# Run autonomous improve verify keep-or-revert loops across coding tasks with autoresearch

> Turn Claude Code, OpenCode, or Codex into a metric-driven loop that makes one change at a time, verifies it mechanically, and keeps or reverts automatically.

- Skill: `agentskillexchange/run-autonomous-improve-verify-keep-or-revert-loops-across-co` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/run-autonomous-improve-verify-keep-or-revert-loops-across-co`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/run-autonomous-improve-verify-keep-or-revert-loops-across-co/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/run-autonomous-improve-verify-keep-or-revert-loops-across-co

---


# Run autonomous improve verify keep-or-revert loops across coding tasks with autoresearch

Turn Claude Code, OpenCode, or Codex into a metric-driven loop that makes one change at a time, verifies it mechanically, and keeps or reverts automatically.

## Prerequisites

Git repository, one supported agent environment such as Claude Code, OpenCode, or OpenAI Codex, mechanical verification command or metric

## Installation

Requirements and caveats from upstream:
- [Karpathy's autoresearch](https://github.com/karpathy/autoresearch) demonstrated that a 630-line Python script could autonomously improve ML models overnight — **100 experiments per night** — by following simple princ...
- The wizard walks you through 5 steps: capture goal → define scope → define metric → define direction → validate verify command (dry-run). Every gate is mechanical — scope must resolve to files, metric must output a nu...

Basic usage or getting-started notes:
- [How It Works](#how-it-works) · [Commands](#commands) · [Quick Start](#quick-start) · [Guides](guide/) · [FAQ](#faq)
- | /autoresearch | Run the autonomous iteration loop (unlimited) |
- | Iterations: N | Add to inline config to run exactly N iterations then stop |

- Source: https://github.com/uditgoenka/autoresearch
- Extracted from upstream docs: https://raw.githubusercontent.com/uditgoenka/autoresearch/HEAD/README.md

## Documentation

- https://github.com/uditgoenka/autoresearch#readme

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/run-autonomous-improve-verify-keep-or-revert-loops-across-coding-tasks-with-autoresearch/)