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/dinhtungdu/tangerine/browser-testnpx skills add dinhtungdu/tangerine --skill browser-testgit clone --depth 1 https://github.com/dinhtungdu/tangerineWrote 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/dinhtungdu/tangerine/browser-test)<a href="https://agentmods.dev/skills/dinhtungdu/tangerine/browser-test"><img src="https://agentmods.dev/badge/skills/dinhtungdu/tangerine/browser-test.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 5.1 | $0.00056 | $0.02934 |
| Opus 5 | $0.00028 | $0.01467 |
| Sonnet 5 | $0.00011 | $0.00587 |
| Haiku 4.5 | $0.00006 | $0.00293 |
Grade A, and why
browser-test scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(playwright-cli:*) Bash(bunx vite:*) Bash(curl:*) Bash(kill:*) Bash(jq:*) How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Test
Visually verify web UI changes by running the app in a real browser and taking screenshots.
Always launch playwright-cli with Chromium explicitly. Do not rely on the default browser selection, because Chrome may be unavailable on Tangerine VMs.
When to use
After completing work on any feature, bug fix, or change that affects the web dashboard (web/src/). Do NOT use for server-only or shared-only changes.
Prerequisites
playwright-cliinstalled globally (npm install -g @playwright/cli)- Chromium installed (
npx playwright install chromium) - Both are pre-installed on Tangerine VMs
Quick workflow
1. Derive port from worktree slot number
2. Start vite dev server on that port (background)
3. Wait for server ready
4. Open Chromium with playwright-cli
5. If auth is enabled, inject the auth token into localStorage
6. Navigate to affected pages, take screenshots
7. Check console for errors
8. Clean up (close browser, kill dev server)
Detailed steps
Step 1 — Derive a unique port
Extract the slot number from your worktree path and compute a port:
# Worktree path looks like: /workspace/<project>/worktrees/<projectId>-slot-<N>
SLOT_NUM=$(basename "$PWD" | grep -oP 'slot-\K\d+')
VITE_PORT=$((5170 + SLOT_NUM))
echo "Using port $VITE_PORT"
If you cannot determine the slot number, use port 5199 as a fallback.
Step 2 — Start the dev server
cd web && bunx vite --port $VITE_PORT > /tmp/vite-$VITE_PORT.log 2>&1 &
VITE_PID=$!
echo "Vite PID: $VITE_PID"
Step 3 — Wait for the server
# Wait up to 30 seconds for vite to be ready
for i in $(seq 1 30); do
curl -s -o /dev/null http://localhost:$VITE_PORT && break
sleep 1
done
Step 4 — Open browser and take screenshots
Use a named session tied to the task to avoid conflicts with other tasks:
TASK_SHORT=$(echo $TANGERINE_TASK_ID | cut -c1-8)
SESSION="task-$TASK_SHORT"
# Open Chromium explicitly (headless by default)
playwright-cli --browser chromium -s=$SESSION open http://localhost:$VITE_PORT
# Always set viewport explicitly — some environments open Chromium with a
# non-standard default size, causing screenshots at 1/4 resolution or smaller.
# Use 1920x1080 for crisp, full-HD screenshots (headless Chromium has dpr=1).
playwright-cli -s=$SESSION resize 1920 1080
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 278 lines · 56 tokens per session scan A c8bb21382857
browser-test is a skill published in the GitHub repository dinhtungdu/tangerine (5 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 2,934 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
browse
Fast headless browser for QA testing and site dogfooding. (gstack).
playwright-dev
Explains how to develop Playwright - add APIs, MCP tools, CLI commands, and vendor dependencies.
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
playwright-cli
官方Microsoft Playwright CLI网页自动化工具,支持所有主流浏览器的无头/有头自动化操作,包括页面导航、元素交互、截图、录制、测试等功能。当用户提到网页自动化、浏览器操作、爬虫、截图、录制用户操作、E2E测试时触发。.
playwright-screen-recording
Record browser test videos with Playwright for PR review and bug fix verification.