Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/idavidov13/agentic-playwrightnpx agentmods add skills/idavidov13/agentic-playwright/data-strategyWrote 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/idavidov13/agentic-playwright/data-strategy)<a href="https://agentmods.dev/skills/idavidov13/agentic-playwright/data-strategy"><img src="https://agentmods.dev/badge/skills/idavidov13/agentic-playwright/data-strategy/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/idavidov13/agentic-playwright/data-strategy"><img src="https://agentmods.dev/badge/skills/idavidov13/agentic-playwright/data-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 39 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Agent Snooping · line 206 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00160 | $0.02957 |
| Opus 5.5 | $0.00064 | $0.01183 |
| Sonnet 5.5 | $0.00032 | $0.00591 |
| Haiku 4.5 | $0.00016 | $0.00296 |
Grade A, and why
data-strategy 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 1mo 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Strategy
This framework uses a bifurcated data strategy: static data for deterministic curated cases and dynamic factories for test isolation.
Critical
- Static data files are TypeScript only. Every file under
test-data/static/**is a.tsfile that exportsas constliteral values. NEVER use.json. - Static data files may only export literal values. No runtime imports (type-only imports are fine), no function definitions, no computed values, no Faker calls. Dynamic data belongs in factories, not in static files.
- NEVER hardcode test content strings (names, emails, todo text, product names, descriptions, etc.) in a spec file. Generate with a Faker factory.
- NEVER redefine universal type-mismatch arrays (
[123, true, null, undefined], etc.) inline. Import them fromtest-data/static/util/invalid-values.ts. - ALWAYS validate factory output with
Schema.parse(...)and return the Zod-inferred type. - NEVER generate app-defined strings with Faker (error messages, button labels, page headers). Those live in
enums/so they stay in sync with the application under test. - NEVER store fixed expected values that are used in a single assertion in a static data file. Keep them inline in the test.
- ALWAYS follow the
refactor-valuesskill before editing any existing static-data file or enum value — these edits cascade through assertions and data-driven loops. - NEVER introduce magic numbers (timeouts, retry counts, limits) inline. Prefer web-first assertions; when a numeric value is unavoidable, route it through
playwright.config.tsor an enum inenums/.
File Locations
{area}is a placeholder. Before creating or referencing any path below, runls test-data/static/andls test-data/factories/to discover the real subdirectory names in this repo (e.g.,front-office,back-office) and use those instead.
| Type | Directory | Purpose |
|---|---|---|
| Universal invalid arrays | test-data/static/util/ |
Type-mismatch tuples reused by every negative test (.ts, as const) |
| Domain-specific static | test-data/static/{area}/ |
Curated invalid/boundary sets tied to the app's validation rules (.ts, as const) |
| Dynamic factories | test-data/factories/{area}/ |
Faker + Zod factories for unique, valid data per test run |
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.
- 1mo ago First seen · 236 lines · 160 tokens per session scan A 61a821dad24c
data-strategy is a skill published in the GitHub repository idavidov13/agentic-playwright (235 stars, last pushed 5d ago), licensed MIT. It adds 160 tokens to every session and 2,957 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
vindicate
Use when the user wants to write, add, fix, stabilize (flaky), refactor, run, or audit Playwright browser tests, draft requirements/stories from a recording (no tests), find test-coverage gaps, scaffold a Playwright project, or set up Playwright CI. Vindicate's guided workflow for grounded, conformant Playwright test…
E2E Testing Patterns
Comprehensive end-to-end testing methodologies and best practices covering architecture, test design, data management, flakiness prevention, and cross-browser strategies.
Laravel Dusk Testing
Expert-level Laravel Dusk browser testing skill for PHP/Laravel applications. Covers Chrome-based E2E testing, browser assertions, Page Objects, component testing, authentication helpers, and database integration.
JMeter Load Testing
Load and performance testing skill using Apache JMeter, covering test plans, thread groups, assertions, listeners, timers, and distributed testing.
ac-qa-e2e-review
Reviews spec implementation with E2E visual browser validation via Playwright. Triggers on keywords: e2e review, visual review, spec review, browser validation.
ac-qa-test-e2e
Executes E2E tests from definition files with Playwright browser automation. Triggers on keywords: test e2e, run e2e, execute e2e test, e2e test runner.