reversa

reversa is a command for Claude Code from doncheli/don-cheli-sdd. It costs 14 tokens per session (1,197 once invoked), scanned A, original, Apache-2.0.

A reverse-architecture tool analyzes an existing codebase and maps its components, connections, data flows, technologies, and code ownership. This is reverse engineering: learning a system’s design from its code.

In plain words
What is it for?
Use it to scan a project, identify its frameworks and components, and document how data and dependencies move through the system.
Why use it?
It gives developers a clearer model of an unfamiliar project before they modify it, reducing inconsistent changes and duplicated work.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Part of the don-cheli-sdd plugin — 28 skills, 115 commands, 1 agent shipped together

Good fit Use it to scan a project, identify its frameworks and components, and document how data and dependencies move through the system.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/doncheli/don-cheli-sdd/reversa
Install

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.

Clone the repo
git clone --depth 1 https://github.com/doncheli/don-cheli-sdd

Made for: Claude Code.

Or install don-cheli-sdd, the plugin that ships this one along with the rest of its 28 skills, 115 commands, 1 agent.

Wrote 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.

agentmods badge for reversa

README.md
[![agentmods](https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/reversa/github.svg)](https://agentmods.dev/commands/doncheli/don-cheli-sdd/reversa)
Your own site
<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/reversa"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/reversa/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.

agentmods 80×15 button for reversa

Your own site · 80×15
<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/reversa"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/reversa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,197 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.01197
Opus 5 $0.00007 $0.00598
Sonnet 5 $0.00003 $0.00239
Haiku 4.5 $0.00001 $0.00120

Measured 5d ago against content hash 4bec1e53fe1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

reversa 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 5d 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.

scripts/.claude/commands/dc/reversa.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dc:reversa

Objetivo

Analizar un codebase existente y extraer su arquitectura implícita: componentes, conexiones, flujos de datos, tecnologías y propiedad de código. Convierte código desorganizado en un mapa arquitectónico explícito.

Adaptado de DevilDev (lak7/devildev) — Reverse Architecture.

Uso

/dc:reversa                          # Analizar el proyecto actual
/dc:reversa @ruta/al/proyecto        # Analizar un proyecto específico
/dc:reversa --profundidad superficial # Solo estructura de alto nivel
/dc:reversa --profundidad profunda    # Incluir flujo de datos y dependencias

Por Qué Existe

El 80% del trabajo de desarrollo es sobre codebases existentes, no greenfield. Antes de modificar un sistema, necesitas entender:

  • ¿Cuáles son los componentes principales?
  • ¿Cómo se conectan entre sí?
  • ¿Qué tecnologías usa cada componente?
  • ¿Dónde vive el código de cada componente?

Sin esta herramienta, un agente IA empieza a modificar código sin entender la arquitectura, generando inconsistencias y duplicación.

Comportamiento

Paso 1: Escaneo Estructural

Escaneando proyecto...
├── Detectando framework: Next.js 15 + TypeScript
├── Identificando dependencias: 24 directas, 8 dev
├── Mapeando estructura de directorios
└── Analizando imports y exports

Paso 2: Identificación de Componentes

Aplica estas reglas (de DevilDev):

  1. Solo componentes con evidencia — No inventar lo que no existe
  2. Test de valor de negocio — ¿Un stakeholder no-técnico lo entendería?
  3. Test de significancia — ¿Si falla, requiere una solución técnica diferente?
  4. Test de independencia — ¿Se podría reemplazar con otra tecnología?

Paso 3: Mapeo de Propiedad de Código

Para cada componente:

{
  "codeOwnership": {
    "primaryImplementation": {
      "directories": ["src/services/auth/"],
      "files": ["src/middleware/jwt.ts"],
      "confidence": 0.9,
      "rationale": "Contiene toda la lógica de autenticación"
    },
    "supportingRelated": {
      "directories": ["src/utils/crypto/"],
      "confidence": 0.6,
      "rationale": "Helpers de encriptación usados por auth"
    },
    "sharedDependencies": {
      "files": ["src/db/prisma.ts"],
      "confidence": 0.3,
      "rationale": "Cliente de BD compartido con otros servicios"
    }
  }
}

Read the full file on GitHub · 156 lines

Changes

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.

  1. 5d ago First seen · 156 lines · 14 tokens per session scan A 4bec1e53fe1e

Subscribe to this mod's changes

reversa is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 29d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,197 once invoked, about $0.0001 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.