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 rules/stramp/lost-mines-phandelver/test-driven-development-practicesgit clone --depth 1 https://github.com/Stramp/Lost-Mines-PhandelverWhat 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 | $0.02049 | $0.02049 |
| Opus 5 | $0.01025 | $0.01025 |
| Sonnet 5 | $0.00410 | $0.00410 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade A, and why
test-driven-development-practices 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧪 Test-Driven Development (TDD) - Practices
📋 Checklist TDD Obrigatório
BEFORE escrever QUALQUER código crítico, SEMPRE verificar:
-
[ ] Escrevi o teste que falha (Red)?
- Teste define comportamento esperado?
- Teste pode detectar erros?
- Teste compila (mesmo que função não exista ainda)?
-
[ ] O teste é atômico e focado?
- Testa uma única coisa?
- Nome descritivo (
<Scenario>_<Condition>_<ExpectedResult>)? - Independente de outros testes?
-
[ ] O teste NÃO tem lógica interna?
- Valor esperado é hardcoded (não calculado)?
- Teste chama a função real do módulo oficial?
- Mock apenas simula dados (não implementa lógica)?
- Teste falharia se o código estivesse errado?
- Não há lógica de cálculo no teste?
-
[ ] A função será testável isoladamente?
- Sem dependências ocultas?
- Parâmetros claros?
- Retorno verificável?
-
[ ] Implementação mínima faz teste passar (Green)?
- Solução mais simples possível?
- Teste fica verde?
- Comportamento básico funciona?
-
[ ] Refatorei com segurança (Refactor)?
- Testes ainda passam?
- Código melhorado sem quebrar comportamento?
- Clean Code aplicado?
Se QUALQUER resposta for NÃO → PARAR e corrigir antes de continuar
⚠️ Exceções: Quando Test-After é Aceitável
Test-After (escrever teste depois) é aceitável quando:
-
❌ Getters/Setters simples (sem lógica)
// Não precisa de teste primeiro float GetHealth() const { return Health; } void SetHealth(float NewHealth) { Health = NewHealth; } -
❌ Wrappers diretos de API Unreal (sem lógica customizada)
// Wrapper simples, testar depois se necessário UDataTable* GetRaceDataTable() const { return RaceDataTable; } -
❌ Integração com Blueprint (testar depois pode ser mais prático)
// Integração complexa, testar depois UFUNCTION(BlueprintCallable) void InitializeFromBlueprint(UCharacterSheetDataAsset* Asset);
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 · 252 lines · 2,049 tokens per session scan A 360ba65c5028
test-driven-development-practices is a cursor rule published in the GitHub repository Stramp/Lost-Mines-Phandelver (2 stars, last pushed 9mo ago), licensed MIT. It adds 2,049 tokens to every session, about $0.0102 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 cursor rules, from other repositories
unit-tests-tdd
TDD required for behavior changes; ≥80% package coverage on touched packages; unit-test conventions.
elite-developer
Principal Full-Stack Engineer for surgical implementation, strict TDD, complex debugging, and UI construction. Enforces the Agentic Company pipeline and high-rigor engineering standards. This agent contains the full knowledge of TDD, Systematic Debugging, Build Error Resolution, and Refactoring.
mcpnuke-tests
Test conventions for mcpnuke — enforces TDD workflow.
test_first_workflow
Enforce test-first or test-alongside development. Load when implementing new features, APIs, or UI components.
android_unit_testing_bdd
Unit testing best practices with BDD style.
03-testing
Testing requirements — test-before-commit policy, coverage expectations, and test quality standards.