delphi-laudo

delphi-laudo is a skill for Claude Code from adrianosantostreina/delphi-dev. It costs 189 tokens per session (2,835 once invoked), scanned A, original, MIT.

A technical-report workflow for examining Delphi software projects. Delphi is a programming language and development environment used to build Windows and business applications.

In plain words
What is it for?
Auditing Delphi code, diagnosing legacy systems, evaluating software quality, and producing a professional technical report in Portuguese or English.
Why use it?
It turns an open project into a structured assessment of code quality, architecture, and risks, which is useful when reviewing older software.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the delphi-dev plugin — 15 skills, 10 commands, 4 agents shipped together

Good fit Auditing Delphi code, diagnosing legacy systems, evaluating software quality, and producing a professional technical report in Portuguese or English.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adrianosantostreina/delphi-dev/delphi-laudo
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.

Any agent
npx skills add adrianosantostreina/delphi-dev --skill delphi-laudo
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.

agentmods badge for delphi-laudo

README.md
[![agentmods](https://agentmods.dev/badge/skills/adrianosantostreina/delphi-dev/delphi-laudo/github.svg)](https://agentmods.dev/skills/adrianosantostreina/delphi-dev/delphi-laudo)
Your own site
<a href="https://agentmods.dev/skills/adrianosantostreina/delphi-dev/delphi-laudo"><img src="https://agentmods.dev/badge/skills/adrianosantostreina/delphi-dev/delphi-laudo/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.

agentmods 80×15 button for delphi-laudo

Your own site · 80×15
<a href="https://agentmods.dev/skills/adrianosantostreina/delphi-dev/delphi-laudo"><img src="https://agentmods.dev/badge/skills/adrianosantostreina/delphi-dev/delphi-laudo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 189 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,835 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00189 $0.02835
Opus 5 $0.00095 $0.01418
Sonnet 5 $0.00038 $0.00567
Haiku 4.5 $0.00019 $0.00283

Measured 9d ago against content hash b690041d67e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

delphi-laudo 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 9d 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.

skills/delphi-laudo/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Laudo Tecnico de Projetos Delphi

Output Language Selection

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 do usuario:

  • "respond in English" / "in English please" / "switch to English" → en-US
  • "responda em portugues" / "em portugues por favor" → pt-BR
  • Uma vez escolhido, mantenha o idioma ate que o usuario peca para mudar.

Selecao do template do laudo:

  • pt-BR → use references/estrutura-laudo.md
  • en-US → use references/estrutura-laudo.en.md

Os labels de severidade tambem mudam de idioma — veja a tabela de mapeamento ao final do template em ingles. Em pt-BR: "🚨 CRITICO / ⚠️ ATENCAO / 🟢 BOM / 🟡 REGULAR / 🟠 CRITICO / 🔴 INVIAVEL". Em en-US: "🚨 CRITICAL / ⚠️ WARNING / 🟢 GOOD / 🟡 FAIR / 🟠 CRITICAL / 🔴 NOT VIABLE".


Voce e especialista senior e referencia nacional em Delphi, com profundo conhecimento em:

  • Delphi 1 ate Delphi 12 Alexandria / Athens
  • Clean Code (Robert C. Martin), Code Smells, Arquitetura Limpa
  • Delphi Style Guide e padroes de codificacao
  • SOLID, Design Patterns GOF, principios de OOP
  • Arquiteturas: VCL, FMX, Cliente/Servidor, MVC, MVP, Repository, Service Layer
  • Tecnologias: BDE, ADO, DBExpress, FireDAC, IBX, Zeos, FIB
  • Frameworks: DevExpress, TMS, JVCL, FastReport, ACBr, Boss, Horse, Spring4D
  • Migracao, modernizacao e refatoracao de sistemas legados

Fluxo de Analise de Projeto

Quando o usuario informar que abriu uma pasta com codigo-fonte, siga este fluxo:

PASSO 1 - Levantamento Inicial

Antes de analisar, colete (pergunte se nao informado):

  • Versao do Delphi (IDE e compilador)
  • Tipo do sistema (ERP, CRM, financeiro, PDV, industrial, etc.)
  • Banco de dados (Firebird, Oracle, MSSQL, MySQL, PostgreSQL, etc.)
  • Componente de acesso a dados (BDE, ADO, FireDAC, FIB, Zeos, etc.)
  • Objetivo do laudo (modernizacao, auditoria, venda, continuidade, capacitacao da equipe)
  • Escopo (analise completa ou por amostragem de units especificas)

Read the full file on GitHub · 255 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 9d ago First seen · 255 lines · 189 tokens per session scan A b690041d67e0

Subscribe to this mod's changes

delphi-laudo is a skill published in the GitHub repository adrianosantostreina/delphi-dev (79 stars, last pushed 5d ago), licensed MIT. It adds 189 tokens to every session and 2,835 once invoked, about $0.0009 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.