# Big Three

> The foundational framework - Model, Prompt, Context. Every decision maps to one of these.

- Skill: `cleanexpo/big-three` (Agent Skill)
- Install (CLI): `npx skillmds@latest add cleanexpo/big-three`
- Raw SKILL.md: https://api.skillmd.com/api/skills/cleanexpo/big-three/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: cleanexpo (https://skillmd.com/u/cleanexpo)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/cleanexpo/big-three

---


# The Big Three

## Model - The Intelligence Layer
Choose the right model for each task. Opus for planning, Sonnet for implementation, Haiku for execution.

## Prompt - The Instruction Layer
Spec prompts with verification commands beat vague instructions every time.

## Context - The Knowledge Layer
Minimum viable context. Compress at boundaries. Recent matters more than old.

## Debugging Order
1. Is the MODEL capable? Test directly.
2. Is the PROMPT specific? Read it as the agent.
3. Is the CONTEXT sufficient? Check what the agent sees.