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/platonai/browser4/test-productionnpx skills add platonai/Browser4 --skill test-productiongit clone --depth 1 https://github.com/platonai/Browser4Wrote 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.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 | $0.00044 | $0.01269 |
| Opus 5 | $0.00022 | $0.00634 |
| Sonnet 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 4d 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.
- 4d ago First seen · 135 lines · 44 tokens per session scan A 7292f1eef31c
test-production is a skill published in the GitHub repository platonai/Browser4 (1,120 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. 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
browser_harness
../../SKILL.md.
cli-docs-guidelines
Review or write CLI documentation. Enforces progressive disclosure, logical command ordering, and plain-language explanations. Use when asked to "write CLI docs", "document commands", "review CLI reference", or "update command docs".
readme-guidelines
Review or write README content for open-source projects. Enforces progressive disclosure, jargon-free language, and single-concept code examples. Use when asked to "write README", "review README", "update README", or "check docs".
cdp
Drive Browser Use Desktop's assigned Chromium target via the DevTools Protocol from JavaScript. Run snippets through the bundled browser-harness-js CLI; it auto-spawns a long-lived Bun HTTP server holding a CDP Session, and every call executes against the same persistent connection.
Video Editor (FFmpeg)
AI-powered Video Editor with trimming, merging, effects, overlays, and export.
Codex
Mission control: create tasks, assign to an agent/team, wait for human approval, worker runs in the background, accept results.