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 agentmods add skills/kivo360/omoios/agent-browsernpx skills add kivo360/OmoiOS --skill agent-browsergit clone --depth 1 https://github.com/kivo360/OmoiOSWrote 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/kivo360/omoios/agent-browser)<a href="https://agentmods.dev/skills/kivo360/omoios/agent-browser"><img src="https://agentmods.dev/badge/skills/kivo360/omoios/agent-browser.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.01720 |
| Opus 5 | $0.00035 | $0.00860 |
| Sonnet 5 | $0.00014 | $0.00344 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
agent-browser 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 6d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-browser
CLI browser automation optimized for AI. Use refs from snapshots for reliable element selection. 93% less context than Playwright MCP, 95% first-try success rate.
Core Workflow
agent-browser open <url> # Navigate
agent-browser snapshot -i # Get interactive elements with refs
agent-browser click @e2 # Click by ref
agent-browser fill @e3 "text" # Fill by ref
agent-browser snapshot -i # Re-snapshot after changes
agent-browser close # Close browser
Snapshot (Most Important)
Get accessibility tree with element refs for deterministic selection:
agent-browser snapshot # Full tree
agent-browser snapshot -i # Interactive only (buttons, inputs, links)
agent-browser snapshot -c # Compact (no empty elements)
agent-browser snapshot -d 3 # Limit depth
agent-browser snapshot -i -c --json # Combine for AI parsing
Output example:
- heading "Example Domain" [ref=e1]
- button "Submit" [ref=e2]
- textbox "Email" [ref=e3]
Use refs with @ prefix: agent-browser click @e2
Essential Commands
Navigation
agent-browser open <url> # Go to URL
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
Interaction
agent-browser click @ref # Click element
agent-browser fill @ref "text" # Clear and fill input
agent-browser type @ref "text" # Type into element
agent-browser press Enter # Press key
agent-browser select @ref "value" # Select dropdown option
agent-browser check @ref # Check checkbox
agent-browser hover @ref # Hover element
agent-browser scroll down 500 # Scroll (up/down/left/right)
Get Info
agent-browser get text @ref # Get text content
agent-browser get value @ref # Get input value
agent-browser get title # Page title
agent-browser get url # Current URL
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.
- 6d ago First seen · 241 lines · 70 tokens per session scan A 02fba5979738
agent-browser is a skill published in the GitHub repository kivo360/OmoiOS (76 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,720 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
playwriter
Browser automation via Playwriter (remorses) using persistent Chrome sessions and the full Playwright Page API.