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/alphaaiservice/cortex/gen-mockupgit clone --depth 1 https://github.com/alphaaiservice/cortexWhat 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 | $0.00090 | $0.01340 |
| Opus 5 | $0.00045 | $0.00670 |
| Sonnet 5 | $0.00018 | $0.00268 |
| Haiku 4.5 | $0.00009 | $0.00134 |
Grade A, and why
gen-mockup 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Mockup Generator — Screens Before You Build
Generate viewable, brand-consistent screen mockups that sit between /gen-prd and /auto-build. The mockup skill auto-loads with this command and defines the quality bar.
$ARGUMENTS = product/screen description, or a path to a PRD/PRD.md.
Section 0: Input Parsing & Context Detection
0a. Parse input
- If
$ARGUMENTSis a file path → read it as the PRD; extract the screen list, primary entities, and user roles. - If it's free text → treat it as the product/screen brief.
- Flags:
--fidelity=low|mid|high(default mid)--screens=a,b,c(explicit screen list; otherwise infer from the PRD/brief)--mobile(use a ~390px phone frame instead of desktop)--next(emit real Next.js + shadcn components undermockups-next/instead of standalone HTML — for direct promotion)
0b. Detect brand source (CRITICAL — reuse, don't invent)
Search the project for, in order:
BRAND_GUIDE.md(from/gen-brand)globals.css/app/globals.csswith OKLCH--tokenstailwind.config.*theme extension If found → extract fonts, OKLCH color tokens (light + dark), radius, spacing; use them verbatim. If none found and fidelity is mid/high → tell the user "no brand found — running with a sensible neutral default; run/gen-brandfirst for on-brand mockups" and proceed with a tasteful default token set.
0c. Decide the screen list
From PRD/brief infer the screens to mock. Map each to one of the 6 Cortex page templates (see frontend skill / CODE_PATTERNS_FRONTEND_PAGES.md): List · Detail · Form · Settings · Dashboard · Auth. Confirm the list back to the user in one line before generating.
Section 1: Generation
1a. Per-screen rules (enforced by the mockup skill)
- Self-contained: each screen is ONE
.htmlfile, openable with no build step. Use Tailwind via CDN (<script src="https://cdn.tailwindcss.com">) for mid/high-fi; plain CSS grayscale for low-fi. - Inject the brand tokens into a
<style>block as CSS variables; components consume the tokens (never raw hex in markup). - Load the brand fonts via
<link>(Google Fonts) at mid/high-fi. - Realistic content — plausible names, numbers, dates, states. Never lorem ipsum.
- Show the meaningful states for that screen type (empty / loading skeleton / populated) where it adds signal.
- Semantic HTML + visible focus states + AA contrast (the
accessibilityskill applies even here). - High-fi screens carry a small fixed "MOCKUP — not production" ribbon.
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 · 91 lines · 90 tokens per session scan A 3797bff2b39a
gen-mockup is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 26d ago), licensed MIT. It adds 90 tokens to every session and 1,340 once invoked, about $0.0005 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 2026-08-31.
Other commands, from other repositories
_composicion
Protocolo interno compartido para la composición dinámica del equipo de Alfred según tarea, stack y señales runtime.
feature
Ciclo completo de desarrollo: producto, arquitectura, desarrollo, QA, docs, entrega.
ajustes
Configura Alfred Dev: autonomía, proyecto, Lucius, memoria y personalidad. Antes /alfred-dev:config.
discuss
Refina una idea o feature antes de abrir un flujo completo de implementación.
lucius
Segunda opinión técnica externa vía Codex CLI — diagnóstico y prescripción por ítem.
map-codebase
Analiza un repositorio existente y crea un mapa persistente del codebase.