sandbox-agent is an HTTP and server-sent-events service that runs coding agents inside isolated sandboxes and lets another application control them remotely. Developers use it to run agents such as Claude Code, Codex, OpenCode, Cursor, Amp, or Pi while streaming events, managing sessions, and storing transcripts. The catalogue entries provide agents, skills, commands, instructions, and MCP integration for working with the service.
Borrowing it
Nothing to install: this file belongs to rivet-dev/sandbox-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rivet-dev/sandbox-agent/main/.agents/skills/agent-browser/SKILL.mdgit clone --depth 1 https://github.com/rivet-dev/sandbox-agentWrote 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/rivet-dev/sandbox-agent/agent-browser)<a href="https://agentmods.dev/skills/rivet-dev/sandbox-agent/agent-browser"><img src="https://agentmods.dev/badge/skills/rivet-dev/sandbox-agent/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/rivet-dev/sandbox-agent/agent-browser"><img src="https://agentmods.dev/badge/skills/rivet-dev/sandbox-agent/agent-browser.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 | $0.00108 | $0.04600 |
| Opus 5.5 | $0.00043 | $0.01840 |
| Sonnet 5.5 | $0.00022 | $0.00920 |
| Haiku 4.5 | $0.00011 | $0.00460 |
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.
This is a copy
77% identical to agent-browser — 142 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with agent-browser
Core Workflow
Every browser automation follows this pattern:
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(get element refs like@e1,@e2) - Interact: Use refs to click, fill, select
- Re-snapshot: After navigation or DOM changes, get fresh refs
agent-browser open https://example.com/form
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"
agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i # Check result
Command Chaining
Commands can be chained with && in a single shell invocation. The browser persists between commands via a background daemon, so chaining is safe and more efficient than separate calls.
# Chain open + wait + snapshot in one call
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i
# Chain multiple interactions
agent-browser fill @e1 "[email protected]" && agent-browser fill @e2 "password123" && agent-browser click @e3
# Navigate and capture
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png
When to chain: Use && when you don't need to read the output of an intermediate command before proceeding (e.g., open + wait + screenshot). Run commands separately when you need to parse the output first (e.g., snapshot to discover refs, then interact using those refs).
Essential Commands
# Navigation
agent-browser open <url> # Navigate (aliases: goto, navigate)
agent-browser close # Close browser
# Snapshot
agent-browser snapshot -i # Interactive elements with refs (recommended)
agent-browser snapshot -i -C # Include cursor-interactive elements (divs with onclick, cursor:pointer)
agent-browser snapshot -s "#selector" # Scope to CSS selector
# Interaction (use @refs from snapshot)
agent-browser click @e1 # Click element
agent-browser click @e1 --new-tab # Click and open in new tab
agent-browser fill @e2 "text" # Clear and type text
agent-browser type @e2 "text" # Type without clearing
agent-browser select @e1 "option" # Select dropdown option
agent-browser check @e1 # Check checkbox
agent-browser press Enter # Press key
agent-browser keyboard type "text" # Type at current focus (no selector)
agent-browser keyboard inserttext "text" # Insert without key events
agent-browser scroll down 500 # Scroll page
agent-browser scroll down 500 --selector "div.content" # Scroll within a specific container
# Get information
agent-browser get text @e1 # Get element text
agent-browser get url # Get current URL
agent-browser get title # Get page title
# Wait
agent-browser wait @e1 # Wait for element
agent-browser wait --load networkidle # Wait for network idle
agent-browser wait --url "**/page" # Wait for URL pattern
agent-browser wait 2000 # Wait milliseconds
# Downloads
agent-browser download @e1 ./file.pdf # Click element to trigger download
agent-browser wait --download ./output.zip # Wait for any download to complete
agent-browser --download-path ./downloads open <url> # Set default download directory
# Capture
agent-browser screenshot # Screenshot to temp dir
agent-browser screenshot --full # Full page screenshot
agent-browser screenshot --annotate # Annotated screenshot with numbered element labels
agent-browser pdf output.pdf # Save as PDF
# Diff (compare page states)
agent-browser diff snapshot # Compare current vs last snapshot
agent-browser diff snapshot --baseline before.txt # Compare current vs saved file
agent-browser diff screenshot --baseline before.png # Visual pixel diff
agent-browser diff url <url1> <url2> # Compare two pages
agent-browser diff url <url1> <url2> --wait-until networkidle # Custom wait strategy
agent-browser diff url <url1> <url2> --selector "#main" # Scope to element
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 4.9 KB
- references/proxy-support.md 4.9 KB
- references/session-management.md 4.2 KB
- references/snapshot-refs.md 4.2 KB
- references/video-recording.md 3.5 KB
- templates/authenticated-session.sh 3.6 KB runs code
- templates/capture-workflow.sh 1.8 KB runs code
- templates/form-automation.sh 1.8 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 · 540 lines · 108 tokens per session scan A 6472477cf348
agent-browser is a skill published in the GitHub repository rivet-dev/sandbox-agent (1,609 stars, last pushed 13d ago), licensed Apache-2.0. It adds 108 tokens to every session and 4,600 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 77% identical to agent-browser, differing in 142 lines, and is treated as a copy.
Other skills, from other repositories
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
browser_cdp
Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default browser opens no debugging port; pass an explicit cdpport only when the user wants another local tool to attach.
browser_cdp
Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.
browser_visible
Browser launch controls for choosing whether a Chromium-based browser window is visible, which browser program to run, and which startup options to pass.
browser_visible
Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…
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…