autoresearch
Runs an autonomous loop that modifies code, verifies the result against a mechanical metric, and keeps or discards each change, for iterative improvement, debugging and ship-readiness checks in Claude Code.

Runs an autonomous loop that modifies code, verifies the result against a mechanical metric, and keeps or discards each change, for iterative improvement, debugging and ship-readiness checks in Claude Code.
Autonomous iteration loop: modify, verify, keep/discard against any metric
Autonomous iteration loop: modify, verify, keep/discard against any metric
Hunt bugs with scientific method: hypothesize, test, falsify, repeat
Analyze iteration results: trends, plateaus, regressions, recommendations
Crush errors one-by-one until zero remain: tests, types, lint, build
Research ICP challenges, discover improvements, generate PRDs
Scout codebase and auto-generate docs — or a navigable wiki knowledge base — with validation-fix loop
Convert a goal into validated Scope, Metric, Direction, Verify config
5 expert personas debate proposed changes before implementation
8 personas interrogate requirements until constraints saturate
Adversarial debate with blind judges until convergence
Layered regression stability gate: capture baseline behavior on the base ref, diff the candidate, verdict STABLE/UNSTABLE before…
Generate edge cases across 12 dimensions from a seed scenario
Is this you? Claim your profilePut a plugin at the top of Plugins, from $9