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 fmflurry/settings-opencode --skill playwright-e2e-authoringgit clone --depth 1 https://github.com/fmflurry/settings-opencodeWrote 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/fmflurry/settings-opencode/playwright-e2e-authoring)<a href="https://agentmods.dev/skills/fmflurry/settings-opencode/playwright-e2e-authoring"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/playwright-e2e-authoring/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/fmflurry/settings-opencode/playwright-e2e-authoring"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/playwright-e2e-authoring.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 | $0.00166 | $0.02291 |
| Opus 5.5 | $0.00066 | $0.00916 |
| Sonnet 5.5 | $0.00033 | $0.00458 |
| Haiku 4.5 | $0.00017 | $0.00229 |
Grade A, and why
playwright-e2e-authoring 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 27d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright E2E Authoring — gc.platform
This suite tests the live gc.platform stack end-to-end: the real Angular frontend (http://localhost:4200) plus the real GcPlatform.Api .NET backend, orchestrated by docker-compose at the repo root. Tests drive the full stack — there are no mocks, no stubs, no fake data.
Path convention: All paths in this document are relative to tests/playwright/ (the test suite root).
Your job when this skill is active: turn a request like "add E2E tests for the <feature> screen" into a correct POM + module fixture + spec, colocated under tests/<module>/, that compiles under strict TypeScript and follows the conventions the existing auth and invoices modules already demonstrate.
When to activate
- Adding E2E coverage for a new frontend feature module or screen.
- Writing a new
.spec.ts, a Page Object Model, or a module fixture. - Extending an existing module with another screen/POM.
- Any "test the X page/flow with Playwright" request, even when the conventions aren't named.
The four rules (non-negotiable — they are project law)
These come from tests/playwright/CLAUDE.md. Everything this skill generates must honour them.
| # | Rule | What it means in practice |
|---|---|---|
| 1 | No mocks | Real frontend + real backend + real DB. No page.route()/context.route(), no MSW/sinon/nock, no fixture stubs, no page.waitForTimeout() or arbitrary sleeps. Create/clean test data via real API or UI. |
| 2 | Page Object Model | Every screen is a POM class under tests/<module>/pages/ extending BasePage. Specs never call raw page.locator() — all DOM access flows through a POM. |
| 3 | Work by fixture | POMs are injected via Playwright fixtures (test.extend). Specs import test/expect from their module fixture, never from @playwright/test. Never new SomePage() inside a spec. |
| 4 | Per application module | One test folder per frontend feature: frontend/src/app/modules/<module> → tests/<module>/. POM, fixtures, and specs stay colocated. Cross-module helpers live in support/. |
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.
- 27d ago First seen · 140 lines · 166 tokens per session scan A 142d97c6dce2
playwright-e2e-authoring is a skill published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed 2d ago), licensed MIT. It adds 166 tokens to every session and 2,291 once invoked, about $0.0007 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 2026-09-20.
Other skills, from other repositories
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
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.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.