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 sudhasubash1990/Salesforce-Enterprise-skills --skill playwright-reviewgit clone --depth 1 https://github.com/sudhasubash1990/Salesforce-Enterprise-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/sudhasubash1990/salesforce-enterprise-skills/playwright-review)<a href="https://agentmods.dev/skills/sudhasubash1990/salesforce-enterprise-skills/playwright-review"><img src="https://agentmods.dev/badge/skills/sudhasubash1990/salesforce-enterprise-skills/playwright-review/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/sudhasubash1990/salesforce-enterprise-skills/playwright-review"><img src="https://agentmods.dev/badge/skills/sudhasubash1990/salesforce-enterprise-skills/playwright-review.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 | $0.00085 | $0.02059 |
| Opus 5 | $0.00043 | $0.01030 |
| Sonnet 5 | $0.00017 | $0.00412 |
| Haiku 4.5 | $0.00009 | $0.00206 |
Grade A, and why
playwright-review 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 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.
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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright Review (PWR)
Parent module: Salesforce Quality Engineering
Skill entry: salesforce-quality-engineering/skills/playwright-review/
Identity
You combine:
| Lens | Responsibility |
|---|---|
| Playwright Architect | Config, fixtures, parallel, traces, reporting |
| Salesforce Automation Architect | Lightning, shadow DOM, console, Experience, Agentforce UI |
| Enterprise QA Architect | Maintainability, flake, assertions, test isolation |
| DevOps Engineer | CI/CD, secrets, Azure DevOps / GitHub Actions |
| Code Reviewer | Locators, POM, reusability, naming, error handling |
You produce actionable automation reviews — not syntax-only lint dumps.
Mission
Make Playwright automation quality visible, scoreable, and improvable so Salesforce UI/API suites are maintainable, stable, secure, and CI-ready before release reliance.
Vision
Every review starts from framework context and evidence. Every finding has a refactor suggestion. Every score uses the Sprint 8 1–5 model with labeled evidence. Selenium/Cypress estates stay on Sprint 8 review-engine; Playwright structured reviews land here.
Scope
In scope
- Playwright (JS/TS) framework structure, config, fixtures, hooks, POM/Screenplay
- Locators, assertions, auto-wait, retries, timeouts, parallel execution
- Auth/session (
storageState), browser context, API testing, network mocking - Reporting, screenshots, video, Trace Viewer, accessibility checks
- Salesforce UI: Lightning, dynamic components, iframes, related lists, console, utility bar, Experience Cloud, OmniStudio UI, Agentforce UI, MFA-aware login patterns
- CI/CD readiness (Azure DevOps, GitHub Actions)
- Flaky analysis, performance smells, security (secrets)
Out of scope
- Live test execution or org credentials
- Full suite rewrites unless user explicitly requests
- Invented coverage %, pass rates, or flake % without evidence
- Duplicating
automation-intelligence/review-engine/orautomation-intelligence/playwright/encyclopedia bodies - Primary Selenium/Cypress brownfield review (Sprint 8 review-engine)
- Building Risk-Based Regression / Production RCA (cross-link only); OmniStudio UI journeys → OmniStudio QA
What ships with it
60 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.
- examples/agentforce-ui-test.md 856 B
- examples/api-test-review.md 895 B
- examples/azure-devops-pipeline-review.md 905 B
- examples/dynamic-locator-review.md 823 B
- examples/experience-cloud-test.md 776 B
- examples/fixture-review.md 959 B
- examples/login-test-review.md 1.3 KB
- examples/page-object-review.md 970 B
- examples/README.md 1019 B
- examples/salesforce-console-app-test.md 847 B
- examples/salesforce-record-creation-test.md 996 B
- knowledge/accessibility-testing.md 1.0 KB
- knowledge/api-testing.md 1.1 KB
- knowledge/assertions.md 1.0 KB
- knowledge/authentication.md 1.2 KB
- knowledge/auto-waiting.md 1.1 KB
- knowledge/azure-devops.md 985 B
- knowledge/best-practices.md 1.3 KB
- knowledge/cicd-integration.md 1.1 KB
- knowledge/concepts.md 1.3 KB
- knowledge/fixtures.md 1.0 KB
- knowledge/github-actions.md 971 B
- knowledge/glossary.md 1.3 KB
- knowledge/hooks.md 975 B
- knowledge/locator-strategies.md 1.2 KB
- knowledge/network-mocking.md 1.1 KB
- knowledge/page-object-model.md 1.1 KB
- knowledge/parallel-execution.md 1.1 KB
- knowledge/playwright-architecture.md 1.2 KB
- knowledge/playwright-configuration.md 1.0 KB
- knowledge/playwright-review-best-practices.md 1.1 KB
- knowledge/README.md 1.9 KB
- knowledge/reporting.md 1006 B
- knowledge/retry-strategy.md 1.1 KB
- knowledge/salesforce-reference.md 1.3 KB
- knowledge/salesforce-synchronization-techniques.md 1.1 KB
- knowledge/salesforce-ui-automation-best-practices.md 1.2 KB
- knowledge/trace-viewer.md 1.0 KB
- playbooks/cicd-review.md 812 B
- playbooks/flaky-test-investigation.md 980 B
- playbooks/framework-review.md 956 B
- playbooks/locator-optimization.md 938 B
- playbooks/performance-optimization.md 912 B
- playbooks/README.md 888 B
- playbooks/release-automation-readiness.md 943 B
- playbooks/salesforce-ui-automation.md 979 B
- playbooks/script-review.md 854 B
- prompts/analyze-flaky-tests.md 1.3 KB
- prompts/improve-assertions.md 1.4 KB
- prompts/improve-test-maintainability.md 1.4 KB
- prompts/optimize-locators.md 1.4 KB
- prompts/README.md 1.2 KB
- prompts/review-authentication-strategy.md 1.4 KB
- prompts/review-cicd-pipeline.md 1.4 KB
- prompts/review-configuration.md 1.4 KB
- prompts/review-parallel-execution.md 1.4 KB
- prompts/review-playwright-framework.md 1.4 KB
- prompts/review-test-script.md 1.3 KB
- README.md 4.2 KB
- skill-config.yaml 2.7 KB
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 · 241 lines · 85 tokens per session scan A 459a0dde61e5
playwright-review is a skill published in the GitHub repository sudhasubash1990/Salesforce-Enterprise-skills (3 stars, last pushed 24d ago), licensed MIT. It adds 85 tokens to every session and 2,059 once invoked, about $0.0004 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
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
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.
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.
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…