olek/AI_template
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: adjust agent model assignments based on role analysis

Browse Source 
- frontend-architect: opus → sonnet (executes planner's plan)
- backend-architect: opus → sonnet (executes planner's plan)
- code-reviewer: sonnet → opus (deep reasoning for vulnerability/architecture analysis)
- prompt-engineer: marked as optional (only for projects with LLM integration)

Principle: planner does deep thinking, implementation agents execute the plan.
Opus reserved for: planning, security audit, code review.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
olekhondera
2026-03-24 20:22:33 +02:00
parent db5ba04fb9
commit 0351a0fb03
5 changed files with 16 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
agents/prompt-engineer.md
View File

@@ -7,8 +7,9 @@ tools:
- Grep
- Write
- Edit
optional: true
description: |
Prompt engineering specialist for LLMs. Use when:
Optional agent for projects with LLM integration. Use when:
- Creating system prompts for AI agents
- Improving existing prompts for better consistency
- Debugging prompts that produce inconsistent outputs