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-autonomousgit 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-autonomous)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-autonomous"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-autonomous/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-autonomous"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-autonomous.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 | $0.00077 | $0.02675 |
| Opus 5 | $0.00039 | $0.01337 |
| Sonnet 5 | $0.00015 | $0.00535 |
| Haiku 4.5 | $0.00008 | $0.00267 |
Grade A, and why
reversa-autonomous 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 9d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o Reversa em modo autônomo. Você executa exatamente o mesmo plano e a mesma sequência de agentes do orquestrador reversa, com uma diferença central: todas as decisões que o fluxo normal pergunta ao longo do caminho são coletadas em uma entrevista única no início. Depois da entrevista, você só para quando existir necessidade real (lista fechada na seção "Paradas legítimas").
Relação com o skill reversa
Este skill herda o comportamento do orquestrador reversa. Antes de executar:
- Leia o
SKILL.mddo skillreversa(pasta irmãreversa/no mesmo diretório de skills) e suas references (step-01-first-run.md,step-02-resume.md,step-03-specs-organization.md,step-04-regression-check.md,checkpoint-guide.md,state-schema.md). - Siga tudo o que está lá: checkpoints, escala de confiança, expansão do plano após o Scout, verificação de regressão, regra absoluta non-destructive.
- Aplique por cima os overrides deste documento. Em conflito, este documento vence.
Aviso sobre o modo de execução
Este skill foi projetado para rodar em sessões com aprovação automática de ferramentas (modo YOLO do Claude Code ou equivalente em outras engines). Isso significa que não haverá um humano aprovando cada ação. Por isso:
- A regra absoluta do Reversa vale com rigor total: escreva APENAS em
.reversa/,<output_folder>/e na seção de histórico de_reversa_forward/<feature>/regression-watch.md. Nunca modifique, mova ou apague qualquer outro arquivo do projeto. - Nunca execute comandos destrutivos ou de efeito externo (deletar arquivos,
git push, publicar, instalar dependências) por conta própria. - Na dúvida entre agir e não agir sobre algo fora das pastas do Reversa, não aja e registre a dúvida no relatório final.
Entrevista inicial (a única parada planejada)
Ao ser ativado, leia .reversa/state.json e monte a entrevista com apenas as perguntas ainda não respondidas. Perguntas já persistidas em state.json ou .reversa/config.toml não são refeitas.
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.
- 9d ago First seen · 140 lines · 77 tokens per session scan A 232ded8bc1f7
reversa-autonomous is a skill published in the GitHub repository sandeco/reversa (1,567 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 2,675 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 2026-08-30.
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…
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…
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…