Open Agents is an open-source reference application for running background coding agents through a web interface, durable workflows, isolated Vercel sandboxes, and GitHub integration. Developers fork and adapt it to let agents make code changes without keeping a local computer running. The catalogue entries provide skills, agents, and instructions for its workflow.
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 vercel-labs/open-agents --skill agent-browsergit clone --depth 1 https://github.com/vercel-labs/open-agentsWrote 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/vercel-labs/open-agents/agent-browser)<a href="https://agentmods.dev/skills/vercel-labs/open-agents/agent-browser"><img src="https://agentmods.dev/badge/skills/vercel-labs/open-agents/agent-browser/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/vercel-labs/open-agents/agent-browser"><img src="https://agentmods.dev/badge/skills/vercel-labs/open-agents/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 15 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Rogue Agent · line 283 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00051 | $0.02864 |
| Opus 5.5 | $0.00020 | $0.01146 |
| Sonnet 5.5 | $0.00010 | $0.00573 |
| Haiku 4.5 | $0.00005 | $0.00286 |
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 1mo 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.
Copies of this mod
4 near-identical copies found in the catalogue:
- agent-browser — 100% identical, 0 lines differ
- agent-browser — 100% identical, 0 lines differ
- agent-browser — 100% identical, 0 lines differ
- agent-browser — 95% identical, 1 lines differ
How it starts
The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with agent-browser
Quick start
agent-browser open <url> # Navigate to page
agent-browser snapshot -i # Get interactive elements with refs
agent-browser click @e1 # Click element by ref
agent-browser fill @e2 "text" # Fill input by ref
agent-browser close # Close browser
Core workflow
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(returns elements with refs like@e1,@e2) - Interact using refs from the snapshot
- Re-snapshot after navigation or significant DOM changes
Commands
Navigation
agent-browser open <url> # Navigate to URL (aliases: goto, navigate)
# Supports: https://, http://, file://, about:, data://
# Auto-prepends https:// if no protocol given
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
agent-browser close # Close browser (aliases: quit, exit)
agent-browser connect 9222 # Connect to browser via CDP port
Snapshot (page analysis)
agent-browser snapshot # Full accessibility tree
agent-browser snapshot -i # Interactive elements only (recommended)
agent-browser snapshot -c # Compact output
agent-browser snapshot -d 3 # Limit depth to 3
agent-browser snapshot -s "#main" # Scope to CSS selector
Interactions (use @refs from snapshot)
agent-browser click @e1 # Click
agent-browser dblclick @e1 # Double-click
agent-browser focus @e1 # Focus element
agent-browser fill @e2 "text" # Clear and type
agent-browser type @e2 "text" # Type without clearing
agent-browser press Enter # Press key (alias: key)
agent-browser press Control+a # Key combination
agent-browser keydown Shift # Hold key down
agent-browser keyup Shift # Release key
agent-browser hover @e1 # Hover
agent-browser check @e1 # Check checkbox
agent-browser uncheck @e1 # Uncheck checkbox
agent-browser select @e1 "value" # Select dropdown option
agent-browser select @e1 "a" "b" # Select multiple options
agent-browser scroll down 500 # Scroll page (default: down 300px)
agent-browser scrollintoview @e1 # Scroll element into view (alias: scrollinto)
agent-browser drag @e1 @e2 # Drag and drop
agent-browser upload @e1 file.pdf # Upload files
What ships with it
8 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.
- references/authentication.md 4.3 KB
- references/proxy-support.md 4.2 KB
- references/session-management.md 3.8 KB
- references/snapshot-refs.md 4.0 KB
- references/video-recording.md 4.3 KB
- templates/authenticated-session.sh 4.1 KB runs code
- templates/capture-workflow.sh 1.9 KB runs code
- templates/form-automation.sh 1.6 KB runs code
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.
- 1mo ago First seen · 357 lines · 51 tokens per session scan A 9caba4d013da
agent-browser is a skill published in the GitHub repository vercel-labs/open-agents (5,856 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 2,864 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
computer-use
Read and drive native desktop apps through the accessibility layer — list apps, snapshot a window as a numbered element tree, then click/type/scroll/drag by element index or screen coordinates. Use for a desktop app, not a web page. macOS + Windows; off unless enabled in Settings.
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
browser-auth
Browse sites that need a logged-in session with playwright-cli, using attach mode, saved storage state, or individual cookies. Use when a page is behind a login wall and a plain open lands on a sign-in screen.
browser-recording
Record a browser flow as video/GIF evidence for animations, transitions and multi-step interactions a still screenshot cannot prove. Uses the project's Playwright via a bundled runner, then ffmpeg to mp4 + GIF. Use when asked to record a demo or GIF, or when a UI change involves motion.
web-browse
Open a REAL external web page in Kiro Crew's Browser panel. Primary path is the browser MCP tool (native panel); playwright-cli is the fallback for remote/plain-browser sessions and attached logged-in browsers. Use when the user wants to VIEW or verify a public URL (dev server = web-preview).
web-verify
Use after a user-visible UI edit to verify your OWN change on an isolated loopback server. Capture, read and show real screenshots. Backends: playwright-cli (live Browser panel), agent-browser (annotated frames, pixel diff, a11y), or scripted Playwright. Not web-preview or external-page web-browse.