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 HoangNguyen0403/agent-skills-standard --skill quality-engineering-playwright-cligit clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standardWrote 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/hoangnguyen0403/agent-skills-standard/quality-engineering-playwright-cli)<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/quality-engineering-playwright-cli"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/quality-engineering-playwright-cli/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/hoangnguyen0403/agent-skills-standard/quality-engineering-playwright-cli"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/quality-engineering-playwright-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00787 |
| Opus 5 | $0.00015 | $0.00394 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
quality-engineering-playwright-cli 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎭 Playwright CLI (Web Automation)
Priority: P1 (HIGH)
[!IMPORTANT] Tier 0 (Infrastructure): Browser process management, named sessions, network/console logs. Tier 1 (Core Interactions): Clicks, fills, and navigation (
openvsgoto). Tier 2 (Verification): Snapshot-based assertions and auth state persistence.
🔌 Activation
Triggers: playwright-cli, browser automation, web verify, snapshot, auth-state.json.
🛠 Core Workflow
| Step | Command | Purpose |
|---|---|---|
| 1 | playwright-cli -s={ID} open <url> |
Start named session. (Mandatory -s=). |
| 2 | playwright-cli -s={ID} snapshot --aria |
Aria Snapshot: YAML-like view for LLM reasoning (Best for assertions). |
| 3 | playwright-cli -s={ID} console |
Check for JS errors/warnings. |
| 4 | playwright-cli -s={ID} screenshot |
Visual evidence. Use --mask <ref> for dynamic content. |
| 5 | playwright-cli -s={ID} close |
MANDATORY Cleanup. |
For a sticky header that appears after scrolling, scroll until the header is visible, use hover on the header (or its stable role/reference) to establish the visible state, then capture the screenshot. Keep the named session open until the evidence is captured.
💡 Agent-Native Optimization
- Aria-First: Use
snapshot --ariaas primary way to "see" page. Filters noise. - Robust Locators: Prefer Role-based references (e.g.
button[name="Submit"]) over fragile CSS classes. - Visual Stability: evaluated
document.body.style.animation = 'none'to freeze animations before capture.
🚫 Anti-Patterns (Zero-Tolerance)
- Unnamed Sessions: Never omit
-s=. Bare commands collide across concurrent runs. - Double Open: Use
openfor first run;gotofor mid-session navigation. - Unmasked Snapshots: Mask clocks/random IDs before comparison to avoid false positives.
- Orphaned Processes: Always
closesession, even on failure.
✅ Evaluation Criteria
- Cleanup Rate: 100% session closure.
- Assertion Quality: 90% of assertions use
snapshotrather than pixels. - Auth Persistence: Successful re-use of
state-loadfor multi-step flows.
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.
- 12d ago First seen · 71 lines · 30 tokens per session scan A acdcb51d684c
quality-engineering-playwright-cli is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 787 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
verify
Build/launch/drive recipe for verifying apps/docs changes at runtime (demos, docs pages, llms.txt).
phaser
Build 2D browser games with Phaser 4: scene lifecycle, sprites, Arcade/Matter physics, tilemaps, WebGL rendering, filters, lighting, shaders, DynamicTexture/RenderTexture, SpriteGPULayer, TilemapGPULayer, and Phaser 3 to 4 migration. Trigger: phaser, phaser 4, phaser v4, create phaser game, add phaser scene, phaser…
threejs
Build 3D browser apps AND games with Three.js (r150+, ES modules): scene setup, geometries, materials, lighting, animation, GLTF models, physics (Rapier/cannon-es/arcade), character controllers, follow/third-person cameras, fixed-timestep loops, post-processing, and performance/debugging. Use for 'create a three.js…
gamepad
Add on-screen touch controls (virtual joystick + buttons) to browser games using @vibedgames/gamepad. Use when the user wants mobile/touch controls, a virtual joystick or d-pad, on-screen action buttons, or to make a desktop game playable on phones. Triggers on: 'add touch controls', 'mobile controls', 'make it work…
playtest
Drive a real browser to play a game and prove it works — smoke checks, scripted bot playtests, softlock detection, canvas/WebGL determinism, screenshots and visual diffs — via vg playtest (agent-browser). Use for canvas/WebGL games (Phaser, Three.js) and for verifying a deployed game. Trigger: "playtest", "test my…
game-playbook
The end-to-end recipe for building a GREAT browser game from a one-line idea, plus the craft checklist that separates a tech demo from something fun. Use when the user says 'make a game', 'build a [genre] game' ('make a pixel art top-down slasher', 'build a platformer', 'make a shooter'), 'create a game', or asks to…