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 EricTechPro/startup-claude-skills --skill playwright-qa-cligit clone --depth 1 https://github.com/EricTechPro/startup-claude-skillsWrote 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/erictechpro/startup-claude-skills/playwright-qa-cli)<a href="https://agentmods.dev/skills/erictechpro/startup-claude-skills/playwright-qa-cli"><img src="https://agentmods.dev/badge/skills/erictechpro/startup-claude-skills/playwright-qa-cli/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/erictechpro/startup-claude-skills/playwright-qa-cli"><img src="https://agentmods.dev/badge/skills/erictechpro/startup-claude-skills/playwright-qa-cli.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 | $0.00152 | $0.02683 |
| Opus 5.5 | $0.00061 | $0.01073 |
| Sonnet 5.5 | $0.00030 | $0.00537 |
| Haiku 4.5 | $0.00015 | $0.00268 |
Grade A, and why
playwright-qa-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright QA (CLI Variant)
Automated headless-browser QA using playwright-cli bash commands. Provisions a test user, logs in, navigates to target pages, screenshots each step, generates REPORT.md, cleans up.
CRITICAL: No MCP Tools
Do NOT use any mcp__plugin_playwright_playwright__* tools. Use ONLY playwright-cli bash commands via the Bash tool. If playwright-cli is not found, STOP and ask user to install — do NOT fall back to MCP tools.
PATH Setup — REQUIRED
Prefix EVERY playwright-cli bash command with:
export PATH="$HOME/.npm-global/bin:$PATH" && playwright-cli ...
Parameters
| Parameter | Default | Example | Description |
|---|---|---|---|
base |
prod |
local |
prod = CONFIG.md PROD_URL, local = http://localhost:3000 |
mode |
check |
verify |
verify = reproduce bug, check = confirm fix |
url |
auto-detect | /dashboard/receipts |
Page to test |
change_description |
from git diff | "Fixed button overflow" |
What to verify |
ticket_id |
none | PROJ-123 |
Issue tracker ticket (folder naming) |
skip_cleanup |
false |
true |
Keep test user alive |
Configuration
All project-specific settings are defined in CONFIG.md at the root of this skill directory. Before first use, copy CONFIG.example.md to CONFIG.md and fill in your values.
| Setting | Source |
|---|---|
| Test Email | CONFIG.md → TEST_USER_EMAIL |
| Test Password | CONFIG.md → TEST_USER_PASSWORD |
| Supabase Project ID | CONFIG.md → SUPABASE_PROJECT_ID |
| Production URL | CONFIG.md → PROD_URL |
| Viewport | 1440x900 |
Password note: Avoid !, \, $ in test passwords — playwright-cli fill escapes shell-special characters.
Execution Flow
Phase 1: Setup (mkdir screenshots, detect route from git diff)
Phase 1.5: Dev server (local only — check port 3000, start if needed)
Phase 2: Provision test user → read references/provision.md
Phase 3: Login via CLI → use state-save for auth persistence
Phase 4: Navigate & test target page
Phase 5: Cleanup → read references/cleanup.md + playwright-cli close
Phase 6: Generate REPORT.md → read references/report-templates.md
What ships with it
4 files 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.
- 1mo ago First seen · 240 lines · 152 tokens per session scan A 049339d3b66b
playwright-qa-cli is a skill published in the GitHub repository EricTechPro/startup-claude-skills (60 stars, last pushed 4mo ago), licensed MIT. It adds 152 tokens to every session and 2,683 once invoked, about $0.0006 per session on Opus 5.5. 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
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
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.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…