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 marcusrbrown/systematic --skill test-browsergit clone --depth 1 https://github.com/marcusrbrown/systematicWrote 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/marcusrbrown/systematic/test-browser)<a href="https://agentmods.dev/skills/marcusrbrown/systematic/test-browser"><img src="https://agentmods.dev/badge/skills/marcusrbrown/systematic/test-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/marcusrbrown/systematic/test-browser"><img src="https://agentmods.dev/badge/skills/marcusrbrown/systematic/test-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 | $0.00014 | $0.02376 |
| Opus 5.5 | $0.00006 | $0.00950 |
| Sonnet 5.5 | $0.00003 | $0.00475 |
| Haiku 4.5 | $0.00001 | $0.00238 |
Grade A, and why
test-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
88% identical to test-browser — 30 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Test Skill
Run end-to-end browser tests on pages affected by a PR or branch changes using the agent-browser CLI.
Use agent-browser Only For Browser Automation
This workflow uses the agent-browser CLI exclusively. Do not use any alternative browser automation system, browser MCP integration, or built-in browser-control tool. If the platform offers multiple ways to control a browser, always choose agent-browser.
Use agent-browser for: opening pages, clicking elements, filling forms, taking screenshots, and scraping rendered content.
Platform-specific hints:
- In OpenCode, do not use Chrome MCP tools (
mcp__claude-in-chrome__*). - In Codex, do not substitute unrelated browsing tools.
Prerequisites
- Local development server running (e.g.,
bin/dev,rails server,npm run dev) agent-browserCLI installed (see Setup below)- Git repository with changes to test
Setup
Check whether agent-browser is installed:
command -v agent-browser >/dev/null 2>&1 && echo "Installed" || echo "NOT INSTALLED"
If not installed, inform the user: "agent-browser is not installed. Install it with npm install -g agent-browser." Then stop — this skill cannot function without agent-browser.
Workflow
1. Verify Installation
Before starting, verify agent-browser is available:
command -v agent-browser >/dev/null 2>&1 && echo "Ready" || echo "NOT INSTALLED"
If not installed, inform the user: "agent-browser is not installed. Install it with npm install -g agent-browser." Then stop.
2. Ask Browser Mode
Ask the user whether to run headed or headless (using the platform's question tool — e.g., question in OpenCode, request_user_input in Codex, ask_user in Gemini; in Pi, use the blocking-question extension if available, otherwise present numbered options in chat and wait — or present options and wait for a reply):
Do you want to watch the browser tests run?
1. Headed (watch) - Opens visible browser window so you can see tests run
2. Headless (faster) - Runs in background, faster but invisible
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 · 317 lines · 14 tokens per session scan A ffa33e3b86cd
test-browser is a skill published in the GitHub repository marcusrbrown/systematic (24 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 2,376 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to test-browser, differing in 30 lines, and is treated as a copy.
Other skills, from other repositories
playwright
Browser automation, web scraping, E2E testing, and visual regression with Playwright. Covers 30+ patterns: login flows, form testing, responsive design checks, broken link validation, API mocking, data extraction, PDF generation, accessibility audits (axe-core), performance budgets (Lighthouse), visual diffing…
browser-qa
The canonical browser-QA protocol for web changes — target resolution, env attach, the driver gate (Playwright primary, agent-browser, Claude-in-Chrome), validator dispatch, chrome evidence packet. Use when running browser QA; /orc:qa and /orc:flow Phase 6 delegate here.
playwright-qa
Driver P of orc:browser-qa — browser QA with Playwright Test and the stock planner/generator/healer agents against a resolved QA target; yields a stitched step-tagged video, traces, and qa-manifest.json. Use when browser-qa selects the playwright driver; falls back to agent-browser.
qa-targets
Resolve WHERE browser QA runs — named targets in .orc/targets.json (local, staging, preview), the Target gate, credential references (literal | op:// | env:), guard rule. Use before env provisioning in /orc:qa, /orc:flow Phase 6, /orc:evidence.
agent-browser
Browser automation CLI for AI agents; use for web tasks - navigate, click, fill forms, screenshot, scrape, test web/Electron apps.
pn-smoke-tests
Run smoke or E2E tests, debug failures, and verify fixes. Use for end-to-end verification before or after changes.