reversa-restructure

reversa-restructure is a skill for Claude Code, Codex from sandeco/reversa. It costs 42 tokens per session (1,288 once invoked), scanned A, original, MIT.

A Portuguese-language refactoring skill for improving the internal structure of a method or class without changing its observable behaviour. It applies named refactoring techniques in small, reversible steps.

In plain words
What is it for?
Use it to refactor a selected method or class, follow an identified restructuring opportunity, and document evidence that behaviour stayed the same. It does not move modules or change dependencies.
Why use it?
It helps make difficult code easier to understand while preserving what the software does. Its required safety checks and control mode reduce the chance of unnoticed behaviour changes.

Skill for Claude CodeCodex

About the project

Reversa is a reverse-engineering framework that analyzes legacy software and turns its hidden business rules, code flows, and architectural decisions into executable specifications for AI coding agents. Teams use it to help agents safely understand and change systems that lack reliable documentation. The catalogue skills provide the specialized agent workflows used to perform this analysis.

sandeco/reversa · 1,558 stars · on GitHub

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/sandeco/reversa/reversa-restructure
Any agent
npx skills add sandeco/reversa --skill reversa-restructure
Clone the repo
git clone --depth 1 https://github.com/sandeco/reversa

Made for: Claude Code, Codex.

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 reversa-restructure

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandeco/reversa/reversa-restructure.svg)](https://agentmods.dev/skills/sandeco/reversa/reversa-restructure)
Your own site
<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-restructure"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-restructure.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,288 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 5.1 $0.00042 $0.01288
Opus 5 $0.00021 $0.00644
Sonnet 5 $0.00008 $0.00258
Haiku 4.5 $0.00004 $0.00129

Measured yesterday against content hash 1b54b45ea6f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

reversa-restructure 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.

agents/reversa-restructure/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o refatorador de estrutura interna. Sua missão é melhorar a estrutura de um método ou classe sem alterar o comportamento observável, aplicando refatorações nomeadas do catálogo Fowler em passos pequenos e reversíveis. Foco estrito: estrutura interna do trecho. Você não redistribui módulos nem muda a topologia de dependências.

Antes de começar

  1. Leia .reversa/state.json (output_folder, chat_language, doc_language, user_name)
  2. Leia _reversa_refactor/README.md (control_mode, safety_net_policy). Se _reversa_refactor/ não existir, aborte: "Rode /reversa-refactor primeiro para inventariar as oportunidades."
  3. Converse em chat_language; escreva artefatos em doc_language; nunca use travessão

Seleção da oportunidade

  1. Com argumento (/reversa-restructure OPP-...): resolva no opportunities/ do contexto
  2. Sem argumento: aceite um alvo em linguagem natural, resolva o contexto (crie a oportunidade restructure no schema se ainda não existir) e siga
  3. Recuse alvos que não sejam restructure (módulo inteiro, dependências): reencaminhe ao verbo certo

Modo de controle

Siga o control_mode do README (gated por padrão): leitura, análise e prova fluem; TODO passo que toca o código passa por gate com diff aprovado.

Rede de segurança (obrigatória antes de tocar o código)

  1. Verifique se o alvo tem testes que fixam o comportamento observável
  2. Sem cobertura, ofereça gerar testes de caracterização (Feathers) que fixam o comportamento atual como está, incluindo o que parecer errado; aplique-os por diff aprovado e prove PASSANDO antes de refatorar
  3. Se o usuário recusar a rede (e safety_net_policy permitir), rebaixe a transformação para 🔴 e registre que foi feita sem prova mecânica

Preservação de comportamento

Consulte <output_folder>/soul.md e as specs confirmadas do contexto. Nenhuma regra de negócio confirmada pode virar regra ferida. A refatoração muda o COMO, nunca o O QUÊ.

Fluxo

  1. Identifique os code smells do trecho e a refatoração Fowler nomeada para cada um (Extract Method, Rename, Decompose Conditional, Remove Duplication, Introduce Explaining Variable, ...)
  2. Planeje a sequência como passos pequenos, cada um reversível e verde
  3. Gere transformations/OPP-.../plan.html autocontido (CSS inline, tema escuro, estilo das views do Reversa): trecho antes, smells, sequência de refatorações, o que fica de fora. Peça para o usuário abrir e aprovar o plano antes de qualquer edição
  4. Gate: mostre o diff (antes/depois), com a refatoração nomeada por passo, aguarde aprovação, aplique
  5. Prove: rode a rede de segurança e cole a saída mostrando que continua verde. Se ficar vermelha, reverta pelo diff e não insista em silêncio

Read the full file on GitHub · 79 lines

Files

What ships with it

1 file 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. yesterday Changed · +10 lines 1b54b45ea6f6
  2. 6d ago First seen · 69 lines · 42 tokens per session scan A 1be75eb41a03

Subscribe to this mod's changes

reversa-restructure is a skill published in the GitHub repository sandeco/reversa (1,558 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 1,288 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens