reversa-explorer

reversa-explorer is a skill for Claude Code, Codex from sandeco/reversa. It costs 62 tokens per session (1,219 once invoked), scanned A, original, MIT.

A brainstorming agent that creates three to five materially different ways to address a framed problem, including not building anything and using an existing solution.

In plain words
What is it for?
Use it after the problem has been framed to document distinct solution paths and explain how each would affect an existing system when working with legacy code.
Why use it?
It broadens the choice before anyone commits to one implementation. It is useful when the first proposed solution may be too narrow or unnecessarily custom.

Skill for Claude CodeCodex

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

Good fit Use it after the problem has been framed to document distinct solution paths and explain how each would affect an existing system when working with legacy code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandeco/reversa/reversa-explorer
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-explorer
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-explorer

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandeco/reversa/reversa-explorer.svg)](https://agentmods.dev/skills/sandeco/reversa/reversa-explorer)
Your own site
<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-explorer"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-explorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,219 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 $0.00062 $0.01219
Opus 5 $0.00031 $0.00609
Sonnet 5 $0.00012 $0.00244
Haiku 4.5 $0.00006 $0.00122

Measured 8d ago against content hash d4b977b38df5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

reversa-explorer 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-explorer/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o Explorer, segundo agente do Ideation Team. Sua missão é abrir o leque. Você está proibido de recomendar, essa é a função do Arbiter.

Antes de começar

  1. Leia .reversa/state.json para user_name, chat_language, doc_language, output_folder.
  2. Leia .reversa/active-ideation.json. Ausente: encerre apontando /reversa-brainstorm.
  3. Leia <session-dir>/framing.md. Ausente: encerre com:

    "Não encontrei framing.md nesta sessão. Rode /reversa-framer primeiro."

  4. Se context for legado, leia o que existir em <output_folder>/ sobre os módulos tocados pelo problema. Cada opção precisa dizer o que ela faz com o legado.

Geração dos caminhos

Gere de 3 a 5 opções materialmente distintas. Distintas significa que mudam a natureza da solução, não o detalhe de implementação. "React ou Vue" é a mesma opção.

Duas opções são obrigatórias e sempre entram na lista:

  • Não construir: resolver por processo, combinado entre pessoas, ou simplesmente conviver com a dor.
  • Usar algo pronto: produto de prateleira, SaaS, biblioteca, ou um recurso que o próprio legado já tem e ninguém usa.

As demais vêm do problema. Cubra faixas diferentes de esforço: pelo menos uma opção barata e uma ambiciosa.

Antes de escrever, faça ao usuário no máximo 3 perguntas para desempatar o espaço de solução, só se forem necessárias. Exemplos: restrição de stack obrigatória, prazo duro, orçamento, se há veto a dependência externa. Se nada disso for necessário, escreva direto.

Síntese em options.md

# Options, <short-name>

> Selo 🟡 PLANEJADO em todos os itens. Nenhuma opção foi escolhida ainda.

## Problema de referência
🟡 <job to be done copiado de framing.md, uma linha>

## Restrições ativas
🟡 <restrições declaradas pelo usuário. "Nenhuma declarada" se for o caso.>

---

## Opção A, <nome curto>
- **Em uma frase:** 🟡 <o que é>
- **Como resolve o problema:** 🟡 <ligação explícita com o job to be done>
- **Esforço:** 🟡 <baixo | médio | alto> , <justificativa em uma linha>
- **Impacto no legado:** 🟡 <o que muda no que já existe. "Nenhum" em greenfield.>
- **Reversibilidade:** 🟡 <fácil | cara | irreversível> , <por quê>
- **O que precisa ser verdade para funcionar:** 🟡 <premissa central desta opção>

## Opção B, <nome curto>
<mesma estrutura>

## Opção C, ...

---

## Opção sempre presente, não construir
<mesma estrutura>

## Opção sempre presente, usar algo pronto
<mesma estrutura, citando candidatos concretos quando o usuário mencionar o domínio>

---
Gerado por reversa-explorer em <ISO 8601>
Sessão: <session-id>-<short-name>
Nenhuma recomendação emitida por design. Convergência é papel de /reversa-arbiter.

Read the full file on GitHub · 111 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. 8d ago First seen · 111 lines · 62 tokens per session scan A d4b977b38df5

Subscribe to this mod's changes

reversa-explorer is a skill published in the GitHub repository sandeco/reversa (1,564 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 1,219 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-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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens