skill-reverse

skill-reverse is a cursor rule for Cursor from dewtech-technologies/dare-method. It costs 0 tokens per session (1,620 once invoked), scanned A, original, MIT.

A guide for understanding an existing codebase before changing it. It fills in the project’s purpose, responsibilities, inferred behavior, and flow diagrams after an automated scan.

In plain words
What is it for?
It helps document legacy projects, create a preliminary architecture, and identify missing information before writing new requirements.
Why use it?
It reduces guesswork when working on older or unfamiliar software and clearly marks which conclusions are confirmed or inferred.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/dewtech-technologies/dare-method/skill-reverse
Clone the repo
git clone --depth 1 https://github.com/dewtech-technologies/dare-method

Made for: Cursor.

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 skill-reverse

README.md
[![agentmods](https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-reverse.svg)](https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-reverse)
Your own site
<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-reverse"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-reverse.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,620 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01620
Opus 5 $0.00000 $0.00810
Sonnet 5 $0.00000 $0.00324
Haiku 4.5 $0.00000 $0.00162

Measured yesterday against content hash 725d09c1d7db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-reverse 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 yesterday.

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.

implementations/cursor/.cursor/rules/skill-reverse.mdc · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Reverse — Engenharia Reversa (Fase 0)

Esta skill é a camada semântica da engenharia reversa. Ela roda depois do comando dare reverse, que já varreu o código e gerou os esqueletos determinísticos. Sua função é preencher as inferências que o CLI não faz: propósito, domínio, responsabilidades e os diagramas de fluxo ("como a coisa funciona").

Pré-requisito: rodar dare reverse antes (gera DARE/IDEIA.md, DARE/REVERSE/module-*.md e DARE/REVERSE/reverse-facts.json). Se não existirem, peça para rodar dare reverse primeiro.

Quando usar

  • O usuário quer entender / documentar um projeto legado antes de adotar o DARE.
  • Acabou de rodar dare reverse e os artefatos têm seções <!-- AGENT: ... --> em aberto.
  • O objetivo é gerar uma pré-arquitetura (IDEIA.md) que depois vira DESIGN.md.

Marcação de confiança (obrigatória)

Ao preencher cada <!-- AGENT -->, marque cada afirmação com seu nível de confiança + evidência:

  • - 🟢 <claim>. + `arquivo:linha`CONFIRMED: evidência direta no código.
  • - 🟡 <claim>. + `arquivo:linha`INFERRED: padrão/dedução; pode estar errado.
  • - 🔴 <claim>. → ver gaps.mdGAP: não determinável pelo código.

Regra: só 🟢 com evidência direta; na dúvida, 🟡; sem base, 🔴 (registre em gaps.md). Os fatos estruturais (caminho, LOC, deps) já vêm pré-marcados 🟢 pelo CLI — não os altere.

O que fazer

1. Carregar os fatos (não re-varrer tudo)

  • Leia DARE/REVERSE/reverse-facts.json — fonte de fatos determinística (stack, módulos, LOC, grafo de dependências). Confie nela para o inventário.
  • Para cada módulo, abra 2-5 arquivos representativos (entrypoints, controllers, services, models) — o suficiente para inferir responsabilidade e fluxo. Não leia o módulo inteiro.

2. Preencher DARE/IDEIA.md

Substitua cada bloco <!-- AGENT: ... -->:

  • Propósito Inferido — 2-4 frases: o que o software faz e por quê.
  • Domínio & Conceitos — entidades de negócio + glossário.
  • Modelo de Dados (reconstruído) — entidades, campos-chave, relacionamentos.
  • Superfície de API — endpoints inferidos de rotas/controllers.
  • Fluxo do Sistema — um flowchart TD Mermaid do caminho principal de request/dados atravessando os módulos.
  • ⚠️ Incertezas / Gaps — o que NÃO deu pra inferir + perguntas objetivas para o humano.

Read the full file on GitHub · 108 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.

  1. yesterday First seen · 108 lines · 0 tokens per session scan A 725d09c1d7db

Subscribe to this mod's changes

skill-reverse is a cursor rule published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,620 tokens. 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 2026-09-03.