A tool that reads existing Delphi source code and produces a software specification document. Delphi is a programming language and development environment.

Use it to create a specification for a whole Delphi project or business module, in Brazilian Portuguese or English.

It documents an existing system without requiring interviews, while linking requirements to the code it found.

delphi-spec — Skill 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.

Any agent

npx skills add adrianosantostreina/delphi-dev --skill delphi-spec

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/skills/adrianosantostreina/delphi-dev/delphi-spec.svg)](https://agentmods.dev/skills/adrianosantostreina/delphi-dev/delphi-spec)

Your own site

<a href="https://agentmods.dev/skills/adrianosantostreina/delphi-dev/delphi-spec"><img src="https://agentmods.dev/badge/skills/adrianosantostreina/delphi-dev/delphi-spec.svg" alt="Measured on agentmods" height="20"></a>

Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,248 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	$0.00140	$0.01248
Opus 5	$0.00070	$0.00624
Sonnet 5	$0.00028	$0.00250
Haiku 4.5	$0.00014	$0.00125

Measured 7d ago against content hash a2c5995cf448, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

delphi-spec 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 7d 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-spec/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Especificacao de Software (SPEC) — Analise de Codigo-Fonte

Voce e especialista em engenharia reversa de requisitos: lê o codigo-fonte Delphi existente e produz uma SPEC completa, rastreavel e acionavel — sem entrevistar o usuario.

Escopo da SPEC

Uma SPEC cobre o projeto inteiro ou um modulo de negocio. Nunca cubra uma unica unit ou classe.

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

Selecao do template da SPEC:

pt-BR → references/spec-template.md
en-US → references/spec-template.en.md

Os marcadores de inferencia tambem seguem o idioma:

pt-BR → [INFERIDO]
en-US → [INFERRED]

Protocolo de Geracao de SPEC

Execute as etapas abaixo em ordem, sem interromper o usuario com perguntas:

1. SCAN

Use Glob para localizar todos os arquivos .pas, .dfm, .dpr, .dproj no diretorio de trabalho atual.
Identifique: arquivo principal do projeto (.dpr), forms (.dfm + .pas), services, repositories, entities, datamodules.

2. READ

Leia os arquivos relevantes: units de dominio, services, repositories, forms principais, datamodules.
Priorize arquivos com regras de negocio, validacoes e acesso a dados.

3. EXTRACT

Mapeie as seguintes informacoes diretamente do codigo:

Atores: identifique pelos forms e permissoes encontrados no codigo
Requisitos Funcionais (RF): extraia dos metodos publicos, acoes de botoes, eventos de forms
Requisitos Nao Funcionais (RNF): infira da tecnologia usada (versao Delphi, banco de dados, SO alvo)
Regras de Negocio (RN): extraia das validacoes, guards, if/raise encontrados no codigo
Casos de Uso (UC): derive dos fluxos de tela e das acoes principais dos forms
Modelo de Dados: extraia das entidades, records, queries e estruturas de banco encontradas
Integracoes: identifique chamadas HTTP, COM, DLL, WebService no codigo
Restricoes Tecnicas: versao Delphi, banco de dados, plataforma alvo (Win32/Win64/Android/iOS)

Read the full file on GitHub · 109 lines

Files

What ships with it

2 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.

7d ago First seen · 109 lines · 140 tokens per session scan A a2c5995cf448

Subscribe to this mod's changes

delphi-spec is a skill published in the GitHub repository adrianosantostreina/delphi-dev (79 stars, last pushed 3d ago), licensed MIT. It adds 140 tokens to every session and 1,248 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.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens