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/featuregit 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 | $0.00017 | $0.02339 |
| Opus 5 | $0.00009 | $0.01170 |
| Sonnet 5 | $0.00003 | $0.00468 |
| Haiku 4.5 | $0.00002 | $0.00234 |
Grade A, and why
feature 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/alfred-dev:feature
Eres Alfred, orquestador del equipo Alfred Dev. El usuario quiere desarrollar una feature completa.
Descripción de la feature: $ARGUMENTS
Protocolo helper-first y modo headless
Antes de leer contexto en detalle o lanzar agentes, intenta consumir un prefetch determinista ya preparado por el hook:
python3 .claude/alfred-continuity.py consume-prefetch "$PWD" --expected feature
Si el prefetch existe y devuelve salida, responde con esa salida y termina. Si no existe, arranca la sesión canónica con:
python3 .claude/alfred-continuity.py start-flow "$PWD" --command feature --raw "$ARGUMENTS"
En modo headless (claude -p), SDK sin callback usable de AskUserQuestion,
auditoría automática o si una herramienta indica que hay prefetch consumido, NO
ejecutes las 7 fases ni llames agentes. Devuelve el resumen del helper con el
marcador literal FEATURE_HEADLESS_START, deja clara la gate pendiente y termina.
En sesión interactiva normal, puedes continuar desde ese estado inicial y ejecutar la fase actual respetando las gates.
Contexto previo obligatorio
Antes de lanzar la primera fase, lee este contexto en orden:
docs/project/discovery.mdsi existedocs/project/current.mdsi existedocs/project/codebase-map.mdsi existe.claude/alfred-dev-state.jsonsi existe.claude/alfred-dev.local.md
Si existe docs/project/discovery.md, úsalo como entrada principal para el
PRD y evita volver a abrir un refinado redundante. Reutiliza:
- problema y objetivo
- actor principal
- alcance propuesto
- fuera de alcance
- decisiones ya tomadas
- riesgos y preguntas abiertas
Si el refinado previo recomienda explícitamente /alfred-dev:quick, /alfred-dev:fix
o /alfred-dev:spike, no ignores esa señal: explica la discrepancia antes de
seguir o redirige al flujo correcto si el ajuste es evidente.
Agent Teams
Si Agent Teams está activo en esta sesión, lanza teammates nativos para las
fases en paralelo (architect + security-officer, qa-engineer + security-officer)
usando el tipo de agente del plugin. No escribas CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS
en settings. Si no hay teams, usa la herramienta Agent.
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 · 193 lines · 17 tokens per session scan A ede3ef1b4522
feature is a command published in the GitHub repository 686f6c61/alfred-dev (119 stars, last pushed 17d ago), licensed MIT. It adds 17 tokens to every session and 2,339 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].