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-arquitetura-3dgit 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-arquitetura-3d)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-arquitetura-3d"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-arquitetura-3d/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-arquitetura-3d"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-arquitetura-3d.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 102 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00046 | $0.02434 |
| Opus 5 | $0.00023 | $0.01217 |
| Sonnet 5 | $0.00009 | $0.00487 |
| Haiku 4.5 | $0.00005 | $0.00243 |
Grade A, and why
reversa-arquitetura-3d 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 12d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arquitetura 3D
Cria visualizações 3D de arquitetura de software usando Three.js. Gera sempre HTML standalone (arquivo único, self-contained) com cena 3D interativa, controles de câmera (mouse, touch, teclado), sidebar de parâmetros e botão de exportar a viewport como PNG.
A skill cobre cinco modos visuais consagrados em visualização de software, cada um com referência dedicada em references/:
| Modo | Quando usar | Referência |
|---|---|---|
| Code City | Visão geral de tamanho/complexidade de cada arquivo, padrão "cidade de código" | references/CODE_CITY.md |
| Dependency Graph 3D | Grafo de dependências com força repulsiva, nós em 3D | references/DEPENDENCY_GRAPH_3D.md |
| Layer Stack | Camadas arquiteturais (UI / Domain / Infra) empilhadas com setas de fluxo | references/LAYER_STACK.md |
| Call Graph 3D | Árvore de chamadas explorável em profundidade | references/CALL_GRAPH_3D.md |
| Architecture Tour | Câmera animada percorrendo a cena com overlay narrativo | references/ARCH_TOUR.md |
Padrões compartilhados de Three.js, lighting, controles e performance vivem em references/THREE_PATTERNS.md. Cenários de erro e tratamento em references/ERRORS.md.
Fluxo de Trabalho
1. Receber os dados
Os dados podem vir de:
- JSON inline: usuário fornece
modules.json(lista de módulos) e/oudeps.json(grafo de dependências). - Caminho de arquivo: usuário aponta para JSONs em
_reversa_docs/assets/data/(gerados pelo agente/reversa-documentation). - Solicitado ao usuário: se a skill é invocada sem dados, perguntar caminho ou pedir colagem inline.
Schema esperado de modules.json:
[
{
"name": "src/auth/login.ts",
"folder": "src/auth",
"loc": 142,
"complexity": 8,
"type": "code"
}
]
Schema esperado de deps.json (orientado):
{
"nodes": [{ "id": "src/auth/login.ts" }, { "id": "src/auth/jwt.ts" }],
"edges": [{ "from": "src/auth/login.ts", "to": "src/auth/jwt.ts", "weight": 1 }]
}
What ships with it
8 files 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.
- 12d ago First seen · 164 lines · 46 tokens per session scan A a0aea997259b
reversa-arquitetura-3d is a skill published in the GitHub repository sandeco/reversa (1,589 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 2,434 once invoked, about $0.0002 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.