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/gvkhosla/compound-engineering-pi/test-browsernpx skills add gvkhosla/compound-engineering-pi --skill test-browsergit clone --depth 1 https://github.com/gvkhosla/compound-engineering-piWrote 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/gvkhosla/compound-engineering-pi/test-browser)<a href="https://agentmods.dev/skills/gvkhosla/compound-engineering-pi/test-browser"><img src="https://agentmods.dev/badge/skills/gvkhosla/compound-engineering-pi/test-browser.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 | $0.00014 | $0.02316 |
| Opus 5 | $0.00007 | $0.01158 |
| Sonnet 5 | $0.00003 | $0.00463 |
| Haiku 4.5 | $0.00001 | $0.00232 |
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 5d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- test-browser — 98% identical, 4 lines differ
- test-browser — 88% identical, 30 lines differ
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 Claude Code, 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
command -v agent-browser >/dev/null 2>&1 && echo "Installed" || echo "NOT INSTALLED"
Install if needed:
npm install -g agent-browser
agent-browser install
See the agent-browser skill for detailed usage.
Workflow
1. Verify Installation
Before starting, verify agent-browser is available:
command -v agent-browser >/dev/null 2>&1 && echo "Ready" || (echo "Installing..." && npm install -g agent-browser && agent-browser install)
If installation fails, inform the user and stop.
2. Ask Browser Mode
Ask the user whether to run headed or headless (using the platform's question tool — e.g., AskUserQuestion in Claude Code, request_user_input in Codex, ask_user in Gemini — 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
Store the choice and use the --headed flag when the user selects option 1.
3. Determine Test Scope
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.
- 5d ago First seen · 317 lines · 14 tokens per session scan A b8849aa6a87b
test-browser is a skill published in the GitHub repository gvkhosla/compound-engineering-pi (51 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 2,316 once invoked, about $0.0001 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
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
verify
Build, launch, and drive this repo's console app to verify a change end-to-end in a real browser.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
vibe-e2e
Use when performing end-to-end verification before delivery. Launches the project, opens browser, verifies every page renders, every button works, every API responds. Triggers on "E2E", "end-to-end test", "真机验证", "交付验证", "跑一下看看", "打开浏览器验证".
qa
Use when you must verify a change actually works through the REAL browser UI — acceptance, end-to-end, smoke tests, form interactions, navigation, login flows — driven by the agent-browser tool. Invoke when "click through it", "does the UI work", "smoke test the page", or browser-level evidence (screenshots…
buildkite-playwright-failures
Analyze Playwright test logs on Buildkite to extract failed-only tests across jobs.