uditgoenka

uditgoenka/autoresearch

Command

8 personas interrogate requirements until constraints saturate.

uditgoenka/autoresearch

Command

Adversarial debate with blind judges until convergence.

uditgoenka/autoresearch

Command

Layered regression stability gate: capture baseline behavior on the base ref, diff the candidate, verdict STABLE/UNSTABLE before you push.

uditgoenka/autoresearch

Command

Generate edge cases across 12 dimensions from a seed scenario.

uditgoenka/autoresearch

Command

STRIDE + OWASP security audit with red-team adversarial personas.

uditgoenka/autoresearch

Command

Ship anything through 8 phases: checklist, dry-run, deploy, verify.

uditgoenka/autoresearch

Instructions file CodexOpenCode

Instructions for uditgoenka/autoresearch, covering agents.md — autoresearch, what is autoresearch?, installation, claude code (plugin) and codex (plugin).

uditgoenka/autoresearch

Plugin Claude Code

Autonomous improvement engine. 14 commands: iterate, plan, debug, fix, security, ship, scenario, predict, learn, reason, probe, improve, evals, regression.

uditgoenka/autoresearch

Hook

Runs before the agent uses a tool for Write, Bash, Glob, Grep, Read and Edit tool calls, executing node-hook-runner.sh via bash (7 commands). From uditgoenka/autoresearch.

uditgoenka/autoresearch

Hook

Runs when you submit a prompt, before the agent sees it, executing node-hook-runner.sh via bash (3 commands). From uditgoenka/autoresearch.

uditgoenka/autoresearch

Hook

Runs when a subagent starts, executing node-hook-runner.sh via bash. From uditgoenka/autoresearch.

uditgoenka/autoresearch

Hook

Runs when a session starts, executing node-hook-runner.sh via bash. From uditgoenka/autoresearch.

uditgoenka/autoresearch

Hook

Runs when a session ends, executing node-hook-runner.sh via bash. From uditgoenka/autoresearch.