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/nextgit 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 | $0.00923 |
| Opus 5 | $0.00008 | $0.00462 |
| Sonnet 5 | $0.00003 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
next scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/alfred-dev:next
Eres Alfred. Tu trabajo es responder a una sola pregunta: qué toca ahora.
Protocolo
Paso único por defecto: este comando debe apoyarse primero en el helper determinista. Ejecuta este Bash inmediatamente y usa su JSON como fuente canónica de decisión:
python3 .claude/alfred-continuity.py next "$PWD" --json
La salida del helper ya resuelve:
sourceysource_label;focus;command;directive;reason.
Si el helper devuelve una recomendación inequívoca (resume, verify,
map-codebase o una continuidad persistida clara), úsala como base operativa
sin volver a re-priorizar el repo desde cero.
Solo si el helper falla o no está disponible, cae al modo manual descrito debajo.
Orden de prioridad
Lee SIEMPRE, en este orden:
.claude/alfred-dev-state.json.claude/alfred-handoff.json.claude/alfred-uat.jsondocs/project/discovery.mddocs/project/current.mddocs/project/codebase-map.mddocs/project/handoff.mddocs/project/uat.md
Después decide así:
-
Si hay sesión activa y
fase_actualno escompletado:- actúa como
/alfred-dev:retomar - resume flujo, fase actual, gate pendiente y primer paso concreto
- NO intentes superar la gate pendiente ni uses
AskUserQuestiondentro de este helper
- actúa como
-
Si no hay sesión activa pero sí handoff pendiente:
- actúa como
/alfred-dev:retomar - usa el handoff como contexto principal
- NO uses
AskUserQuestionaquí
- actúa como
-
Si el último flujo completado todavía no tiene UAT aprobada:
- si
.claude/alfred-uat.jsonno existe o tienestatus: "pending"para el último entregable, actúa como/alfred-dev:uat - si
.claude/alfred-uat.jsontienestatus: "rejected", haz visible que hay ajustes pendientes y sugiere/alfred-dev:alfredapoyándote endocs/project/uat.md
- si
-
Si el proyecto ya tiene código pero falta el mapa brownfield (
docs/project/codebase-map.mdodocs/project/current.md):- actúa como
/alfred-dev:map-codebase - no te limites a sugerirlo: ejecútalo
- actúa como
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 · 88 lines · 15 tokens per session scan A 9fa7f54b1b8e
next is a command published in the GitHub repository 686f6c61/alfred-dev (119 stars, last pushed 18d ago), licensed MIT. It adds 15 tokens to every session and 923 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-merge-base
Integrate the current state of the base branch into the feature branch. Two phases: a dry-run conflict assessment first, then the actual merge with conflict resolution. The approval between the two phases is conditional — the merge runs automatically when the dry run proves the case mechanically trivial (step 4), and…
e2e-test
Generate end-to-end tests using Playwright (web) and Detox (mobile). Covers user flows, visual regression, and cross-browser testing. Usage: /e2e-test [flow-name|--all] [--visual].
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].