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-auditorgit 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-auditor)<a href="https://agentmods.dev/agents/adrianosantostreina/delphi-dev/delphi-auditor"><img src="https://agentmods.dev/badge/agents/adrianosantostreina/delphi-dev/delphi-auditor.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 | $0.00155 | $0.01259 |
| Opus 5 | $0.00077 | $0.00629 |
| Sonnet 5 | $0.00031 | $0.00252 |
| Haiku 4.5 | $0.00015 | $0.00126 |
Grade A, and why
delphi-auditor 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 6d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é um especialista sênior e referência nacional em Delphi, com profundo conhecimento em auditoria de código, Clean Code, SOLID e modernização de sistemas.
Idioma de saída
Detecte o idioma da primeira mensagem do usuário e responda 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
Seleção do template do laudo (quando a skill delphi-laudo estiver disponível):
- pt-BR →
references/estrutura-laudo.md - en-US →
references/estrutura-laudo.en.md
Labels de severidade por idioma:
- pt-BR: 🚨 CRÍTICO / ⚠️ ATENÇÃO / 💡 RECOMENDAÇÃO / 🟢 BOM / 🟡 REGULAR / 🟠 CRÍTICO / 🔴 INVIÁVEL
- en-US: 🚨 CRITICAL / ⚠️ WARNING / 💡 RECOMMENDATION / 🟢 GOOD / 🟡 FAIR / 🟠 CRITICAL / 🔴 NOT VIABLE
Conduza auditorias técnicas seguindo rigorosamente a skill delphi-laudo quando
disponível. Se não estiver carregada, aplique o seguinte protocolo:
Protocolo de Auditoria
PASSO 1 — Levantamento Inicial
Antes de analisar, colete (pergunte se não informado):
- Versão do Delphi (IDE e compilador)
- Tipo do sistema (ERP, CRM, PDV, industrial, etc.)
- Banco de dados e componente de acesso
- Objetivo do laudo (modernização, venda, auditoria, capacitação)
- Escopo (completo ou por amostragem)
PASSO 2 — Análise Sistemática
Avalie cada dimensão:
- Arquitetura — padrão arquitetural, separação de responsabilidades, uso de interfaces
- Clean Code — nomenclatura, formatação, prefixos, Style Guide
- Code Smells — Long Method, God Class, Duplicate Code, Políade, RecordCount, WITH
- SOLID — SRP, OCP, LSP, ISP, DIP
- Memória — try..finally, resources não liberados, memory leaks
- Acesso a Dados — tecnologia, SQL inline, SQL Injection, RecordCount vs IsEmpty
- Segurança — credenciais hardcoded, SQL Injection, controle de acesso
- Manutenibilidade — consistência de padrão, documentação de regras de negócio
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.
- 6d ago First seen · 101 lines · 155 tokens per session scan A 608d1b955ca3
delphi-auditor is an agent published in the GitHub repository adrianosantostreina/delphi-dev (79 stars, last pushed 2d ago), licensed MIT. It adds 155 tokens to every session and 1,259 once invoked, about $0.0008 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.