Free Will

This is a forcing function for deliberate engineering decisions when your first instinct might be expensive to get wrong. It fires autonomously on mechanical triggers like a fix failing twice, adding a dependency, schema design, or changing a public API. The core mechanism refuses premature collapse: instead of greedy-decoding to the obvious solution, you hold multiple branches open (the urge, the contrarian, synthesis, out-of-box moves, precedent, first principles), ground each in real evidence from the codebase or docs, walk forward through consequences, then deliberately choose and try to refute the winner before acting. It logs decisions and rejected branches to docs/decision_logs/. Expensive on purpose, so not for routine calls. A decision worth more than one forward pass.

Install to Claude Code

npx -y skills add syahiidkamil/software-engineer-ai-agent-atlas --skill free-will --agent claude-code