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 songofhawk/playwright-mcp-tabbed --skill playwright-tabbed-orchestrationgit clone --depth 1 https://github.com/songofhawk/playwright-mcp-tabbedWrote 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/songofhawk/playwright-mcp-tabbed/playwright-tabbed-orchestration)<a href="https://agentmods.dev/skills/songofhawk/playwright-mcp-tabbed/playwright-tabbed-orchestration"><img src="https://agentmods.dev/badge/skills/songofhawk/playwright-mcp-tabbed/playwright-tabbed-orchestration/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/songofhawk/playwright-mcp-tabbed/playwright-tabbed-orchestration"><img src="https://agentmods.dev/badge/skills/songofhawk/playwright-mcp-tabbed/playwright-tabbed-orchestration.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 | $0.00096 | $0.01741 |
| Opus 5 | $0.00048 | $0.00870 |
| Sonnet 5 | $0.00019 | $0.00348 |
| Haiku 4.5 | $0.00010 | $0.00174 |
Grade A, and why
playwright-tabbed-orchestration 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 10d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright Multi-Tab + Parent/Child Agent Orchestration
Use Cases
- A batch of pages or scenarios must be validated within the same browser context (e.g. shared login state) and you want true parallelism to reduce total time.
- The parent agent is responsible for: resolving BASE_URL, creating tabs, partitioning tasks, aggregating results; child agents are responsible for: calling MCP only within their assigned
tab_id, without stealing focus from other tabs.
Prerequisites
- MCP server: playwright-tabbed — if not installed, prompt the user to run
npm install playwright-mcp-tabbed. - If the task depends on an authenticated session: complete BASE_URL Resolution below first; then verify login state; do not create new tabs in bulk or spawn child agents until the user explicitly confirms (gate can be loosened or tightened per business rules; halt and wait for the user if not logged in).
Installation Path and Script Location
When resolving BASE_URL, run the following from the skill root directory:
node scripts/resolve-base-url.js
If called from a different working directory, use an absolute path or cd to the skill root first. When relying on .env.local / .env / playwright.env.local at the repository root, the terminal or agent's cwd should be inside the target project repo (the script walks up from cwd to locate .git).
BASE_URL Resolution
The parent agent must not ask the user to guess the address or wait for a passphrase before BASE_URL (configured as PLAYWRIGHT_BASE_URL) has been determined.
Recommended: run the script first to obtain PLAYWRIGHT_BASE_URL, then align with the current tab's origin via browser_context_info as needed.
node scripts/resolve-base-url.js
Optional flags: --source prints the resolution source, --strip-trailing-slash removes a trailing /, --export outputs export PLAYWRIGHT_BASE_URL=....
If the script exits with a non-zero code: prompt the user to configure a source following the full resolution order described at the top of scripts/resolve-base-url.js (or run node scripts/resolve-base-url.js --help).
What ships with it
2 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.
- 10d ago First seen · 101 lines · 96 tokens per session scan A a285dee91d0c
playwright-tabbed-orchestration is a skill published in the GitHub repository songofhawk/playwright-mcp-tabbed (0 stars, last pushed 5mo ago), licensed MIT. It adds 96 tokens to every session and 1,741 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
Browser Agent QA Testing
Teach agents to use AI browser agents for exploratory and smoke QA with step budgets, evidence-based assertions, guardrails, and Playwright conversion.
nobrainer-browser
Use when the owner says nb-browser or nobrainer-browser, asks to inspect or operate a rendered website, attach to an existing approved Chrome/Edge session, restart an approved non-default Chromium profile for loopback CDP, reproduce a browser flow, run Playwright tests, or record and analyze a Playwright trace. Prefer…
glance-test
Run E2E browser tests on any web application using Glance MCP. Use when the user says "test this page," "check this URL," "run E2E tests," "browser test," "test the login flow," "check if the site works," "visual regression," or "screenshot this page." Also use for post-deploy verification and smoke tests.
ironbee-browser-devtools-cli
Automates browser interactions using Playwright for web testing, debugging, and automation. Use when the user needs to navigate websites, take screenshots, fill forms, click elements, extract page content (HTML/text), audit accessibility (ARIA/AX tree), measure Web Vitals performance, monitor console logs and HTTP…
browser-testing
Automated browser testing, interaction automation, and form testing. Use when the user needs to test web pages, automate browser interactions, fill forms, test validation, run multi-step wizards, or test login/signup flows.
reviewing-flows
Use when the pending flow queue needs triage before approval, such as deciding which recorded flows are worth keeping, clearing out ones that can never replay, or reading a flow's real steps before consenting to it.