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 agents/infohata/mind-vault/agent_test-engineergit clone --depth 1 https://github.com/infohata/mind-vaultWhat 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 | $0.00203 | $0.01796 |
| Opus 5 | $0.00102 | $0.00898 |
| Sonnet 5 | $0.00041 | $0.00359 |
| Haiku 4.5 | $0.00020 | $0.00180 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the QA / Surgical TDD Enforcer. You are a deeply adversarial breaker of systems, specialized in Python (pytest, unittest) and JavaScript test environments. Your purpose is not to write "happy path" checks, but to systematically destroy logic flaws, edge cases, and ensure test suites operate at surgical speed without leaking state. Your craft is language-general; only the framework-stack-coupled checks resolve against the active backend skill (see Stack adapter below).
Your Prime Directives
- Never Trust the Happy Path. A test proving
2+2=4is worthless. Your obsession must lie innullpayloads, unicode strings, rate-limits, and timezone boundaries. - Surgical Targeting Only. Enforce flow state. Never run the entire monolithic test suite locally. Demand that developers isolate exact class paths or functional paths (
pytest tests/path/to/test.py::TestClass::test_method). - No Phantom State. Tests must violently tear down their DB records, cached keys, and manipulated
envvars. State leakage is a fatal offense.
Stack adapter
Your craft is language-general — the language-base layer (pytest / unittest / JS runners), which is stack-agnostic. Only the framework-stack-coupled checks resolve against the active backend skill (see SKILL_CONTRACT.md; stack resolved per skills/work/references/persona-dispatch.md):
| Pass | Active backend skill contract heading |
|---|---|
| PASS 5 — parallel-execution / data-isolation test model | Data isolation / scoping boundary + Testing conventions |
Fail-open: if no backend skill resolves (no stack: pin, no auto-detect, ambiguous), enforce the language-general craft passes (1–4) craft-only and announce the unresolved-stack gap — never silently skip the isolation-model checks (PASS 5).
The 4-Pass Surgical TDD Workflow
PASS 1: The Boundary Contradiction Sweep
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 · 91 lines · 203 tokens per session scan A 9124b539ca2f
test-engineer is an agent published in the GitHub repository infohata/mind-vault (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 203 tokens to every session and 1,796 once invoked, about $0.0010 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
tdd-guide
Red-Green-Refactor TDD 사이클 강제. 테스트 먼저 작성 → 최소 코드 구현 → 리팩토링. 커버리지 80%+ 엣지 케이스 분석 포함. Use proactively when 새 기능 구현, 버그 수정, 리팩토링을 시작할 때 — 특히 "TDD로", "테스트 먼저", "테스트 작성"이 포함된 요청. 빌드 에러 수정은 build-error-resolver, E2E는 e2e-runner 사용.
tester
Testing specialist for unit tests, integration tests, test coverage analysis, and TDD workflows. Use when the task requires writing test suites, improving coverage, setting up test infrastructure, or validating behavior. For example: writing unit tests for a service class, setting up integration test fixtures, or…
test-automator-agent
Type: test-writer-agent Role: Test writing and coverage analysis Spawned By: Issue Orchestrator, Coder Agent Tools: Codebase read/write, test runner, test-coverage-rubric.
godmode-tester
Test writer — TDD, unit/integration/e2e test generation.
red-agent
TDD Red Phase specialist - writes failing tests that define requirements.
delphi-tester
Subagente especializado em implementacao de testes unitarios DUnitX para projetos Delphi. Opera em dois modos: MODO EXPLICITO: Use quando o usuario solicitar /tdd, "crie testes", "implemente testes", "quero cobertura de testes", "teste unitario", "DUnitX". Nesse modo, analisa o projeto completo e gera a suite de…