agentic-development

Este extracto es una copia guardada durante la revisión. La fuente externa contiene la versión completa y actual.

---
name: agentic-development
description: Conversational guidance for building software with AI agents, covering workflows, tool selection, prompt strategies, parallel agent management, and best practices based on real-world high-volume agentic development experience. Use this skill when users ask about setting up agentic workflows, choosing models, optimizing prompts, managing parallel agents, or improving agent output quality.
---

# Agentic Development

This skill provides guidance for building software with AI agents based on real-world experience from high-volume agentic development, specifically Peter Steinberger's "Just Talk To It" methodology developed while building a ~300k LOC TypeScript React application entirely with AI agents.

**Core Philosophy**: Most elaborate frameworks, planning systems, and tooling are premature optimization. Treat AI agents like capable engineers—talk naturally, develop shared context, interrupt when needed, and iterate based on results rather than elaborate plans.

## When to Use This Skill

Apply this skill when users ask about:
- Setting up agentic development workflows
- Choosing tools and models for AI-assisted coding
- Optimizing prompt strategies and context management
- Parallel agent workflows and git management
- Debugging agent behavior or improving output quality
- Evaluating whether to use MCPs, subagents, or other abstractions
- Refactoring strategies with agents
- Testing approaches with AI assistance

## Core Principles

### 1. Think in Blast Radius, Not Complexity

Plan changes by file impact rather than perceived difficulty.

**Application**:
- Before starting, estimate: "Will this touch 3 files or 30?"
- Recognize that multiple large-radius changes prevent isolated commits and complicate recovery
- When an agent takes longer than anticipated, interrupt (escape key) and ask "what's the status?"
- Use "give me a few options before making changes" when uncertain about impact
- Trust that file changes are atomic—agents resume well after interruption

**Guidance Pattern**: When a user describes a task, help gauge blast radius by asking: "How many files do you think this will touch?" This builds intuition for redirecting agents.

### 2. Model Selection and Economics

**Subscription Economics**: Running 4-5 AI subscriptions (~$1k/month) provides effectively unlimited tokens versus per-API-call pricing that costs 5-10x more. This enables context-wasteful usage and multiple parallel agents.

**Model Characteristics**:
- **GPT-5-Codex**: Reads extensively before acting, requires shorter prompts (1-2 sentences often suffice), more cautious with pushback on questionable requests, introverted communication style
- **Claude Sonnet**: More eager to start, requires more explicit direction, verbose communication ("absolutely right", "100% production ready")

**Guidance Pattern**: When advising on model choice, emphasize that model personality affects mental health and productivity. The difference between aggressive optimism (while tests fail) versus quiet progress-making materially impacts burnout.

### 3. Parallel Agents in One Folder

Run 3-8 agents simultaneously in the same directory with one dev server, rather than git worktrees or branch-per-feature.

**Advantages**:
- Test multiple changes at once in running application
- Faster than spawning multiple dev servers or switching branches
- Agents perform atomic commits themselves
- Trade some isolation for velocity gains

**Requirements**:
- Agents must commit only their own changes (requires clear instruction file)
- Single shared dev server for testing
- Accept some git history messiness (clean in batches later)

**Guidance Pattern**: When users struggle with worktrees or branch management, suggest trying parallel agents in one folder for a week. Initial skepticism often gives way to appreciation.

### 4. Screenshots Are 50% of Context Engineering

Drag screenshots into terminal (showing UI, code, or errors) rather than writing len