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 agentmods add skills/vlad-ryzhkov/ai-context-engineering-for-qa/api-tests-javanpx skills add vlad-ryzhkov/ai-context-engineering-for-qa --skill api-tests-javagit clone --depth 1 https://github.com/vlad-ryzhkov/ai-context-engineering-for-qaWhat 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 | $0.00028 | $0.00231 |
| Opus 5 | $0.00014 | $0.00115 |
| Sonnet 5 | $0.00006 | $0.00046 |
| Haiku 4.5 | $0.00003 | $0.00023 |
Grade A, and why
api-tests-java 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 2d 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.
What it actually says
INSTRUCTIONS
You are acting as the QA Automation Lead.
Read AGENTS.md to understand the project philosophy and tech stack.
LOGIC SOURCE
Do NOT guess the procedure and do NOT output anything yet. You MUST use your file-reading tool to fetch and strictly follow:
- First, read the core agent context:
.claude/qa_agent.md - Second, read the specific skill protocol:
.claude/skills/api-tests-java/SKILL.md - Execute based STRICTLY on the logic and output format defined in those files.
CRITICAL REMINDERS
- Use
java.net.http.HttpClient(JDK 17 built-in) — RestAssured, OkHttp, Retrofit are BANNED. - Assertions must use AssertJ with
.as("message")on every assertion. - Serialization: Jackson (PropertyNamingStrategies.SNAKE_CASE) only.
- Async waiting: Awaitility, not Thread.sleep().
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.
- 2d ago First seen · 26 lines · 28 tokens per session scan A e7e5376695ff
api-tests-java is a skill published in the GitHub repository vlad-ryzhkov/ai-context-engineering-for-qa (6 stars, last pushed 25d ago), licensed Unlicense. It adds 28 tokens to every session and 231 once invoked, about $0.0001 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
api-tests
Generate Production-Ready API tests in Kotlin (JUnit5, Allure) from specifications.
init-agent
Generate qaagent.md — AI job description with QA culture, principles and anti-patterns.
init-project
Initialize CLAUDE.md for a new QA project with stack, protocols and conventions.
init-skill
Generate new skills with interactive workflow, checkpoints and iterative refinement.
kotlin-in-action
Apply Kotlin In Action practices (Elizarov, Isakova, Aigner, Jemerov, 2nd Ed). Covers Basics (Ch 1-3: functions, extensions, default args), Classes (Ch 4: sealed, data, delegation, companion objects), Lambdas (Ch 5-6: functional APIs, sequences, scope functions), Nullability (Ch 7-8: safe calls, Elvis, platform types…
auditor
Independent Quality Gatekeeper — represents end user perspective, last line of defense before merge.