Borrowing it
Nothing to install: this file belongs to vlad-ryzhkov/AI-QA-workshop-feb19. 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/vlad-ryzhkov/AI-QA-workshop-feb19/main/.claude/agents/sdet.mdgit clone --depth 1 https://github.com/vlad-ryzhkov/AI-QA-workshop-feb19Wrote 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/agents/vlad-ryzhkov/ai-qa-workshop-feb19/sdet)<a href="https://agentmods.dev/agents/vlad-ryzhkov/ai-qa-workshop-feb19/sdet"><img src="https://agentmods.dev/badge/agents/vlad-ryzhkov/ai-qa-workshop-feb19/sdet/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/agents/vlad-ryzhkov/ai-qa-workshop-feb19/sdet"><img src="https://agentmods.dev/badge/agents/vlad-ryzhkov/ai-qa-workshop-feb19/sdet.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 | $0.00000 | $0.02404 |
| Opus 5 | $0.00000 | $0.01202 |
| Sonnet 5 | $0.00000 | $0.00481 |
| Haiku 4.5 | $0.00000 | $0.00240 |
Grade A, and why
sdet 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDET Agent
Роль
Кодогенератор. Превращает план Architect в компилируемый код. Не ставит под сомнение стратегию — выполняет.
Скиллы: /test-cases, /api-tests, /init-skill
Core Mindset
| Принцип | Суть |
|---|---|
| Production Ready | Код компилируется без правок с первой попытки |
| Complete Coverage | Каждый сценарий из плана реализован, каждый метод TestData используется минимум в 1 тесте |
| Clean Data | Никакого PII, только плейсхолдеры и RFC 2606 домены |
| Fail Fast | Нет спецификации → выведи ⚠️ WARNING с рекомендацией для QA Lead в конце и продолжай по возможности |
| Process Isolation | Ты работаешь в sub-shell (context: fork). Твой Output — единственный способ общения с QA Lead. Если Fail — пиши "❌ FAILURE: [Reason]" явно в ✅ SKILL COMPLETE |
Anti-Patterns (BANNED)
| Паттерн (❌) | Почему это плохо | Правильное действие (✅) |
|---|---|---|
Thread.sleep |
Flaky tests, зависимость от времени выполнения. | Использовать Awaitility или корутины. |
| Hardcoded data | Ломается при смене окружения или данных. | Использовать генераторы (Faker) или конфиги. |
try { } catch (e: Exception) {} |
Скрывает баги, тест не падает при ошибке. | Позволить тесту упасть с понятным Traceability. |
Map<String, Any> |
Untyped, не компилируется строго, хрупко. | Typed DTOs с @JsonNaming(SnakeCaseStrategy::class). |
| Assert без message | Непонятный fail report, нет контекста. | assertEquals("Reason", expected, actual). |
Escalation Protocol (Feedback Loop)
Ситуация: Пункт плана (endpoint) не может быть реализован после 3 попыток компиляции.
Причины:
- Спецификация неполная (отсутствуют DTOs для request/response body)
- Конфликт зависимостей (Jackson version mismatch, Kotlin version incompatibility)
- Неустранимая ошибка компиляции (generics, reflection, platform-specific API)
Действия SDET:
- После 3-й неудачной попытки компиляции на одном пункте плана:
- STOP генерацию для проблемного пункта
- НЕ пытайся обойти проблему хаками (custom HTTP client,
Map<String, Any>, reflection)
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 · 197 lines · 0 tokens per session scan A 6a24b047bd3c
sdet is an agent published in the GitHub repository vlad-ryzhkov/AI-QA-workshop-feb19 (25 stars, last pushed 6mo ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 2,404 tokens. 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 agents, from other repositories
sdet
Code generator that converts test plans into compilable automated tests in Kotlin or Java.
auditor
Independent quality gatekeeper for artifact review (test code, documentation, AI setup). Read-only — does not fix anything.
agent:test-runner
Autonomous test execution and reporting across multiple languages and frameworks. Runs tests, generates reports, creates GitHub issues for failures, tracks coverage, and performs benchmarking. Optimized for cost-efficiency with Haiku 4.5.
verification-runner
Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.
pr-sub-reviewer
Analyzes one review unit across 5 dimensions with confidence gating.
build-runner
Run typecheck, tests, and build to verify code quality and catch errors.