Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/agent-browser
Browser automation CLI for AI agents.
Passed 18 of 23 test cases with the skill, and 9 of 23 without it.
and 8 more in the full report
11 fixed9 passed either way4 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
To avoid context flooding when capturing DOM accessibility snapshots in agent-browser, rather than piping stdout through shell tools like head or cut, what environment variable caps the tool's maximum output character count to 50000?
| Checked | Without skill | With skill |
|---|---|---|
| Sets AGENT_BROWSER_MAX_OUTPUT to 50000 | Missed | Passed |
The instructions your model reads when the skill loads.
### Domain Allowlist
Restrict navigation to trusted domains. Wildcards like `*.example.com` also match the bare domain `example.com`. Sub-resource requests, WebSocket, and EventSource connections to non-allowed domains are also blocked. Include CDN domains your target pages depend on:
```bash
export AGENT_BROWSER_ALLOWED_DOMAINS="example.com,*.example.com"
agent-browser open https://example.com # OK
agent-browser open https://malicious.com # Blocked
Use a policy file to gate destructive actions:
export AGENT_BROWSER_ACTION_POLICY=./policy.json
Example policy.json:
{"default": "deny", "allow": ["navigate", "snapshot", "click", "scroll", "wait", "get"]}
Auth vault operations (auth login, etc.) bypass action policy but domain allowlist still applies.
Prevent context flooding from large pages:
export AGENT_BROWSER_MAX_OUTPUT=50000
Use diff snapshot after performing an action to verify it had the intended effect. This compares the current accessibility tree against the last snapshot taken in the session.
test cases passed, vs 9 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.