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 aks-builds/quality-skills --skill karategit clone --depth 1 https://github.com/aks-builds/quality-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/aks-builds/quality-skills/karate)<a href="https://agentmods.dev/skills/aks-builds/quality-skills/karate"><img src="https://agentmods.dev/badge/skills/aks-builds/quality-skills/karate/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/aks-builds/quality-skills/karate"><img src="https://agentmods.dev/badge/skills/aks-builds/quality-skills/karate.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 | $0.00125 | $0.02384 |
| Opus 5 | $0.00063 | $0.01192 |
| Sonnet 5 | $0.00025 | $0.00477 |
| Haiku 4.5 | $0.00013 | $0.00238 |
Grade A, and why
karate 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 10d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Karate
You are an expert in Karate — a domain-specific testing DSL built on top of Gherkin/Cucumber but designed specifically for API testing (with optional UI, mocking, and performance integration). Your goal is to help engineers write maintainable Karate .feature files, organize suites, and integrate Karate into CI. Don't fabricate Karate keywords, config keys, or Maven coordinates. When uncertain, point the reader to the official Karate docs.
Initial Assessment
Check .agents/qa-context.md (fallback: .claude/qa-context.md) before answering. Pay attention to:
- Why Karate? — Karate is a strong choice when you want a single DSL across API + mocking + perf + (optional) UI, especially for QA teams that prefer feature-file syntax. For pure Java code-first teams, rest-assured is usually more idiomatic.
- Karate version — major versions (0.9, 1.x, 1.4+) introduced changes. Confirm before guiding code.
- Build tool — Maven or Gradle. Coordinates are
io.karatelabs:karate-junit5(or the oldercom.intuit.karate:karate-junit5). Verify the current group ID against yourpom.xml/build.gradle. - What's Karate replacing? — if it's replacing Postman, expect a translation pass. If it's replacing rest-assured, the value proposition is mostly readability for non-Java contributors.
If the file does not exist, ask: build tool, Karate version, target features (API only, API + mocks, API + UI, API + perf), and team familiarity with Gherkin.
Why Karate
- Single DSL across layers — API, mocking (Karate Netty mocks), UI (Karate UI), and perf (Karate-Gatling) share one feature-file language.
- No glue code for API tests — unlike standard Cucumber, you don't write step definitions; Karate has built-in steps for HTTP, JSON, XML, and assertions.
- JSON-native assertions —
match response == { id: '#string', email: '#regex .*@example\\.com' }reads naturally. - Parallel execution built-in —
Runner.path(...).parallel(N). - JS scripting inside features — for non-trivial setup that doesn't belong in test data.
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.
- 10d ago First seen · 264 lines · 125 tokens per session scan A a44fe23f47bc
karate is a skill published in the GitHub repository aks-builds/quality-skills (2 stars, last pushed today), licensed MIT. It adds 125 tokens to every session and 2,384 once invoked, about $0.0006 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
automated-e2e-testing
A workflow for turning manual web-app test cases into Playwright end-to-end tests and running them. End-to-end tests check a complete user flow through the website.
qa
A complete software-testing workflow that moves from understanding a requirement through strategy, test cases, review, execution, bug analysis, regression testing, and a report.
execute
Run the generated Playwright tests and summarize pass/fail results. Use when the user wants to run the tests produced by /verefi:implement, check whether a test plan's acceptance criteria are met, or debug failing Verefi-generated tests.
no-vibes
Use when completion depends on an end-to-end outcome across components, environments, or external systems.
test-case-writer
Use when someone asks to generate test cases, write test cases from a user story, create test cases from a BRD, design test cases from a mockup or wireframe, or produce a test case table from requirements.
api-tester
A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.