AG Kit is a toolkit that gives Google Antigravity coding agents a structured workspace with rules, skills, specialist agents, workflows, persistent memory, orchestration, MCP guidance, and a safety hook. It is for building and operating agent workflows in Antigravity, and its catalogue entries provide parts of that workspace contract.
Borrowing it
Nothing to install: this file belongs to vudovn/ag-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vudovn/ag-kit/main/.agents/skills/webapp-testing/SKILL.mdgit clone --depth 1 https://github.com/vudovn/ag-kitWrote 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/vudovn/ag-kit/webapp-testing)<a href="https://agentmods.dev/skills/vudovn/ag-kit/webapp-testing"><img src="https://agentmods.dev/badge/skills/vudovn/ag-kit/webapp-testing/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/vudovn/ag-kit/webapp-testing"><img src="https://agentmods.dev/badge/skills/vudovn/ag-kit/webapp-testing.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 | $0.00020 | $0.00966 |
| Opus 5.5 | $0.00008 | $0.00386 |
| Sonnet 5.5 | $0.00004 | $0.00193 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
webapp-testing 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.
Copies of this mod
5 near-identical copies found in the catalogue:
- webapp-testing — 88% identical, 2 lines differ
- webapp-testing — 88% identical, 2 lines differ
- webapp-testing — 88% identical, 2 lines differ
- webapp-testing — 88% identical, 2 lines differ
- webapp-testing — 88% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web App Testing
Discover and test everything. Leave no route untested.
🔧 Runtime Scripts
Execute these for automated browser testing:
| Script | Purpose | Usage |
|---|---|---|
scripts/playwright_runner.py |
Basic browser test | python scripts/playwright_runner.py https://example.com |
| With screenshot | python scripts/playwright_runner.py <url> --screenshot |
|
| Accessibility check | python scripts/playwright_runner.py <url> --a11y |
Requires: pip install playwright && playwright install chromium
1. Deep Audit Approach
Discovery First
| Target | How to Find |
|---|---|
| Routes | Scan app/, pages/, router files |
| API endpoints | Grep for HTTP methods |
| Components | Find component directories |
| Features | Read documentation |
Systematic Testing
- Map - List all routes/APIs
- Scan - Verify they respond
- Test - Cover critical paths
2. Testing Pyramid for Web
/\ E2E (Few)
/ \ Critical user flows
/----\
/ \ Integration (Some)
/--------\ API, data flow
/ \
/------------\ Component (Many)
Individual UI pieces
3. E2E Test Principles
What to Test
| Priority | Tests |
|---|---|
| 1 | Happy path user flows |
| 2 | Authentication flows |
| 3 | Critical business actions |
| 4 | Error handling |
E2E Best Practices
| Practice | Why |
|---|---|
| Use data-testid | Stable selectors |
| Wait for elements | Avoid flaky tests |
| Clean state | Independent tests |
| Avoid implementation details | Test user behavior |
4. Playwright Principles
Core Concepts
| Concept | Use |
|---|---|
| Page Object Model | Encapsulate page logic |
| Fixtures | Reusable test setup |
| Assertions | Built-in auto-wait |
| Trace Viewer | Debug failures |
Configuration
| Setting | Recommendation |
|---|---|
| Retries | 2 on CI |
| Trace | on-first-retry |
| Screenshots | on-failure |
| Video | retain-on-failure |
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.
- 1mo ago First seen · 190 lines · 20 tokens per session scan A 2a0dd4918f66
webapp-testing is a skill published in the GitHub repository vudovn/ag-kit (8,203 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 966 once invoked, about $0.0001 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
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.
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.…
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…
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.