mirror of
https://github.com/obra/superpowers.git
synced 2026-06-29 14:09:07 +08:00
274cf1617b
Condense the injected bootstrap without dropping behavior-shaping content: replace the graphviz flowchart with prose (1% rule, plan-mode->brainstorm gate, announce + checklist->todos), fold Instruction-Priority into User Instructions, and drop the per-platform skill-loading section. Keep the full Red Flags rationalization table (all 12), the platform tool-mapping pointer (now a skill-relative path list), skill priority framed as a category (process before implementation, not just the two named skills), and user-instruction precedence plus the WHAT/HOW guard. Snapshot on a local branch for review — NOT final, NOT for dev. Open items: the dropped "Skill Types" (rigid/flexible) section, and evals for user preferences overriding skills. Clean Docker evals show the more-aggressive g-minimal preserves load-bearing triggering across opus/sonnet/haiku/codex/ gemini/kimi; this variant keeps more content. Claude-Session: https://claude.ai/code/session_01Hz32pBE7kiqr78DY6PWmZN