Leaderboard/Automation/codex-autoresearch
Last commit on September 6, 2026·Created on April 20, 2026

TheGreenCedar/codex-autoresearch

Automates iterative optimization loops for measurable technical targets
Combined rank
#372
across all skills
In Automation
#27
category rank
Stars
836
-0.1% in last 7d
Forks
59
0.0% in last 7d
Watchers
0
0 watchers in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
TL;DR

Codex Autoresearch manages the triage and execution of measured improvement loops within local projects. It is designed for tasks where success is defined by a concrete metric, such as reducing test runtime, improving build speed, or lowering query latency.

Performance engineers and ML researchers can use the tool to run repeated experiments against a specific target, such as model loss, while keeping non-measurable work like documentation and architecture direct.

WHO IT'S FOR
Performance engineers
running optimization loops for measurable targets
ML / Data scientists
optimizing model loss through repeated experiments
Frontend / Web performance engineers
improving Lighthouse scores and bundle sizes
AI agent / automation builders
integrating autonomous optimization loops into workflows
Repository contents

1 skill file

Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.

Use this skill

Follow the documented setup, then try a first task.

Install with the Codex plugin picker

Installs: The codex-autoresearch workspace plugin · Codex

Before you start
  • Codex with access to the plugin picker

Run from: The repository you want to improve

  1. Enter this command in a Codex agent session to open the plugin picker.

    /plugins
  2. In the picker, choose `TheGreenCedar -> codex-autoresearch -> Install plugin`. Then start a new Codex task in the repository you want to improve.

Give it something to do.

Suggested first task

Run a bounded parser-runtime experiment

Uses codex-autoresearch

  • Replace the example benchmark command with the command that measures your project workload.
  • Replace the example metric with its name, unit, and optimization direction.
  • Replace the example checks command with your project's correctness checks.
  • Replace `src/parser.mjs`, `bench/parser.mjs`, and `tests/parser.test.mjs` with the corresponding editable and protected paths in your project.
  • Adjust the packet or time budget if needed before approving the proposed contract.
Use the codex-autoresearch skill for this task:

/goal @Codex Autoresearch run a measured loop to reduce parser runtime.
Benchmark: node bench/parser.mjs
Metric: seconds (s), lower is better
Checks: node --test tests/parser.test.mjs
Scope: src/parser.mjs
Protect bench/parser.mjs and tests/parser.test.mjs.
Measure two baselines and repeat each candidate before a keep.
Stop after 5 packets or 30 minutes; repeat measurements count toward that limit.
Propose the complete contract for approval before setup or execution.