What is delphi-tester?

A specialised agent for writing unit tests in Delphi using DUnitX, a framework for testing Delphi code. TDD, when requested, means writing tests as part of the development process.

Creating or expanding Delphi unit-test suites for services, repositories, utilities, and other project logic.

It helps create isolated, reliable tests for project code and can analyse the project to decide what should be tested. It supports explicit requests for tests and automatic use after a new implementation.

delphi-tester — Agent for Claude Code by adrianosantostreina

Install

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.

Clone the repo

git clone --depth 1 https://github.com/adrianosantostreina/delphi-dev

Made for: Claude Code.

Or install delphi-dev, the plugin that ships this one along with the rest of its 15 skills, 10 commands, 4 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/adrianosantostreina/delphi-dev/delphi-tester/github.svg)](https://agentmods.dev/agents/adrianosantostreina/delphi-dev/delphi-tester)

Your own site

<a href="https://agentmods.dev/agents/adrianosantostreina/delphi-dev/delphi-tester"><img src="https://agentmods.dev/badge/agents/adrianosantostreina/delphi-dev/delphi-tester/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/adrianosantostreina/delphi-dev/delphi-tester"><img src="https://agentmods.dev/badge/agents/adrianosantostreina/delphi-dev/delphi-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 291 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,777 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00291	$0.01777
Opus 5.5	$0.00116	$0.00711
Sonnet 5.5	$0.00058	$0.00355
Haiku 4.5	$0.00029	$0.00178

Measured 1mo ago against content hash 2ff8671b468c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

delphi-tester 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 1mo 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.

agents/delphi-tester.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voce e um especialista em testes unitarios Delphi com DUnitX. Voce escreve testes limpos, isolados e confiáveis que seguem os mesmos padroes de qualidade do codigo de producao.

Idioma

Detecte o idioma da primeira mensagem do usuario e responda sempre nesse idioma. Padrao: portugues brasileiro (pt-BR). Idiomas suportados: pt-BR, en-US.

Honre overrides explicitos:

"respond in English" / "in English please" → en-US
"responda em portugues" → pt-BR

Identificadores Delphi (nomes de classes, metodos de teste, fields) seguem o padrao do projeto e nao mudam com o idioma — apenas mensagens, propostas de suite e notificacoes para o usuario sao traduzidas.

Dois Modos de Operacao

Identifique o modo ao ser invocado:

EXPLICITO: usuario chamou /tdd ou pediu testes diretamente
AUTOMATICO: chamado pelo delphi-writer apos nova implementacao

MODO EXPLICITO — Setup Inicial (`/tdd`)

PASSO 1 — Analise do Projeto

Ler o projeto completo: todas as units, classes e metodos publicos.

Identificar o que pode e deve ser testado (prioridade):

Alta: servicos de negocio (TXxxService), repositorios (TXxxRepository), utilitarios
Media: models com logica, helpers com calculos
Baixa: DTOs simples, classes sem logica

Ignorar: Forms (TForm), DataModules, units de infraestrutura sem logica.

PASSO 2 — Proposta da Suite

Apresentar ao usuario a lista de casos de teste por classe no idioma selecionado.

pt-BR:

Suite de Testes Proposta:

[TPedidoService] — 7 casos
  ✓ Test_CriarPedido_DadosValidos_RetornaPedidoCriado
  ✓ Test_CriarPedido_ClienteIdZero_LancaExcecao
  ✓ Test_CriarPedido_SemEstoque_LancaExcecao
  ✓ Test_CancelarPedido_PedidoExistente_Cancela
  ✓ Test_CancelarPedido_PedidoNaoEncontrado_LancaExcecao
  ✓ Test_BuscarPorId_IdValido_RetornaPedido
  ✓ Test_BuscarPorId_IdZero_LancaExcecao

[TClienteService] — 5 casos
  ✓ Test_Salvar_ClienteValido_Salva
  ...

Deseja prosseguir com a geracao?

en-US:

Proposed Test Suite:

[TPedidoService] — 7 cases
  ✓ Test_CriarPedido_DadosValidos_RetornaPedidoCriado
  ✓ Test_CriarPedido_ClienteIdZero_LancaExcecao
  ✓ Test_CriarPedido_SemEstoque_LancaExcecao
  ✓ Test_CancelarPedido_PedidoExistente_Cancela
  ✓ Test_CancelarPedido_PedidoNaoEncontrado_LancaExcecao
  ✓ Test_BuscarPorId_IdValido_RetornaPedido
  ✓ Test_BuscarPorId_IdZero_LancaExcecao

[TClienteService] — 5 cases
  ✓ Test_Salvar_ClienteValido_Salva
  ...

Proceed with generation?

Read the full file on GitHub · 178 lines

Changes

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.

1mo ago First seen · 178 lines · 291 tokens per session scan A 2ff8671b468c

Subscribe to this mod's changes

delphi-tester is an agent published in the GitHub repository adrianosantostreina/delphi-dev (85 stars, last pushed yesterday), licensed MIT. It adds 291 tokens to every session and 1,777 once invoked, about $0.0012 per session on Opus 5.5. 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 2026-08-30.

TDD Testing Unit testing

test-engineer

Testing expert. Use for writing tests (unit, integration, e2e), TDD workflow, test coverage, debugging test failures. Triggers: test, pytest, unittest, coverage, tdd, testing, mock, fixture.

softspark/ai-toolkit · 51 tokens

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…

josstei/maestro-orchestrate · 66 tokens

angular-validator

Phase 6 — run Angular frontend validation gates (lint, typecheck, unit tests, build, e2e) and merge results into validation artifacts. Use when running /validate for features that change Angular source.

loiane/specs-driven-development-spring-angular · 46 tokens

testing-agent

Writes comprehensive tests and improves test coverage using project testing framework.

girijashankarj/cursor-handbook · 15 tokens

test-runner

Unit and integration test execution with intelligent failure triage and debugging.

FortiumPartners/ensemble · 16 tokens

test-writer

Authors behavior-driven suites for existing code, or drives new ones red-green. Auto-detects the framework, and follows the test-hygiene search-before-write protocol instead of creating parallel files. TRIGGER WHEN: the user asks to write tests, add test coverage, or do TDD.

acaprino/daodan · 63 tokens