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 brody-0125/my-claude-skills --skill sub-test-engineergit clone --depth 1 https://github.com/brody-0125/my-claude-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/brody-0125/my-claude-skills/sub-test-engineer)<a href="https://agentmods.dev/skills/brody-0125/my-claude-skills/sub-test-engineer"><img src="https://agentmods.dev/badge/skills/brody-0125/my-claude-skills/sub-test-engineer/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/brody-0125/my-claude-skills/sub-test-engineer"><img src="https://agentmods.dev/badge/skills/brody-0125/my-claude-skills/sub-test-engineer.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 | $0.00093 | $0.06519 |
| Opus 5 | $0.00046 | $0.03259 |
| Sonnet 5 | $0.00019 | $0.01304 |
| Haiku 4.5 | $0.00009 | $0.00652 |
Grade A, and why
sub-test-engineer 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 11d 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 — 606 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub Test Engineer — Type-Aware Testing Workflow Agent
An agent that generates high-quality, convention-compliant tests through the Analyze → Strategize → Generate → Validate workflow, leveraging type system information for intelligent test case discovery.
Role
A testing-specialized workflow agent that generates comprehensive, type-aware tests for Java/Kotlin/TypeScript/Go backend projects. Unlike general coding agents that treat testing as a verification step, this agent treats test quality as the primary output. It automatically detects the project's test infrastructure, analyzes code-under-test complexity, selects appropriate testing techniques (unit, property-based, contract, architecture), and iterates until coverage and mutation-kill targets are met.
Core Principles
- Type-First Analysis: Extract type signatures, class hierarchies, sealed classes, enums, and validation annotations to drive test case discovery
- Multi-Technique Orchestration: Select the right testing technique for each code layer (property-based for domain logic, contract for APIs, architecture tests for structure)
- Coverage-Guided Iteration: Use line/branch coverage as feedback signal to generate targeted tests for uncovered code paths
- Test Quality over Quantity: Validate test effectiveness via mutation testing — a test suite that doesn't kill mutants is incomplete
- Project Pattern Conformance: Learn existing test patterns (naming, structure, fixtures, assertions) and generate tests that match the project style
Input Parsing and Ambiguity Resolution
Input Classification
Parse user input and classify into one of:
1. CLEAR target + mode → "OrderService 테스트 생성. loop 3"
→ target=OrderService, mode=all-in-one, loop=3
→ Proceed to Phase 0
2. CLEAR phase command → "analyze: PaymentService"
→ target=PaymentService, mode=step-by-step, phase=analyze
→ Jump to specified phase
3. CLEAR technique → "property-test: OrderValidator"
→ target=OrderValidator, technique=property-based, mode=technique-specific
→ Skip Phase 2 (Strategize)
4. AMBIGUOUS target → "테스트 해줘", "테스트 좀 추가해줘"
→ No target specified → trigger Target Resolution
→ Ask user or infer from git diff
5. SCOPE too broad → "전체 프로젝트 테스트 생성"
→ Recommend narrowing scope to a package or module
→ Suggest top 3 packages by test debt
What ships with it
60 files 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.
- references/architecture-testing.md 2.9 KB
- references/contract-testing.md 2.0 KB
- references/go-testing-techniques.md 10 KB
- references/integration-testing-techniques.md 2.5 KB
- references/mutation-testing.md 2.0 KB
- references/property-based-testing.md 1.8 KB
- references/test-quality-checklist.md 2.9 KB
- references/unit-testing-techniques.md 1.9 KB
- resources/analyze-protocol.md 17 KB
- resources/error-handling-framework.md 7.7 KB
- resources/error-playbook.md 20 KB
- resources/generate-protocol.md 14 KB
- resources/multi-module-context.md 8.8 KB
- resources/phase-index.md 3.6 KB
- resources/strategize-protocol.md 7.9 KB
- resources/test-discovery-protocol.md 5.8 KB
- resources/validate-protocol.md 13 KB
- resources/validation-tiers.md 1.6 KB
- rules/__tests__/go/extract-functions-test.yml 1.3 KB
- rules/__tests__/go/extract-interface-test.yml 1.3 KB
- rules/__tests__/go/extract-struct-test.yml 1.5 KB
- rules/__tests__/go/extract-validation-test.yml 1.6 KB
- rules/__tests__/java/extract-constructors-test.yml 505 B
- rules/__tests__/java/extract-methods-test.yml 836 B
- rules/__tests__/java/extract-validation-test.yml 672 B
- rules/__tests__/kotlin/extract-constructors-test.yml 419 B
- rules/__tests__/kotlin/extract-functions-test.yml 455 B
- rules/__tests__/typescript/extract-constructors-test.yml 499 B
- rules/__tests__/typescript/extract-methods-test.yml 515 B
- rules/go/extract-functions.yml 495 B
- rules/go/extract-interface.yml 603 B
- rules/go/extract-struct-hierarchy.yml 639 B
- rules/go/extract-validation.yml 678 B
- rules/java/extract-annotations.yml 357 B
- rules/java/extract-class-hierarchy.yml 337 B
- rules/java/extract-constructors.yml 387 B
- rules/java/extract-methods.yml 469 B
- rules/java/extract-validation.yml 532 B
- rules/kotlin/extract-annotations.yml 326 B
- rules/kotlin/extract-class-hierarchy.yml 228 B
- rules/kotlin/extract-constructors.yml 432 B
- rules/kotlin/extract-functions.yml 412 B
- rules/kotlin/extract-validation.yml 563 B
- rules/typescript/extract-class-hierarchy.yml 346 B
- rules/typescript/extract-constructors.yml 470 B
- rules/typescript/extract-decorators.yml 318 B
- rules/typescript/extract-methods.yml 340 B
- rules/typescript/extract-validation.yml 570 B
- scripts/agent-teams/aggregate-results.sh 7.7 KB runs code
- scripts/agent-teams/detect-modules.sh 9.1 KB runs code
- scripts/agent-teams/partition-targets.sh 9.7 KB runs code
- scripts/agent-teams/poll-inbox.sh 6.6 KB runs code
- scripts/agent-teams/shutdown-team.sh 5.2 KB runs code
- scripts/agent-teams/spawn-teammate.sh 3.9 KB runs code
- scripts/agent-teams/team-cli.sh 6.1 KB runs code
- scripts/benchmark/check-regression.sh 9.7 KB runs code
- scripts/benchmark/collect-metrics.sh 5.7 KB runs code
- scripts/benchmark/compare-runs.sh 6.5 KB runs code
- scripts/benchmark/generate-report.sh 2.4 KB runs code
- scripts/benchmark/projects/nestjs-realworld.yml 598 B
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.
- 11d ago First seen · 606 lines · 93 tokens per session scan A d7090878f6ea
sub-test-engineer is a skill published in the GitHub repository brody-0125/my-claude-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 93 tokens to every session and 6,519 once invoked, about $0.0005 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
galvanize
Turn the chosen design into mobilized work — a brief, vertical slices with acceptance criteria, and agreed test seams. Use when a tracked piece of work is at its galvanizing stage.
testing
Design test strategy using Beck's Test Desiderata — which properties matter, which tradeoffs to make. Use when the user asks "how should I test this", "what tests do I need", "review my test strategy", "is this well-tested", or when planning tests for a new feature or refactor.
autoworker
Auto-loop execution workflow with quality gates. Use when starting any non-trivial implementation task. Provides automatic task decomposition, code implementation, testing (L1-L4), and iterative quality gates until completion. Invoke with /autoworker.
subtask-plan
Complete subtask verification plan: upstream traceability table + L1-L4 test plan + self-check. Call after autoworker:subtask-init. Makes subtask ready for code implementation.
subtask-update
Update subtask with fixes or new steps. Two trigger modes: (A) Auto-called by autoworker:gate-check on FAIL — reads FAIL info, adds supplementary steps. (B) User calls with a finding/bug during testing — diagnoses, fixes, updates subtask. Both modes end by invoking autoworker:dispatch to re-enter the loop.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.