codex-research

Name: codex-research
Availability: InStock
Author: oozoofrog

Automate Codex-driven experimentation loops and record results in ledger.tsv.

1|Updated Mar 8, 2026

Search Tags:#automation #research #codex #contract #experiment #loop #ledger

Ready to run

npx skills add https://github.com/oozoofrog/codex-skills --skill codex-research-oozoofrog

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: codex-research
Source: https://github.com/oozoofrog/codex-skills/tree/main/codex-research
Command: npx skills add https://github.com/oozoofrog/codex-skills --skill codex-research-oozoofrog

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Codex Research automates goal-oriented iterative experimentation by orchestrating Codex-driven hypotheses, experiments, and results recording, reducing manual setup and monitoring overhead.

Core Features & Use Cases

Orchestrates design, guided-loop, and autonomous-loop modes for flexible experimentation.
Maintains a structured workspace with program.md, contract.md, state_snapshot.md, and ledger.tsv to track progress.
Provides a CLI workflow to init, check status, and run iterations with max rounds and optional web search or full automation.
Records per-round data in rounds/ with prompts, messages, events, and evidence.

Quick Start

Initialize a workspace, write a contract, and start the guided loop to begin the first research round.

Frequently Asked Questions about codex-research

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate iterative research loops with Codex?▼

Automate iterative research loops by initializing a workspace with a contract, then running guided or autonomous modes to repeatedly invoke Codex for hypotheses and experiments. The workflow orchestrates design, guided-loop, and autonomous-loop modes for bounded iterative work and overnight exploration.

What is a contract-and-state workflow for automated experimentation?▼

A contract-and-state workflow enforces structured experimentation by maintaining program.md, contract.md, state_snapshot.md, and ledger.tsv to track hard gates, experiment status, and control actions. This ensures goal-oriented iterative work remains bounded and auditable throughout the research process.

How do I set up a workspace for Codex-driven experimentation?▼

Initialize a workspace, write a contract defining your goal boundaries, and start the guided loop to begin the first research round. The CLI workflow supports init, status checks, and running iterations with max rounds, optional web search, and full automation settings.

Can I run overnight autonomous exploration with Codex research loops?▼

Yes, autonomous-loop mode supports overnight exploration by running Codex iterations without manual intervention. You can configure max rounds and enable full automation to let the system form hypotheses, test changes, and record results in the ledger autonomously.

Does Codex research loop mode track experiment results in a ledger?▼

Yes, the workflow records per-round data in a ledger.tsv file and a rounds/ directory containing prompts, messages, events, and evidence. This structured recording tracks experiment status and control actions across all iterations for later review.

What are the limitations of automated Codex research loops?▼

Automated Codex research loops require a structured workspace with predefined contracts and are bounded by max rounds settings. The workflow enforces hard gates through state snapshots, meaning experiments cannot proceed beyond contract-defined boundaries without explicit control actions.