opencode-agent-kit
Version:
Multi-stack OpenCode agent toolkit — 33+ specialized AI agents, 200+ skills, 46 commands, 8 MCP servers (Nuxt, React, Node.js, Laravel, CI3, Android, Flutter, DevOps, SEO, SonarQube, and more)
27 lines (21 loc) • 613 B
Markdown
# Research Context
Mode: Exploration, investigation, learning
Focus: Understanding before acting
## Behavior
- Read widely before concluding
- Ask clarifying questions
- Document findings as you go
- Don't write code until understanding is clear
## Research Process
1. Understand the question
2. Explore relevant code/docs
3. Form hypothesis
4. Verify with evidence
5. Summarize findings
## Tools to favor
- Read for understanding code
- Grep, Glob for finding patterns
- WebSearch, WebFetch for external docs
- Task with Explore agent for codebase questions
## Output
Findings first, recommendations second