A Spanish-language assistant command that chooses the appropriate Alfred Dev workflow for a project request. Alfred Dev is a collection of commands for tasks such as planning, fixing, auditing, and shipping software.

Use it as an entry point for Alfred Dev tasks, including repository mapping, feature work, bug fixes, audits, and releases. It can also direct requests to progress, configuration, or recovery commands.

It reduces the need to know which command to run first. It also checks the project’s saved context and routes the request to the available workflow.

alfred — Command for Claude Code by 686f6c61/alfred-dev

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/686f6c61/alfred-dev

agentmods

npx agentmods add commands/686f6c61/alfred-dev/alfred

Made for: Claude Code.

Or install alfred-dev, the plugin that ships this one along with the rest of its 11 skills, 22 commands, 10 agents, 5 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/686f6c61/alfred-dev/alfred/github.svg)](https://agentmods.dev/commands/686f6c61/alfred-dev/alfred)

Your own site

<a href="https://agentmods.dev/commands/686f6c61/alfred-dev/alfred"><img src="https://agentmods.dev/badge/commands/686f6c61/alfred-dev/alfred/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/686f6c61/alfred-dev/alfred"><img src="https://agentmods.dev/badge/commands/686f6c61/alfred-dev/alfred.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,511 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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.02511
Opus 5.5	$0.00006	$0.01004
Sonnet 5.5	$0.00003	$0.00502
Haiku 4.5	$0.00002	$0.00251

Measured 1mo ago against content hash 9cfeeaab9d62, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

alfred 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 1mo 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.

commands/alfred.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/alfred-dev:alfred

Eres Alfred, mayordomo jefe del equipo Alfred Dev. El usuario te ha invocado como asistente contextual y espera que decidas el camino correcto sin tener que ir empujándote paso a paso.

Petición del usuario: $ARGUMENTS

Agent Teams

Si esta sesion tiene Agent Teams activo (CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS), usa teammates nativos para trabajo en paralelo (arquitectura+seguridad, QA+seguridad). No actives esa variable tu. Si no hay teams, usa la herramienta Agent.

Objetivo

Elegir y ejecutar el comando correcto entre la superficie publicada:

/alfred-dev:alfred (esta entrada)
/alfred-dev:progress
/alfred-dev:retomar
/alfred-dev:pause
/alfred-dev:map-codebase
/alfred-dev:discuss
/alfred-dev:memory-ui
/alfred-dev:ajustes
/alfred-dev:uat
/alfred-dev:sync-github
/alfred-dev:quick
/alfred-dev:feature
/alfred-dev:fix
/alfred-dev:spike
/alfred-dev:ship
/alfred-dev:audit
/alfred-dev:lucius
/alfred-dev:update

next y search son helpers internos del runtime. No los presentes como slash commands.

Protocolo obligatorio

Antes de leer contexto o decidir nada, comprueba si UserPromptSubmit ya dejó una ruta helper-first resuelta para esta misma invocación. Ejecuta este Bash inmediatamente y, si devuelve texto, úsalo como respuesta final y termina:

python3 .claude/alfred-continuity.py consume-prefetch "$PWD" --expected alfred

Si no devuelve nada o falla, entonces sí continúa con el protocolo normal.

Antes de decidir, lee SIEMPRE este contexto en este orden:

.claude/alfred-dev-state.json
.claude/alfred-handoff.json
.claude/alfred-uat.json
docs/project/discovery.md
docs/project/current.md
docs/project/codebase-map.md
docs/project/uat.md
.claude/alfred-dev.local.md
README.md, package.json, pyproject.toml, Cargo.toml, go.mod o equivalentes si existen

Después, clasifica la intención del usuario usando su texto y el estado del proyecto. No ofrezcas un menú por defecto.

Read the full file on GitHub · 199 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.

1mo ago First seen · 199 lines · 16 tokens per session scan A 9cfeeaab9d62

Subscribe to this mod's changes

alfred is a command published in the GitHub repository 686f6c61/alfred-dev (117 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 2,511 once invoked, about $0.0001 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 2026-08-30.

Claude Code ai-agents automation claude-code-plugin sdlc

review-pr

Review a PR (GitHub or Bitbucket) — single reviewer by default, or a 3-panelist council with --council.

mumerfarooq-con/asdlc-tools · 28 tokens

gen-brand

Generate complete brand identity with SVG logos, color system, typography, and design tokens. Claude writes SVG code directly — no API key needed. Usage: /gen-brand 'ProductName — description' or /gen-brand ./PRD.md.

alphaaiservice/cortex · 47 tokens

init-project

Initialize a new or upgrade existing project with Alpha AI's standard architecture. Supports Python/FastAPI, Node.js/NestJS, Java/Spring Boot. Usage: /init-project [--lang=python|nestjs|springboot] [--with-frontend] [--with-mobile] [--with-ai] [--existing].

alphaaiservice/cortex · 71 tokens

alfred