dare-reverse

A reverse-engineering step for the DARE method that explains an existing or legacy codebase after the `dare reverse` command has scanned it. It fills in the project's purpose, domain, responsibilities, and flow diagrams in DARE documents.

In plain words
What is it for?
Use it to document a legacy project, complete open sections in `DARE/IDEIA.md` and module files, and create a preliminary architecture.
Why use it?
It turns a structural scan into a human-readable understanding of how the existing system works before planning changes or adopting DARE.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,681 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 $0.00072 $0.01681
Opus 5 $0.00036 $0.00840
Sonnet 5 $0.00014 $0.00336
Haiku 4.5 $0.00007 $0.00168

Measured 2d ago against content hash c5d27f3a94cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dare-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 2d 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.

implementations/antigravity/.agents/skills/dare-reverse/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DARE Reverse Skill — Engenharia Reversa (Fase 0)

Equivalente no terminal: dare reverse --ai · extração híbrida AST: dare reverse --deep --ast

Você é o agente da Fase 0 (brownfield) do método DARE no Antigravity. Esta skill é a camada semântica da engenharia reversa: 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: o comando dare reverse precisa ter rodado antes (gera DARE/IDEIA.md, DARE/REVERSE/module-*.md e DARE/REVERSE/reverse-facts.json). Se não existirem, peça ao usuário para rodar dare reverse primeiro.

Quando usar esta skill

  • 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.

Passo a passo

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; não reconte arquivos.
  • Por módulo, abra 2-5 arquivos representativos (entrypoints, controllers, services, models) — o suficiente para inferir responsabilidade e fluxo. Não leia o módulo inteiro.

Read the full file on GitHub · 112 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. 2d ago First seen · 112 lines · 72 tokens per session scan A c5d27f3a94cb

Subscribe to this mod's changes

dare-reverse is a skill published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,681 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

write-test-plan

Generate a QA/UAT test plan from product specifications and task definitions, covering acceptance testing, integration flows, and exploratory testing. Unit tests are out of scope (handled by write-unit-tests skill).

andresharpe/dotbot · 43 tokens

implement-telegram-bot

Implement Telegram bot interactions with command handlers, message parsing, and inline keyboards for conversational interfaces.

andresharpe/dotbot · 23 tokens

setup-background-job

Set up scheduled background jobs using Quartz.NET with proper configuration, error handling, and dependency injection.

andresharpe/dotbot · 22 tokens

write-unit-tests

Write comprehensive unit tests with proper setup, assertions, and coverage of happy paths, edge cases, and error scenarios.

andresharpe/dotbot · 26 tokens

blazor-component-design

Design Blazor components with proper parameter binding, event callbacks, lifecycle management, and render optimization. Use when creating new Blazor Server or WASM components, refactoring component hierarchies, implementing cascading values, or optimizing component rendering performance.

andresharpe/dotbot · 53 tokens

hedgehog-planning-intake

Use on any core for first-run planning intake — Phase 0 runs the vendored BMAD-METHOD planning shelf, shared by every core, and Phase 1 (mining 04-prd.md into intent records plus the Add-ons/sync-and-remote-entities decision) is full-stack-app's and pwa-app's shared procedure — identical mechanics, a different…

skyf0xx/hedgehog · 374 tokens