Omnara is an open-source platform for running managed AI agents, handling their execution and state while developers choose the models, tools, machines, and user experience. Developers use it to build internal or customer-facing agent applications, while teams can interact with agents through its dashboard or Slack connector. The catalogue skill supports workflows built around Omnara.
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 omnara-ai/omnara --skill browser-agentgit clone --depth 1 https://github.com/omnara-ai/omnaraWrote 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/omnara-ai/omnara/browser-agent)<a href="https://agentmods.dev/skills/omnara-ai/omnara/browser-agent"><img src="https://agentmods.dev/badge/skills/omnara-ai/omnara/browser-agent/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/omnara-ai/omnara/browser-agent"><img src="https://agentmods.dev/badge/skills/omnara-ai/omnara/browser-agent.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 | $0.00077 | $0.03952 |
| Opus 5.5 | $0.00031 | $0.01581 |
| Sonnet 5.5 | $0.00015 | $0.00790 |
| Haiku 4.5 | $0.00008 | $0.00395 |
Grade A, and why
browser-agent 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 2d 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build the Browser Agent
You are building an Omnara agent with the user, starting from agent.yaml in
this folder. The result: an agent profile that does the user's work in their
web apps, has signed in to each account once while the user watched, and is
reachable where they want it, on a schedule if they want one.
Interview first, then build. Don't create anything in Omnara until the user has confirmed your summary in step 2. When a step says to ask the user, ask in plain language, then end your turn and wait for their reply. Where a step gives a default, use it without asking and say in a line what you picked, so the user can change it.
agent.yaml is a guide, not a form. Its browser, sign-in, and machine settings
were tested together: the agent-browser commands, the vault and two-factor
helper in the startup script, the AGENT_BROWSER_* variables, and the settings
that keep the machine alive. Keep them unless you have a reason, and read the
file's comments before editing. Fit everything else to the job: add instruction
sections, an MCP server for an API the user already has, or anything else the
job needs, and tell the user what you changed. If a command fails,
npx omnara <command> --help and docs.omnara.com
have the details.
The commands use the Omnara CLI (npx omnara); add --json when you need to
read IDs. The Omnara MCP tools, the
REST API, and the SDK
work too, and the flags map directly to API fields.
1. Connect to Omnara
Run npx omnara whoami. If you aren't logged in, run npx omnara login without
piping its output, and keep it running: it waits until the user approves. It
opens the approval page in the user's browser and prints the page's link and a
code. Show the user both right away, since you may be on a different machine
than their browser, and ask them to approve once the code matches. If the
request expires, run it again. If login says the account has no organization
yet, have the user create one at the link it prints. Then npx omnara whoami
should succeed.
What ships with it
2 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.
- 2d ago Changed · -102 lines 17f4750777bd
- 7d ago Changed · +77 lines · +2 tokens per session 76c95988549c
- 8d ago First seen · 334 lines · 75 tokens per session scan A c4a71801e868
browser-agent is a skill published in the GitHub repository omnara-ai/omnara (2,920 stars, last pushed today), licensed Apache-2.0. It adds 77 tokens to every session and 3,952 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-08.
Other skills, from other repositories
browser-use
System prompt for an AI agent with Browser Use browser automation and Inkbox email. Drop this into your agent loop to get browser automation and email tools out of the box.
kernel
System prompt for an AI agent with a Kernel cloud browser and Inkbox email. Drop this into your agent loop to get browser automation and email tools out of the box.
webcrawler-deep-crawl
Deep-crawl any website from start URLs, return per-page LLM-ready text/markdown/HTML plus metadata (title, description, author, language, canonical URL, OG) and in-scope outbound links. Use when user mentions deep crawl website, recursive crawl, crawl a whole site, scrape entire website, scrape docs site, scrape…
amazon-search-listing
Amazon search and category listing scraper: extract product listings from any Amazon search results page, keyword search URL, or category browse page and return per-item cards (asin, title, url, image, price, listPrice, stars, reviewCount, badges, isAmazonChoice, isBestSeller, isSponsored, delivery, boughtInPast…
ebay-search-listing
Extracts product listings from any eBay search or category page URL, returning per-item cards (itemNumber, url, title, subtitle, caption, price, priceWithCurrency, currency, wasPrice, bids, shipping, seller, sellerFeedbackCount, sellerPositiveRating, reviewsCount, starRating, image) plus pagination state (currentPage…
etsy-product-detail
Etsy product detail scraper: given an Etsy listing URL, returns full product detail including listingId, title, priceCurrent, priceOriginal, currency, images (all), description, shopName, shopUrl, rating, reviewCount, favorites, inCartCount, variations (with per-option price ranges), highlights, listedDate…