Browser4 is an AI-native browser engine that lets autonomous agents and people control real browsers, extract information from web pages, and automate tasks at scale. It combines browser interaction through a Rust CLI and MCP with deterministic selectors, machine-learning clustering, and language-model extraction. The catalogue entries provide skills and instructions for using Browser4.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/platonai/Browser4npx agentmods add skills/platonai/browser4/test-productionWrote 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/platonai/browser4/test-production)<a href="https://agentmods.dev/skills/platonai/browser4/test-production"><img src="https://agentmods.dev/badge/skills/platonai/browser4/test-production/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/platonai/browser4/test-production"><img src="https://agentmods.dev/badge/skills/platonai/browser4/test-production.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Rogue Agent · line 71 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 | $0.00044 | $0.01269 |
| Opus 5.5 | $0.00018 | $0.00508 |
| Sonnet 5.5 | $0.00009 | $0.00254 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
test-production 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.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Production
Runs bin/test-production.ps1 — an acceptance test that simulates a real end
user's journey with the published browser4-cli release. It downloads,
installs, exercises, uninstalls, and re-installs the global CLI from the public
OSS distribution channel.
This is a separate entrypoint from bin/test.ps1 (covered by the run-tests
skill). test-production.ps1 tests the released artifact — not the
in-repo source — and is designed to be run in CI or locally before tagging a
release.
When to Use
- "run production tests"
- "run the production acceptance test"
- "acceptance-test the latest release"
- "test the published CLI"
- "verify the release before tagging"
- "test a prerelease candidate"
- "run production acceptance with stress"
Safe Default
Running with no arguments shows help (safe default):
./bin/test-production.ps1
Options
| Flag | Description |
|---|---|
-WorkingDir <path> |
Working directory for temporary artifacts (default: random subdir under system temp) |
-Stress |
Enable the multi-scenario stress suite (opt-in) |
-MultiScenariosIterations <n> |
Iterations for the multi-scenario suite (default: 1, only with -Stress) |
-RemoveWorkingDir |
Delete the working directory on exit (default: preserved for review) |
-Version <tag> |
Test a specific release version (e.g. v4.12.0-rc.1, v4.11.0). Default: latest stable |
-Help |
Show help message |
What It Tests
- Release status report — queries GitHub Releases, npm registry, Aliyun OSS CDN, and custom mirrors to verify all distribution channels are reachable.
- Pre-clean — removes any existing global browser4-cli installation.
- Cycle 1 — Clean-room install (no pre-existing config):
- Installs the CLI via the remote bootstrap script (unmodified — no patches).
- Verifies the CLI is on PATH after install.
- Smoke-tests:
--help,--version,config --help,agent-run --help, invalid command. - Cold-starts the browser server (
open), verifies health endpoint responds. - Shuts down the server (
close-all,kill-all), verifies it's unreachable. - Uninstalls and verifies runtime data is removed.
- Cycle 2 — Re-install with config + timing:
- Copies config (LLM keys, etc.) from the user's real
~/.browser4into the test sandbox. - Repeats the install→exercise→uninstall cycle.
- Measures warm-start latency vs cold-start.
- Copies config (LLM keys, etc.) from the user's real
- (With
-Stress) Multi-scenarios stress test — runsbrowser4-tests/tests-production/multi-scenarios.ps1against the global CLI.
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 · 135 lines · 44 tokens per session scan A 7292f1eef31c
test-production is a skill published in the GitHub repository platonai/Browser4 (1,161 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 1,269 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 2026-08-30.
Other skills, from other repositories
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.
run-dashboard-e2e-local-changes
Run Playwright E2E (tests/e2e/) against the docker/ all-in-one harness so it reflects LOCAL code changes, not a stale cached image.
qa-testing-playwright
Builds and debugs Playwright E2E suites. Use when authoring browser tests, fixing flakes, or hardening Playwright CI and locator strategy.
qa-persona-testing
Tests apps as an ICP persona through browser automation and reports friction, fixes, and risks. Use when running persona-based, ICP, or synthetic-user testing.
checking-a-page
Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it. Use after creating or editing an HTML page, or the JavaScript or CSS that a page loads.