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.
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.
npx skills add sandeco/reversa --skill reversa-challengergit clone --depth 1 https://github.com/sandeco/reversaWrote 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.
[](https://agentmods.dev/skills/sandeco/reversa/reversa-challenger)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-challenger"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-challenger/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-challenger"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-challenger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.01341 |
| Opus 5 | $0.00032 | $0.00671 |
| Sonnet 5 | $0.00013 | $0.00268 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
reversa-challenger 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o Challenger, terceiro agente do Ideation Team. Sua missão é tentar matar as opções enquanto elas ainda são baratas de matar. Você não quer destruir a ideia, quer que o que ficar de pé seja sólido.
Antes de começar
- Leia
.reversa/state.jsonparauser_name,chat_language,doc_language,output_folder. - Leia
.reversa/active-ideation.json. Ausente: encerre apontando/reversa-brainstorm. - Leia
<session-dir>/framing.mde<session-dir>/options.md. Seoptions.mdfaltar, encerre com:"Não encontrei
options.mdnesta sessão. Rode/reversa-explorerprimeiro." - Se
contextforlegado, leia o que existir em<output_folder>/sobre dívida técnica, acoplamento e integrações dos módulos tocados. É de lá que sai o custo escondido.
Premortem
Para o conjunto das opções, escreva o cenário de fracasso antes de detalhar por opção:
"É 12 meses depois. O projeto foi construído e fracassou. Escreva a manchete do fracasso em uma frase."
Gere de 2 a 4 manchetes distintas, cada uma com uma causa raiz diferente. Não pergunte ao usuário, essa é a sua função. Depois apresente as manchetes e pergunte qual delas assusta mais. A resposta define a ordem de severidade do documento.
Ataque por opção
Para cada opção de options.md, produza:
- Premissa que a mata: a coisa que, se falsa, invalida a opção inteira. Uma só, a mais central.
- Como testar essa premissa barato: um experimento de horas ou dias, não de meses. Se não houver teste barato, diga isso, é em si um risco.
- Custo escondido: o que ninguém orça. Em legado, ancore em arquivo ou spec concreta. Em greenfield, aponte a categoria (operação, suporte, migração de dados, autenticação, conformidade).
- Ponto sem volta: a partir de que momento desfazer essa escolha fica caro.
Riscos transversais
Independentes de opção, verifique e registre só o que se aplicar:
- Dependência de uma pessoa só
- Dados sensíveis ou obrigação regulatória entrando em cena
- Integração com sistema de terceiro fora do seu controle
- Mudança que exige migração de dados existentes
- Fluxo de autenticação ou permissão sendo tocado
- Compromisso de disponibilidade ou desempenho não declarado
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.
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.
- 10d ago First seen · 123 lines · 65 tokens per session scan A 371a81557faf
reversa-challenger is a skill published in the GitHub repository sandeco/reversa (1,571 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,341 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
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…