🔬

AI EngineeringTypeScript

Codex Autoresearch

by TheGreenCedar

Codex Autoresearch is an AI Engineering skill for Claude Code, published by TheGreenCedar in codex-autoresearch.

830 stars59 forkson TheGreenCedar/codex-autoresearchAdded 2026/08/22Repository updated 2026/08/02

View source on GitHub Download repo ZIP

agent-skillsautonomous-agentsautoresearchcode-optimizationcodexllm-agents

Install in seconds

Install Codex Autoresearch

Copy Codex Autoresearch into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/TheGreenCedar/codex-autoresearch/tree/main/plugins/codex-autoresearch/skills/codex-autoresearch ~/.claude/skills/codex-autoresearch

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/TheGreenCedar/codex-autoresearch.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: plugins/codex-autoresearch/skills/codex-autoresearch/SKILL.md in TheGreenCedar/codex-autoresearch
Installs to: ~/.claude/skills/codex-autoresearch
Collection: The only skill cataloged from this repository
Category: AI Engineering — 2451 skills

What Codex Autoresearch does

Codex Autoresearch runs a measured, resumable improvement loop in a local project. Use it for benchmark-driven optimization, quality-gap research, packet logging, and review-branch finalization.

Codex Autoresearch is cataloged under AI Engineering on DirSkills. Codex Autoresearch comes from a repository tagged agent-skills, autonomous-agents, autoresearch, code-optimization and codex.

Documentation

README

Excerpt

Codex Autoresearch

Turn an improvement request into a measured, resumable loop. Report the metric, decision, evidence, next action, and real publication state. Do not replace them with a generic claim that the project is "better."

setup -> doctor -> next -> log -> state -> finalize-preview

Use this as the only Codex-facing Autoresearch skill. Do not route to retired subskills, slash commands, or MCP surfaces.

Establish the working truth

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Codex Autoresearch

How does Codex Autoresearch compare to other AI Engineering skills?
Codex Autoresearch ranks #1566 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Codex Autoresearch against them. Open each page to compare what they document and how they install.

More AI Engineering skills

Codex Autoresearch is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #1566 by stars among them.

Browse all AI Engineering skills →

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.