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/init-projectgit 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 | $0.00071 | $0.14183 |
| Opus 5 | $0.00036 | $0.07091 |
| Sonnet 5 | $0.00014 | $0.02837 |
| Haiku 4.5 | $0.00007 | $0.01418 |
Grade A, and why
init-project scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
export const api = axios.create({ How it starts
The opening of the file, as written. The whole thing — 1,262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Initialization — Alpha AI Standards
Initialize project: $ARGUMENTS
Mode Detection
Automatically detect whether this is a new project or existing project:
# Check if target directory has existing code
ls $ARGUMENTS/app/ 2>/dev/null || ls $ARGUMENTS/src/ 2>/dev/null || ls $ARGUMENTS/package.json 2>/dev/null
Step 0: Detect Backend Language
Before scaffolding, detect the backend language:
--langflag: If provided, use it directly (python, nestjs, springboot)- Existing project: Detect from files:
- requirements.txt / pyproject.toml / app/main.py → python-fastapi
- package.json with @nestjs/ / nest-cli.json / src/main.ts → nodejs-nestjs
- build.gradle.kts / pom.xml with spring-boot / src/main/java/ → java-springboot
- New project without --lang: Default to python-fastapi
- Load reference files:
skills/alpha-architecture/references/LANG_PROFILE_{LANG}.md→ directory structure, deps, configs, Docker, verify commandsskills/alpha-architecture/references/CODE_PATTERNS_{LANG}.md→ code patterns
Step 0.1: Database Selection
Before scaffolding, ask the user which database(s) this project will use:
╔══════════════════════════════════════════════════════════════╗
║ DATABASE SELECTION ║
╠══════════════════════════════════════════════════════════════╣
║ ║
║ Which database(s) will this project use? ║
║ ║
║ 1. MySQL only — Relational data, strict schemas, ║
║ transactions, JOINs. Best for: e-comm, ║
║ SaaS, financial apps, CRUD apps ║
║ ║
║ 2. MongoDB only — Flexible documents, nested objects, ║
║ schema-less. Best for: CMS, logs, ║
║ profiles, analytics, real-time apps ║
║ ║
║ 3. Both (MySQL + MongoDB) — MySQL for transactional data, ║
║ MongoDB for logs/profiles/flexible docs ║
║ ║
║ Enter 1, 2, or 3: ║
╚══════════════════════════════════════════════════════════════╝
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.
- yesterday First seen · 1,262 lines · 71 tokens per session scan A 84e3fec4d606
init-project is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 25d ago), licensed MIT. It adds 71 tokens to every session and 14,183 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
alfred
Asistente contextual de Alfred Dev. Enruta automáticamente al flujo o comando operativo correcto.
feature
Ciclo completo de desarrollo: producto, arquitectura, desarrollo, QA, docs, entrega.
_composicion
Protocolo interno compartido para la composición dinámica del equipo de Alfred según tarea, stack y señales runtime.
ajustes
Configura Alfred Dev: autonomía, proyecto, Lucius, memoria y personalidad. Antes /alfred-dev:config.
audit
Auditoría completa del proyecto con 4 agentes en paralelo.
discuss
Refina una idea o feature antes de abrir un flujo completo de implementación.