browser-test

browser-test is a skill for Claude Code from dinhtungdu/tangerine. It costs 56 tokens per session (2,934 once invoked), scanned A, original, MIT.

A browser-based visual testing guide for checking web interface changes with Chromium, an open-source web browser.

In plain words
What is it for?
Use it after changing a web dashboard to start the app, open affected pages, take screenshots, inspect console errors, and clean up the test process.
Why use it?
It catches layout problems and browser-console errors that ordinary code checks may miss.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Install

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.

agentmods
npx agentmods add skills/dinhtungdu/tangerine/browser-test
Any agent
npx skills add dinhtungdu/tangerine --skill browser-test
Clone the repo
git clone --depth 1 https://github.com/dinhtungdu/tangerine

Made for: Claude Code.

Wrote 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.

agentmods badge for browser-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/dinhtungdu/tangerine/browser-test.svg)](https://agentmods.dev/skills/dinhtungdu/tangerine/browser-test)
Your own site
<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>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,934 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash c8bb21382857, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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:*)
.agents/skills/browser-test/SKILL.md · 278 lines

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-cli installed 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

Read the full file on GitHub · 278 lines

Files

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.

Changes

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.

  1. 6d ago First seen · 278 lines · 56 tokens per session scan A c8bb21382857

Subscribe to this mod's changes

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.