reversa-reconstructor

reversa-reconstructor is a skill for Claude Code, Codex from sandeco/reversa. It costs 64 tokens per session (3,222 once invoked), scanned A, original, MIT.

A step-by-step guide for rebuilding software from Reversa specifications, which are documents describing how an existing program works. It creates a bottom-up work plan and implements one task at a time.

In plain words
What is it for?
Use it when an _reversa_sdd_ folder contains the required specifications and you want to recreate the software, choosing original or migration specifications when both exist.
Why use it?
It keeps reconstruction manageable and limits how much of the specification must be read at each step.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: names the AskUserQuestion tool; mentions Claude Code; mentions Codex.

Good fit Use it when an _reversa_sdd_ folder contains the required specifications and you want to recreate the software, choosing original or migration specifications when both exist.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandeco/reversa/reversa-reconstructor
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 · 1,564 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.

Any agent
npx skills add sandeco/reversa --skill reversa-reconstructor
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-reconstructor

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandeco/reversa/reversa-reconstructor.svg)](https://agentmods.dev/skills/sandeco/reversa/reversa-reconstructor)
Your own site
<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-reconstructor"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-reconstructor.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,222 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 $0.00064 $0.03222
Opus 5 $0.00032 $0.01611
Sonnet 5 $0.00013 $0.00644
Haiku 4.5 $0.00006 $0.00322

Measured 8d ago against content hash 4999886c76fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

reversa-reconstructor 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 8d 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.

agents/reversa-reconstructor/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o Reconstructor. Sua missão é transformar as especificações geradas pelo Reversa em um plano de reconstrução executável e depois implementar cada tarefa sob demanda — bottom-up, uma por vez.

Regra fundamental

Nunca leia mais do que o necessário para cada etapa. O plano é criado lendo poucos arquivos. Cada tarefa lê apenas os arquivos que ela precisa. Isso preserva tokens e permite pausar e retomar a qualquer momento.


Ao ser invocado

Passo 1 — Verificar pré-requisitos

Verifique se a pasta _reversa_sdd/ existe no diretório atual.

Se não existir, encerre:

"Não encontrei _reversa_sdd/. Execute o Reversa no projeto original primeiro, depois copie a pasta para este diretório."

Passo 2 — Detectar migração e perguntar a fonte

Verifique se _reversa_sdd/migration/handoff.md existe.

Se NÃO existir: o projeto não tem migração concluída, vá direto para o Passo 3 com fonte original (comportamento padrão).

Se existir: o projeto tem migração concluída e o usuário pode escolher reconstruir a partir das specs originais (sistema fiel ao legado) ou das specs da migração (sistema novo na stack alvo). Pergunte:

"Encontrei specs de migração em _reversa_sdd/migration/. Você quer reconstruir a partir de:

  1. Specs originais: reimplementa o sistema fiel ao legado a partir de _reversa_sdd/
  2. Specs da migração: implementa o sistema novo na stack alvo a partir de _reversa_sdd/migration/
  3. Outro: descreva (ex: "reconstruir só um módulo", "misturar fontes")

Use o menu interativo da engine (no Claude Code, AskUserQuestion); em engines sem suporte, peça o número 1–3 ou texto livre."

Aguarde a resposta. NÃO escolha por conta própria. Persista a escolha em memória da sessão para usar nos passos 3 e 4 e para gravar no plano. Se a opção 3 for ambígua, refaça a pergunta uma vez antes de decidir.

Caso especial: migração em andamento (sem handoff.md). Se existir _reversa_sdd/migration/.state.json mas não existir handoff.md, informe:

"Detectei uma migração em andamento (sem handoff.md). Para reconstruir a partir das specs da migração, finalize-a com /reversa-migrate antes. Vou prosseguir com as specs originais. Tudo bem?"

Se o usuário disser não, encerre sem fazer nada.

Read the full file on GitHub · 244 lines

Files

What ships with it

3 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. 8d ago First seen · 244 lines · 64 tokens per session scan A 4999886c76fb

Subscribe to this mod's changes

reversa-reconstructor is a skill published in the GitHub repository sandeco/reversa (1,564 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 3,222 once invoked, about $0.0003 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