autoresearch-wrapper

Discover dependency-aware optimization candidates across repo modules or files, classify them as surely or probably optimizable, collect the required metric and run settings, and drive a Git-worktree-backed autoresearch loop with status and resume helpers.

Create a feature-addition run with multiple candidate implementations. Use when the user wants to add a new feature and compare approaches to find the best capability ceiling.

Create a feature-deletion run that removes a part and optimizes dependent parameters. Use when the user wants to remove a module or file and find the best post-deletion configuration.

Show or plot recorded metric flow for an autoresearch-wrapper run. Use when the user wants the chronological metric sequence, best-so-far progression, or a terminal-friendly plot.

Poll the active autoresearch-wrapper run at a configurable interval. Use when the user wants to watch run progress, check rounds completed, best metric, and early exit status.

Start or resume a dependency-aware autoresearch-wrapper run in Git worktrees. Use when the target and metric are already configured and the user wants to initialize or continue the optimization loop.

Dependency-aware repo optimization workflow. Use when scanning a repo for optimizable parts, selecting a target, wrapping a repo-local script, configuring metrics and execution settings, or orchestrating a worktree-backed autoresearch run.

Show dependency-aware autoresearch-wrapper state for the current repo. Use when the user wants the selected part, readiness, runs, candidates, or current status summary.