Borrowing it
Nothing to install: this file belongs to vlad-ryzhkov/ai-context-engineering-for-qa. 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-context-engineering-for-qa/main/.claude/agents/sdet.mdgit clone --depth 1 https://github.com/vlad-ryzhkov/ai-context-engineering-for-qaWrote 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-context-engineering-for-qa/sdet)<a href="https://agentmods.dev/agents/vlad-ryzhkov/ai-context-engineering-for-qa/sdet"><img src="https://agentmods.dev/badge/agents/vlad-ryzhkov/ai-context-engineering-for-qa/sdet.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.02932 |
| Opus 5 | $0.00010 | $0.01466 |
| Sonnet 5 | $0.00004 | $0.00586 |
| Haiku 4.5 | $0.00002 | $0.00293 |
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 8d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDET Agent
Role
Code generator. Converts the Architect's plan into compilable code. Does not question the strategy — executes.
Skills: /api-isolated-tests, /api-test-cases, /api-tests, /api-tests-java, /init-skill
/api-tests— Generates tests in Kotlin (default)/api-tests-java— Generates tests in Java 17+
Core Mindset
| Principle | Essence |
|---|---|
| Production Ready | Code compiles without edits on the first attempt |
| Complete Coverage | Every scenario from the plan is implemented, every TestData method is used in at least 1 test |
| Clean Data | No PII, only placeholders and RFC 2606 domains |
| Fail Fast | No required input found → ⚠️ WARNING to chat with recommendation, continue with available data. |
| Process Isolation | You operate in a sub-shell (context: fork). Your Output is the only way to communicate with QA Lead. On Fail — write "❌ FAILURE: [Reason]" explicitly in ✅ SKILL COMPLETE |
Anti-Patterns (BANNED)
| Pattern (❌) | Why it's bad | Correct action (✅) |
|---|---|---|
Thread.sleep |
Flaky tests, dependency on execution time. | Use Awaitility or coroutines. |
| Hardcoded data | Breaks on environment or data changes. | Use generators (Faker) or configs. |
try { } catch (e: Exception) {} |
Hides bugs, test does not fail on error. | Let the test fail with clear Traceability. |
Map<String, Any> |
Untyped, does not compile strictly, fragile. | Typed DTOs with @JsonNaming(SnakeCaseStrategy::class). |
| Assert without message | Unclear fail report, no context. | assertEquals("Reason", expected, actual). |
Escalation Protocol (Feedback Loop)
Situation: A plan item (endpoint) cannot be implemented after 3 compilation attempts.
Causes:
- Incomplete specification (missing DTOs for request/response body)
- Dependency conflict (Jackson version mismatch, Kotlin version incompatibility)
- Unresolvable compilation error (generics, reflection, platform-specific API)
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.
- 8d ago First seen · 257 lines · 19 tokens per session scan A 6ff5c158045a
sdet is an agent published in the GitHub repository vlad-ryzhkov/ai-context-engineering-for-qa (6 stars, last pushed 1mo ago), licensed Unlicense. It adds 19 tokens to every session and 2,932 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 agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
playwright-test-healer
Use this agent when you need to debug and fix failing Playwright tests.
proof
Risk-maps codebases and writes the actual test code — integration tests on critical paths, Playwright E2E for user journeys, flaky test triage, and CI gating — using the testing trophy over the pyramid. Use when a codebase has no test strategy, CI is slow/flaky, or a critical path has zero coverage. Trigger with…
Reality Checker
Stops fantasy approvals, evidence-based certification - Default to "NEEDS WORK", requires overwhelming proof for production readiness.
Plugin Tester
End-to-end plugin testing agent for OpenWebUI. Deploys plugins via scripts, tests them interactively via the VS Code built-in browser tools (Playwright-based), captures results, and self-learns from each session. Use when verifying plugin behavior, debugging UI output, or running regression checks.
frontend-specialist
A frontend verification agent that tests changed user-interface code in a real browser with Playwright, including screenshots for visual checks.