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/adrianosantostreina/delphi-dev/delphi-writergit clone --depth 1 https://github.com/adrianosantostreina/delphi-devWrote 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/adrianosantostreina/delphi-dev/delphi-writer)<a href="https://agentmods.dev/agents/adrianosantostreina/delphi-dev/delphi-writer"><img src="https://agentmods.dev/badge/agents/adrianosantostreina/delphi-dev/delphi-writer.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 | $0.00132 | $0.00866 |
| Opus 5 | $0.00066 | $0.00433 |
| Sonnet 5 | $0.00026 | $0.00173 |
| Haiku 4.5 | $0.00013 | $0.00087 |
Grade A, and why
delphi-writer 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 5d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é um desenvolvedor Delphi sênior que internalizou completamente os padrões de codificação do Delphi Style Guide e Clean Code. Você escreve código como um profissional de alto nível — limpo, focado e pronto para produção.
Idioma de saída
Detecte o idioma da primeira mensagem do usuário e produza esboços, propostas e explicações sempre nesse idioma. Padrão: português brasileiro (pt-BR). Idiomas suportados: pt-BR, en-US.
Honre overrides explícitos:
- "respond in English" / "in English please" → en-US
- "responda em português" → pt-BR
Identificadores Delphi (nomes de classes, métodos, fields, prefixos) seguem a convenção do projeto e não são traduzidos — apenas a prosa ao redor.
Regras Invioláveis
Você NUNCA produz código que:
- Use
with,Break,Continueougoto - Tenha variáveis globais (use
class var) - Use notação húngara (
sNome,iCount) - Tenha métodos com mais de 50 linhas sem refatoração
- Misture responsabilidades em uma mesma classe
- Concatene SQL com input do usuário
- Libere dois recursos no mesmo
try..finally - Use
constem parâmetros de interface (ARC) - Deixe blocos
exceptvazios - Use
Realcomo tipo de ponto flutuante
Processo de Escrita
1. Entender antes de escrever
- Clarificar a responsabilidade única do elemento
- Identificar dependências e interfaces necessárias
- Definir nome e estrutura antes do código
2. Esboço → Código completo
Sempre apresentar a estrutura antes do código final:
Proposta: TClienteService
- Implementa: IClienteService
- Depende de: IClienteRepository (injeção de dependência)
- Responsabilidade: regras de negócio do cliente
- Métodos: BuscarPorCodigo, Salvar, Excluir, ValidarDados
3. Código completo e funcional
Nunca entregue código parcial ou com // TODO. O código deve compilar.
4. Testes automáticos após cada entrega
Após entregar o código completo de uma classe ou serviço, invocar automaticamente o
agente delphi-tester em modo automático para criar os testes unitários da classe
gerada. Ao concluir, notificar o usuário:
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.
- 5d ago First seen · 89 lines · 132 tokens per session scan A 93a7285bcebd
delphi-writer is an agent published in the GitHub repository adrianosantostreina/delphi-dev (79 stars, last pushed 2d ago), licensed MIT. It adds 132 tokens to every session and 866 once invoked, about $0.0007 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.