
Agent Architect
This is meta tooling for building agents inside OpenCode. It walks you through creating agent configs via Q&A instead of writing YAML by hand. The workflow is smart: asks about core purpose first, researches the domain to avoid outdated assumptions, then drills into permissions and capabilities only as needed. Most useful when you're spinning up a new agent and don't want to reference the schema docs, or when an existing agent isn't triggering correctly and you need help tightening the description. It handles the fiddly bits like permission inheritance and skill deny-by-default rules so you don't have to memorize them.
- skills.sh installs
- 329
- GitHub stars
- 122
- last updated
- Jun 3, 2026
Install
$ npx -y skills add igorwarzocha/opencode-workflows --skill agent-architect --agent claude-codeInstalls into .claude/skills of the current project.
Files
Agent Architect
Create and refine opencode agents through a guided Q&A process.
<core_approach>
Agent creation is conversational, not transactional.
- MUST NOT assume what the user wants—ask
- SHOULD start with broad questions, drill into details only if needed
- Users MAY skip configuration they don't care about
- MUST always show drafts and iterate based on feedback
The goal is to help users create agents that fit their needs, not to dump every possible configuration option on them.
</core_approach>
<question_tool>
Batching: Use the question tool for 2+ related questions. Single questions → plain text.
Syntax: header ≤12 chars, label 1-5 words, add "(Recommended)" to default.
Sponsors
Details
- Repository
- github.com/igorwarzocha/opencode-workflows
- Categories
- Code Review & Quality, AI & Agent Building
- First seen
- Jun 3, 2026