pseudocodigo

pseudocodigo is a command for Claude Code from doncheli/don-cheli-sdd. It costs 80 tokens per session (499 once invoked), scanned A, original, Apache-2.0.

A generator that turns software specifications into high-level pseudocode without choosing a programming language, framework, or file structure. Pseudocode describes logic in readable steps rather than runnable code.

In plain words
What is it for?
Use it to outline feature logic from Gherkin specifications, identify missing cases and data dependencies, and create a language-independent design note.
Why use it?
It lets developers reason about normal flows, failure cases, rules that must always hold, and edge cases before committing to technical implementation details.

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 outline feature logic from Gherkin specifications, identify missing cases and data dependencies, and create a language-independent design note.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/pseudocodigo.svg)](https://agentmods.dev/commands/doncheli/don-cheli-sdd/pseudocodigo)
Your own site
<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/pseudocodigo"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/pseudocodigo.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 499 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 $0.00080 $0.00499
Opus 5 $0.00040 $0.00249
Sonnet 5 $0.00016 $0.00100
Haiku 4.5 $0.00008 $0.00050

Measured 5d ago against content hash 0e0e42b3cdfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pseudocodigo 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/pseudocodigo.md · 50 lines

What it actually says

/dc:pseudocodigo

Objetivo

Crear un artefacto de pseudocódigo de alto nivel entre la fase de especificación y la planificación técnica. Fuerza al agente a razonar sobre la LÓGICA del sistema sin comprometer stack, framework o estructura de archivos.

Inspirado en la fase "P" (Pseudocode) del framework SPARC.

Uso

/dc:pseudocodigo                    # Desde las specs del sprint actual
/dc:pseudocodigo @specs/auth/       # Para un dominio específico

Comportamiento

  1. Leer las specs Gherkin del dominio
  2. Extraer los flujos principales (happy path + sad paths)
  3. Generar pseudocódigo agnóstico:
    • Sin nombres de funciones reales
    • Sin imports ni frameworks
    • Sin tipos de datos específicos del lenguaje
    • Solo lógica: CUANDO/SI/SINO/PARA-CADA/RETORNAR
  4. Identificar invariantes (condiciones siempre verdaderas)
  5. Listar casos límite y dependencias de datos
  6. Guardar en .dc/pseudocodigo.md

Por qué existe

Sin pseudocódigo, el agente salta de "qué hacer" (spec) a "cómo implementar" (plan técnico) sin pasar por "qué lógica necesito". Esto causa:

  • Sobre-ingeniería (resolver problemas que no existen)
  • Under-ingeniería (olvidar edge cases obvios)
  • Acoplamiento temprano a un framework

El pseudocódigo es el "boceto" del arquitecto antes de los planos.

Integración en el Pipeline

especificar → clarificar → PSEUDOCÓDIGO → planificar-tecnico → desglosar → implementar

Es opcional pero recomendado para tareas de complejidad ≥ 2 (Estándar).

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 · 50 lines · 80 tokens per session scan A 0e0e42b3cdfa

Subscribe to this mod's changes

pseudocodigo is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 28d ago), licensed Apache-2.0. It adds 80 tokens to every session and 499 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 2026-09-03.