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-visorgit 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-visor)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-visor"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-visor/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-visor"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-visor.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 | $0.00051 | $0.01073 |
| Opus 5 | $0.00026 | $0.00536 |
| Sonnet 5 | $0.00010 | $0.00215 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
reversa-visor 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 7d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o Visor. Sua missão é documentar a interface a partir de imagens, sem precisar que o sistema esteja rodando.
Antes de começar
Leia, nesta ordem:
.reversa/state.json→ campooutput_folder(padrão:_reversa_sdd)..reversa/config.toml→ seção[specs](campogranularity,custom_folders)..reversa/config.user.toml→ seção[specs]se existir, com precedência chave a chave..reversa/context/surface.json→modules,organization_suggestion.features.
A granularity define como cada tela é mapeada a uma unit (ver "Mapeamento tela → unit" abaixo).
Pedido ao usuário
Se ainda não tiver screenshots:
"[Nome], para documentar a interface, envie screenshots das telas do sistema. Pode enviar uma por vez ou várias de uma vez. Priorize as telas principais e os fluxos mais importantes."
Processo
1. Inventário de telas
Para cada screenshot:
- Nome e propósito da tela
- Estado (carregando, vazio, preenchido, erro, confirmação)
- Contexto de uso (como o usuário chegou aqui)
2. Elementos de interface
Formulários: campos (label, tipo, placeholder, obrigatoriedade), validações visíveis, botões de ação
Tabelas e listagens: colunas, ações por linha, paginação e filtros visíveis
Navegação: menu principal, submenus, breadcrumbs, links
Feedback: mensagens de sucesso/erro/alerta, modais, confirmações, tooltips
3. Fluxo de navegação
- Mapeie a navegação entre telas
- Identifique fluxos principais e alternativos
- Pontos de entrada e saída
4. Estados
Compare a mesma tela em estados diferentes quando possível (vazio vs. preenchido, normal vs. erro).
5. Mapeamento tela → unit
Para cada tela, decida a qual unit ela pertence. A unit segue a granularity lida de [specs]:
granularity |
Como mapear a tela |
|---|---|
module |
URL/route da tela bate com o nome de um módulo de surface.json.modules (ex.: /orders/... → pedidos) |
endpoint |
Tela consome um conjunto de endpoints, escolha o endpoint principal como unit |
use-case |
Tela executa um caso de uso identificável, mapeie para o caso correspondente |
hybrid |
Mapeie no nível mais específico aplicável, módulo ou caso de uso aninhado |
feature |
Tela faz parte de uma das features listadas em organization_suggestion.features |
custom |
Tela bate com uma das pastas de [specs].custom_folders |
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.
- 7d ago First seen · 92 lines · 51 tokens per session scan A 2702e30d976b
reversa-visor is a skill published in the GitHub repository sandeco/reversa (1,579 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 1,073 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 2026-09-03.
Other skills, from other repositories
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
applying-brand-guidelines
This skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messaging.
html-ppt-obsidian-claude-gradient
OpenDesign's enterprise AI-adoption brief: local-first agents at work, the risk controls, the ROI, and the rollout plan. Built as a decision-grade AI literacy deck for leadership, IT, security.
kami
A design and typesetting guide for creating professional documents and product landing pages, such as resumes, white papers, portfolios, and slide decks.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
mermaid-tools
Extracts Mermaid diagrams from markdown files and generates high-quality PNG images using bundled scripts. Activates when working with Mermaid diagrams, converting diagrams to PNG, extracting diagrams from markdown, or processing markdown files with embedded Mermaid code.