200. Use when wiring a…
scan-releases
Scan official AI release notes, changelogs, and deprecation pages, then flag what affects the user's stack and recommend an action for each item. Trigger on requests like "what AI releases happened recently," "check if my models or tools are deprecated," "any changelog updates that affect my stack," or periodic…
daily-ai-brief
Run the AI-news crew (scout, analyst, editor) to sweep the field with web search and ship a ranked briefing. Trigger when the user asks for an AI news brief, a daily or weekly AI roundup, "what shipped in AI", a model-release recap, or wants the standing cadence run.
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.