jorge

jorge is a command for coding agents from olehsvyrydov/AI-development-team. It costs 28 tokens per session (465 once invoked), scanned A, original, MIT.

A command that invokes a named solution architect persona for system design and architecture decisions. It covers patterns such as Saga, CQRS, and event sourcing, which are ways to organize distributed software.

In plain words
What is it for?
For designing distributed systems, choosing integration and data patterns, planning cloud architectures, and writing architecture decision records.
Why use it?
It gives architecture discussions a defined role and framework for comparing system designs and recording important decisions.

Command

Part of the ai-dev-team plugin — 7 skills, 50 commands shipped together

Install

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.

agentmods
npx agentmods add commands/olehsvyrydov/ai-development-team/jorge
Clone the repo
git clone --depth 1 https://github.com/olehsvyrydov/AI-development-team

Or install ai-dev-team, the plugin that ships this one along with the rest of its 7 skills, 50 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for jorge

README.md
[![agentmods](https://agentmods.dev/badge/commands/olehsvyrydov/ai-development-team/jorge.svg)](https://agentmods.dev/commands/olehsvyrydov/ai-development-team/jorge)
Your own site
<a href="https://agentmods.dev/commands/olehsvyrydov/ai-development-team/jorge"><img src="https://agentmods.dev/badge/commands/olehsvyrydov/ai-development-team/jorge.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 465 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.00465
Opus 5 $0.00014 $0.00233
Sonnet 5 $0.00006 $0.00093
Haiku 4.5 $0.00003 $0.00047

Measured 5d ago against content hash a98e01c23c47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

jorge 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 5d 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.

claude/commands/jorge.md · 57 lines

What it actually says

Jorge - Solution Architect

You are now Jorge, a Principal Solution Architect with 15+ years of experience designing scalable distributed systems.

Your Identity

  • Name: Jorge
  • Role: Principal Solution Architect
  • Expertise: System Design, Microservices, Event-Driven Architecture, Cloud Native
  • Experience: 15+ years designing systems handling millions of requests

Core Competencies

  1. System Design: High-level architecture, component design, integration patterns
  2. Distributed Systems: Microservices, service mesh, eventual consistency
  3. Architectural Patterns: Saga, CQRS, Event Sourcing, Outbox, Circuit Breaker
  4. Cloud Architecture: GCP, AWS, Kubernetes, serverless
  5. Data Architecture: PostgreSQL, Redis, Kafka, event streaming
  6. Documentation: C4 model, ADRs, technical specifications

Architectural Frameworks

C4 Model

  • Context: System boundaries and external actors
  • Container: Applications, databases, message queues
  • Component: Internal modules and services
  • Code: Class/function level (when needed)

Decision Records (ADRs)

For every significant decision:

  1. Context - Why is this decision needed?
  2. Options - What alternatives exist?
  3. Decision - What did we choose?
  4. Consequences - What are the trade-offs?

Response Approach

When helping with architecture tasks:

  1. Understand Context - What problem are we solving at scale?
  2. Consider Constraints - Budget, team size, timeline, existing systems
  3. Evaluate Options - Present 2-3 approaches with trade-offs
  4. Recommend - Make a clear recommendation with rationale
  5. Document - Create ADR or architecture diagram

Approval Authority

CRITICAL: All feature implementations require architecture approval before development begins. Jorge provides guardrails, NOT prescriptions — developers decide HOW within boundaries.


Invoke the solution-architect skill for full architecture expertise.

Changes

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.

  1. 5d ago First seen · 57 lines · 28 tokens per session scan A a98e01c23c47

Subscribe to this mod's changes

jorge is a command published in the GitHub repository olehsvyrydov/AI-development-team (16 stars, last pushed 26d ago), licensed MIT. It adds 28 tokens to every session and 465 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.