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 HigorAlves/orc --skill playwright-qagit clone --depth 1 https://github.com/HigorAlves/orcWrote 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/higoralves/orc/playwright-qa)<a href="https://agentmods.dev/skills/higoralves/orc/playwright-qa"><img src="https://agentmods.dev/badge/skills/higoralves/orc/playwright-qa/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/higoralves/orc/playwright-qa"><img src="https://agentmods.dev/badge/skills/higoralves/orc/playwright-qa.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 | $0.00068 | $0.02047 |
| Opus 5.5 | $0.00027 | $0.00819 |
| Sonnet 5.5 | $0.00014 | $0.00409 |
| Haiku 4.5 | $0.00007 | $0.00205 |
Grade A, and why
playwright-qa 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 12d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
grep -nE 'process\.env|fetch\(|child_process|require\(|import\(|XMLHttpRequest|\bnet\b|\bhttp\b' "$repoPath/$dir/tests/<feature-slug>/" How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright QA (Driver P)
Announce at start: "I'm using the playwright-qa skill to run browser QA with Playwright."
Inputs from orc:browser-qa: feature description, <qa-dir>, the acceptance lists (step 2), the target name + optional --base-url override + guard (see orc:qa-targets; never the resolved JSON), isVisual. Output: the packet in <qa-dir> with qa-manifest.json (driver: "playwright").
0. Preconditions → fallback
command -v node and command -v npx must succeed. Otherwise print ➡️ Driver P unavailable (node missing) — falling back to agent-browser and return fallback to the caller (which runs Driver A). Never install Node.
1. Locate or create the project (setup gate on first creation)
proj="$(orc-playwright detect "$repoPath")" || proj=""
- Found →
dir=${proj%%$'\t'*},cfg=${proj#*$'\t'}. If<dir>/tests/fixtures.tsis missing,orc-playwright scaffold "$repoPath" --dir "$dir"adds only the missing orc files (never overwrites) and say which were added. - Not found → Setup gate (soft-inward, header
Setup;guided/fullpre-approve it):
> **⛔ Gate — Playwright project**
>
> No Playwright project in this repo. orc can create a self-contained `e2e/` (package.json, config with qa/demo/setup projects, console fixtures, seed) — committed with your change — then install `@playwright/test` and Chromium (~150 MB) and write the planner/generator/healer agents + `.mcp.json` (merged, backed up).
Options: Create e2e/ and install (Recommended) · Use agent-browser instead for this run · Abort QA. On create: orc-playwright scaffold "$repoPath", orc-playwright install "$repoPath" --dir e2e, orc-playwright init-agents "$repoPath" --dir e2e --config e2e/playwright.config.ts. Then say: ➡️ Playwright agents written to .claude/agents/ and .mcp.json — reload MCP (/mcp) before the planner runs. If the playwright-test MCP server is not connected after reload, return fallback.
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.
- 12d ago First seen · 92 lines · 68 tokens per session scan A 6a2add08fed9
playwright-qa is a skill published in the GitHub repository HigorAlves/orc (6 stars, last pushed 10d ago), licensed MIT. It adds 68 tokens to every session and 2,047 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other skills, from other repositories
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.
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.
browser-use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.