feat: enforce subagent-driven-development on capable harnesses

- Subagent-driven-development is now mandatory when harness supports it
- No longer offer choice between subagent-driven and executing-plans
- Executing-plans reserved for harnesses without subagent capability
- Update plan header to reference both execution paths

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Jesse Vincent
2026-01-22 21:56:14 +00:00
parent fbcf9475e4
commit fd90ed5dd9
2 changed files with 17 additions and 15 deletions

View File

@@ -17,6 +17,12 @@
- Platform planning features (e.g., EnterPlanMode) should not be used
- Direct implementation without writing-plans is not allowed
**Subagent-driven development now mandatory on capable harnesses**
- On harnesses with subagent support (Claude Code), subagent-driven-development is now required after plan approval
- No longer offers a choice between subagent-driven and executing-plans
- Executing-plans is only used on harnesses without subagent capability
**OpenCode: Switched to native skills system**
Superpowers for OpenCode now uses OpenCode's native `skill` tool instead of custom `use_skill`/`find_skills` tools. This is a cleaner integration that works with OpenCode's built-in skill discovery.