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/gap-analysisgit 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 | $0.00042 | $0.04372 |
| Opus 5 | $0.00021 | $0.02186 |
| Sonnet 5 | $0.00008 | $0.00874 |
| Haiku 4.5 | $0.00004 | $0.00437 |
Grade A, and why
gap-analysis 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 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.
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 — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gap Analysis — Alpha AI Standards Compliance (Context-Aware)
Analyze project at: $ARGUMENTS (default: current directory)
Compare the existing codebase against ONLY the standards relevant to this project — NOT every standard in the book.
KEY PRINCIPLE: A project that doesn't need MongoDB should NOT be flagged for missing MongoDB. A project without payments should NOT be flagged for missing Razorpay. Only check what the project ACTUALLY requires.
Step 0: Detect Project Requirements
Before checking any standards, first understand WHAT this project needs.
0.1: Read Project Context
Gather requirements from these sources (check in order):
1. Read PRD.md or PRD_*.md (if exists) — most authoritative source of requirements
2. Read SPRINT_PLAN.md (if exists) — tells what features are planned
3. Read PROJECT_ANALYSIS.md (if exists, from /analyze-project)
4. Read README.md (if exists) — project description
5. Read CLAUDE.md (if exists) — project-specific standards
6. Quick scan of codebase (package.json, requirements.txt, docker-compose.yml)
0.2: Build Project Requirements Profile
Based on the context gathered, build a requirements profile by answering YES/NO to each:
PROJECT REQUIREMENTS PROFILE
═══════════════════════════════
Project Name: [detected name]
Project Type: [API only | Web app | Mobile app | Full-stack | AI/ML | Library]
Description: [1-line from PRD/README]
Core Requirements:
Has backend API? → [YES/NO]
Has user authentication? → [YES/NO]
Has SQL database (relational data)? → [YES/NO]
Has document/NoSQL storage needs? → [YES/NO] — only YES if project stores:
- Unstructured documents, logs, audit trails
- Highly nested/variable-schema data
- Chat messages, activity feeds, analytics events
- If NO clear need → NO (do NOT default to YES)
Has caching/session needs? → [YES/NO] — only YES if project has:
- High-traffic endpoints needing caching
- Real-time session management
- Rate limiting, queues, pub/sub
- If simple CRUD app → NO
Has payment processing? → [YES/NO]
Has India market / INR billing? → [YES/NO] — determines Razorpay vs Stripe
Frontend Requirements:
Has web frontend? → [YES/NO]
Has mobile app? → [YES/NO]
Needs dark mode? → [YES/NO] — YES if user-facing app
Needs i18n (multilingual)? → [YES/NO] — only if PRD mentions multiple languages
Needs animations/transitions? → [YES/NO]
Feature Requirements:
Has file uploads? → [YES/NO]
Has full-text search? → [YES/NO] — only if search is a core feature
Has real-time features? → [YES/NO] — chat, live updates, notifications
Has push notifications? → [YES/NO] — only if mobile or PWA with push
Has email sending? → [YES/NO]
Has social login (Google/Apple)? → [YES/NO]
Has role-based access (RBAC)? → [YES/NO] — only if multiple user roles
Has 2FA/MFA? → [YES/NO] — only if high-security app
Has background jobs/queues? → [YES/NO]
AI/GenAI Requirements:
Has AI/LLM features? → [YES/NO]
Has RAG/document search? → [YES/NO]
Has AI agents/tools? → [YES/NO]
Has MCP/A2A integration? → [YES/NO]
Infrastructure:
Needs error tracking (production)? → [YES/NO] — YES if deploying to production
Needs analytics? → [YES/NO] — only if tracking user behavior
Needs monitoring? → [YES/NO] — YES if production deployment
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 · 420 lines · 42 tokens per session scan A ce4323974311
gap-analysis is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 25d ago), licensed MIT. It adds 42 tokens to every session and 4,372 once invoked, about $0.0002 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
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.