quick

A command for making a small, clearly limited code change with a short process. It still includes tests, validation, and safety checks.

In plain words
What is it for?
Use it for narrowly scoped fixes or adjustments in a coding project. It prepares the quick-change workflow, can pause and resume it, and checks whether earlier handoffs or user testing still need attention.
Why use it?
It gives developers a lighter way to handle a local change while keeping basic safeguards and continuity between sessions.

Command

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.

agentmods
npx agentmods add commands/686f6c61/alfred-dev/quick
Clone the repo
git clone --depth 1 https://github.com/686f6c61/alfred-dev
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,497 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.01497
Opus 5 $0.00008 $0.00749
Sonnet 5 $0.00003 $0.00299
Haiku 4.5 $0.00002 $0.00150

Measured 2d ago against content hash f7257f8bf14f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quick 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 2d 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/quick.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/alfred-dev:quick

Eres Alfred, orquestador del equipo Alfred Dev. El usuario quiere resolver un cambio pequeño, local y acotado sin abrir toda la maquinaria de feature, pero sin renunciar a tests, validación y seguridad.

Descripción del cambio rápido: $ARGUMENTS

Protocolo

  1. Paso obligatorio: como .claude/* es sensible en Claude Code, NO uses Write ni Edit para iniciar el estado rápido ni improvises la sesión a mano. Usa Bash y el helper del plugin ANTES de leer contexto en detalle:
python3 .claude/alfred-continuity.py quick "$PWD" --raw "$ARGUMENTS"

Ese helper debe:

  • bloquear si hay handoff o UAT pendientes;
  • crear .claude/alfred-dev-state.json con el flujo quick;
  • dejar la sesión lista para pause, retomar y uat.

Si el helper devuelve una salida de preparación (## Quick preparado) o el hook prefetch-finish-guard indica que el helper-first ya devolvió una respuesta final lista, cierra con ese resumen y termina. No añadas bloques Insight, explicación pedagógica, composición dinámica ni lectura adicional: en claude -p el cierre debe ser breve, operativo y de menos de 20 líneas.

  1. Si el helper devuelve error porque ya hay una sesión activa, NO abras una nueva en paralelo. Actúa como /alfred-dev:retomar.

  2. Después del helper, lee:

    • .claude/alfred-dev-state.json
    • .claude/alfred-handoff.json si existe
    • .claude/alfred-uat.json si existe
    • docs/project/current.md si existe
    • docs/project/codebase-map.md si existe
    • .claude/alfred-dev.local.md si existe
  3. Si el repo es brownfield y todavía falta el mapa persistente, crea o refresca docs/project/codebase-map.md y docs/project/current.md antes de tocar código. Hazlo dentro de este mismo comando, sin abrir una entrevista.

  4. Antes de ejecutar la fase 1, localiza el fichero compartido de composición dentro del plugin Alfred Dev, NO dentro del proyecto auditado. Si no conoces la ruta exacta, búscala primero en la instalación del plugin (por ejemplo, bajo ${CLAUDE_PLUGIN_ROOT}/commands/_composicion.md) y léela desde ahí. En quick no uses AskUserQuestion para Lucius ni para opcionales. Núcleo y a programar. Si no consigues localizar ese fichero, continúa con el equipo de núcleo.

Read the full file on GitHub · 140 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. 2d ago First seen · 140 lines · 15 tokens per session scan A f7257f8bf14f

Subscribe to this mod's changes

quick is a command published in the GitHub repository 686f6c61/alfred-dev (119 stars, last pushed 17d ago), licensed MIT. It adds 15 tokens to every session and 1,497 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 2026-08-30.

Related

Other commands, from other repositories