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 agentmods add commands/686f6c61/alfred-dev/quickgit clone --depth 1 https://github.com/686f6c61/alfred-devWhat 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 | $0.00015 | $0.01497 |
| Opus 5 | $0.00008 | $0.00749 |
| Sonnet 5 | $0.00003 | $0.00299 |
| Haiku 4.5 | $0.00002 | $0.00150 |
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.
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: $ARGUMENTS
Protocolo
- Paso obligatorio: como
.claude/*es sensible en Claude Code, NO usesWriteniEditpara iniciar el estado rápido ni improvises la sesión a mano. Usa Bash y el helper del plugin ANTES de leer contexto en detalle:
python3 .claude/alfred-continuity.py quick "$PWD" --raw "$ARGUMENTS"
Ese helper debe:
- bloquear si hay handoff o UAT pendientes;
- crear
.claude/alfred-dev-state.jsoncon el flujoquick; - dejar la sesión lista para
pause,retomaryuat.
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.
-
Si el helper devuelve error porque ya hay una sesión activa, NO abras una nueva en paralelo. Actúa como
/alfred-dev:retomar. -
Después del helper, lee:
.claude/alfred-dev-state.json.claude/alfred-handoff.jsonsi existe.claude/alfred-uat.jsonsi existedocs/project/current.mdsi existedocs/project/codebase-map.mdsi existe.claude/alfred-dev.local.mdsi existe
-
Si el repo es brownfield y todavía falta el mapa persistente, crea o refresca
docs/project/codebase-map.mdydocs/project/current.mdantes de tocar código. Hazlo dentro de este mismo comando, sin abrir una entrevista. -
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. Enquickno usesAskUserQuestionpara Lucius ni para opcionales. Núcleo y a programar. Si no consigues localizar ese fichero, continúa con el equipo de núcleo.
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.
- 2d ago First seen · 140 lines · 15 tokens per session scan A f7257f8bf14f
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.
Other commands, from other repositories
cdd-pre-pr
Run a pre-PR checklist for the current branch. Compare against the base branch to identify all changes. This is a verification session: it runs CI gates, code-reviews the diff, and reconciles documentation against the changes.
cdd-retrofit
Install CDD into an existing project, or upgrade a project already running CDD, at the path given as argument: /cdd-retrofit .
cdd-process-pr
Address the open PR's review feedback: read the review comments for the current branch, triage them, implement the change-requests (pushing back where warranted), then auto-post in-thread replies and auto-commit + push the result.
cdd-quick-create
Produce a small, self-contained deliverable — a script plus a README, not a full CDD project: /cdd-quick-create (takes an optional one-line description of what to build).
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].
accessibility
Audit frontend for WCAG 2.1 AA compliance: check semantic HTML, ARIA labels, color contrast, keyboard navigation, screen reader support. Usage: /accessibility [page-or-component] [--fix] [--level=AA|AAA].