Codex Stops at 4 Subagents. Raise multi_agent_v2 Concurrency
Codex defaults to 4 concurrent subagents. This multi_agent_v2 config raises the session cap so you can run dozens in parallel. Start small to avoid 429s.
Read articleTopic Pillar & Hub
Codex
Practical Workflows, Usage Limits, and Multi-Folder Execution with OpenAI Codex
Deep-dive operational notes for OpenAI Codex and CLI tooling. From understanding usage reset mechanics to optimizing multi-folder projects, these field reports help builders maximize productivity.
Core Engineering Pillars
Rate Limits & Reset Architecture
Understanding how Codex throttles usage and how to design failover strategies.
Multi-Repo & Multi-Folder Workflows
Organizing complex mono-repos and microservices for focused agent execution.
Self-Audit & Quality Assurance
Running automated self-audits before merging agent-generated diffs.
Recommended Progression
- 1. Optimize Workspace Boundaries
Configure folder scoping to prevent excessive scanning.
- 2. Monitor Token & Cost Caps
Set up session tracking to avoid sudden rate limit blocks during active development.
Frequently Asked Questions
How does Codex handle project-wide context?
Codex builds indexed symbol representations, but performance scales dramatically when work is constrained to specific target modules.
Field Reports & Case Studies
Codex Articles (15)
Codex Usage Reset August 30, 2026: Tibo on Longer Limits
The August 30, 2026 Codex usage reset comes with token fixes from OpenAI. Tibo says the same limits may last 10% to 50% longer.
Read article
The Story Behind Codex Reset, According to Tibo
Tibo Sottiaux says Codex Reset began as usage compensation after broken builds. He still controls the reset button.
Read articleA Dual-Agent Coding Workflow with Codex and ChatGPT Pro
Use Codex as project lead and independent verifier while ChatGPT Pro handles focused engineering tasks through a browser-based collaboration loop.
Read articleCodex Usage Will Reset Again. OpenAI Found the Drain.
OpenAI found several causes behind faster Codex usage drain and plans a full paid-user reset. Builders are already planning what to run next.
Read article
How to Use DeepSeek Models in Codex
Configure Codex to use DeepSeek models with DeepSeek's official setup script, verify the result, and restore your previous configuration.
Read article
How I Choose GPT-5.6 Sol, Terra, Luna, and Effort Levels
A practical decision guide for choosing a GPT-5.6 model and reasoning effort level based on task difficulty, speed, and iteration cost.
Read articleCodex Just Shipped Two Features That Matter
A practical look at ChatGPT Voice and multi-folder projects in Codex, including their workflow benefits, limits, and setup details.
Read articleRunning Kimi K3 Inside Codex
A step-by-step setup for running Kimi K3 inside the Codex app through CC Switch, with routing details and model-picker caveats.
Read articleCodex Is Burning Through Your SSD. Here's How I Stopped It
A practical guide to checking Codex's SQLite log writes, blocking the unwanted inserts, and protecting your SSD without deleting conversation history.
Read articleCodex Can Now Copy Your Actions
Codex Record and Replay watches a Mac workflow once, turns it into an editable Skill, then reruns it with new inputs. macOS only, not in the EU.
Read articleA Practical Guide to Using /goal in Codex
Use Codex goals as completion contracts with explicit outcomes, verification, constraints, iteration rules, and safe stop conditions.
Read articleCodex Is No Longer Just a Coding Tool
OpenAI repositioned Codex for knowledge work with role-specific plugins, hosted Sites, and Annotations. Non-developers are growing fastest.
Read articleUsed Codex to figure out what was eating my Mac's storage
A read-only Codex prompt that turned macOS System Data into a prioritized storage map, with 180 GB reclaimable on a 1TB Mac.
Read articleLet Codex Distill Your Own Workflow
How Codex can review your recent work, find repeated manual workflows, and turn the best ones into reusable skills, agents, or automations.
Read article