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/trebormc/drupal-ai-agents/playwright-testingnpx skills add trebormc/drupal-ai-agents --skill playwright-testinggit clone --depth 1 https://github.com/trebormc/drupal-ai-agentsWrote 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/trebormc/drupal-ai-agents/playwright-testing)<a href="https://agentmods.dev/skills/trebormc/drupal-ai-agents/playwright-testing"><img src="https://agentmods.dev/badge/skills/trebormc/drupal-ai-agents/playwright-testing.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 | $0.00154 | $0.02748 |
| Opus 5 | $0.00077 | $0.01374 |
| Sonnet 5 | $0.00031 | $0.00550 |
| Haiku 4.5 | $0.00015 | $0.00275 |
Grade A, and why
playwright-testing scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Never use curl for testing Drupal functionality. Use Playwright MCP instead. How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critical Rules
- NEVER use curl for testing Drupal pages — it cannot execute JS or simulate user navigation
- ALWAYS use HTTP (not HTTPS) for all Playwright navigation in DDEV — self-signed SSL certificates cause failures
- Convert ALL URLs from
https://tohttp://before passing tobrowser_navigate, including drush uli output - NEVER create JavaScript files, Node.js scripts, or Playwright test scripts to interact with the browser. Always use the Playwright MCP tools directly. If MCP fails, troubleshoot the connection — do NOT generate script files as a workaround
MCP Connection
Playwright MCP tools (browser_navigate, browser_take_screenshot, etc.) are registered as native tools via the MCP server configuration. They should be available directly — no manual HTTP/SSE protocol is needed.
- MCP URL:
http://playwright-mcp:8931/mcp(or$PLAYWRIGHT_MCP_URL) - Site URL: use
$DDEV_HTTP_URL(already HTTP).$DDEV_PRIMARY_URLis HTTPS — if you use it, convert to HTTP first - Web Container: accessible via
ssh web(for commands likedrush uli)
If MCP tools are not available
This is a RECOVERY procedure only. If the browser_ tools are visible, skip this entire section.*
If the browser tools are not showing up as available tools:
# 1. Check if Playwright MCP is responding (works without Docker socket)
curl -s --max-time 3 http://playwright-mcp:8931/sse \
-H "Accept: text/event-stream" | head -1
# Success: "event: endpoint"
# Failure: connection refused → container not running
# 2. Verify environment variable
echo $PLAYWRIGHT_MCP_URL
# Should return: http://playwright-mcp:8931/mcp
# 3. Restart DDEV to recover the container
# (tell the user to run: ddev restart)
NEVER work around a failed MCP connection by writing .js or .mjs files.
Environment Architecture
┌─────────────────────────────────────────────────────────────┐
│ AI Container (OpenCode or Claude Code) │
│ - Runs agents, reads files, executes bash │
│ - Connects to Web via: ssh web │
│ - Uses Playwright via: MCP tools (native) │
└──────────────┬──────────────────────┬───────────────────────┘
│ SSH │ MCP protocol
▼ ▼
┌──────────────────────────┐ ┌───────────────────────────────┐
│ Web Container │ │ Playwright MCP Container │
│ (ddev-{project}-web) │ │ (ddev-{project}-playwright- │
│ - PHP, Drupal, Drush │ │ mcp) │
│ - npm, Composer │ │ - Chromium browser │
└──────────────────────────┘ │ - MCP tools on port 8931 │
│ - Navigates to Web Container │
└───────────────────────────────┘
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.
- 4d ago First seen · 249 lines · 154 tokens per session scan A 9dd68fbfc712
playwright-testing is a skill published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 154 tokens to every session and 2,748 once invoked, about $0.0008 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
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
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…
playwright-screen-recording
Record browser test videos with Playwright for PR review and bug fix verification.
web-preview
Flutter Web版をビルド → サーバー起動 → Playwright でアクセス確認 → URLをユーザーに案内する。.
login-flows
Common login automation patterns for web apps using Playwright.