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-forward-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-forward-autonomous)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-forward-autonomous"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-forward-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-forward-autonomous"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-forward-autonomous.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00128 | $0.03637 |
| Opus 5.5 | $0.00051 | $0.01455 |
| Sonnet 5.5 | $0.00026 | $0.00727 |
| Haiku 4.5 | $0.00013 | $0.00364 |
Grade A, and why
reversa-forward-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 26d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o orquestrador forward do Reversa em modo autônomo. Você executa o mesmo pipeline do reversa-forward (requirements, clarify?, plan, to-do, audit?, quality?, coding, sync) sobre uma fila de features, uma depois da outra. Toda decisão que o fluxo normal pergunta ao longo do caminho é coletada numa entrevista única no início. Depois dela, você só para nos casos da seção "Paradas legítimas".
Relação com os skills do pipeline
- Leia o
SKILL.mddoreversa-forward(pasta irmãreversa-forward/no mesmo diretório de skills). Dele você herda a resolução de pastas, a organização das specs e a tabela de estágio físico, que é a única fonte de verdade sobre em que ponto cada feature está. - Para executar uma fase, leia o
SKILL.mddo skill da fase (pasta irmãreversa-<fase>/) e siga as instruções no contexto atual. Os skills de fase são user-invoked, então nunca tente ativá-los pelo nome: leia o arquivo. - Aplique por cima os overrides deste documento. Em conflito, este documento vence.
Aviso sobre o modo de execução
Este skill foi feito para sessões com aprovação automática de ferramentas (modo YOLO do Claude Code, /goal ou equivalente). Ao contrário do /reversa-autonomous, que só escreve documentação, este skill escreve código do projeto, e só por um caminho: a fase reversa-coding, obedecendo .reversa/reversa-config.json. Por isso:
- Fora da fase coding, escreva apenas em
.reversa/,<output_folder>/e<forward_folder>/. - Na fase coding, a política de edição do legado vale com rigor total. NUNCA crie nem edite
.reversa/reversa-config.json: nem a entrevista, nem o/goal, nem um pedido na conversa liberam edição. A config só muda pela mão do usuário. - Nunca faça
git push, publicação, deploy ou comando destrutivo por conta própria. Build e testes locais que as ações doactions.mdpedirem são permitidos. Instalar dependência só quando uma ação doactions.mdpedir explicitamente. - Na dúvida entre agir e não agir sobre algo fora do que a fase manda, não aja e registre no relatório final.
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.
- 26d ago First seen · 185 lines · 128 tokens per session scan A 211986673ab8
reversa-forward-autonomous is a skill published in the GitHub repository sandeco/reversa (1,784 stars, last pushed yesterday), licensed MIT. It adds 128 tokens to every session and 3,637 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.