executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
locality-aware-parallel-autoregressive-decodingAccelerate image generation by generating multiple patches in parallel instead of sequentially. Uses locality-aware ordering that generates spatially-close tokens while keeping concurrent tokens far apart, reducing steps from 256 to 20 (12× speedup) while maintaining quality.
Independent GitHub snapshot · Automated classification · Original documentation governs