Mastering advanced AI tooling in Codex

Overview

Configure Codex as a durable, repo-native agent using AGENTS.md, config.toml, skills, and safe automation patterns. Drive Codex to plan, patch, test, and resume work reliably across sessions utilizing latest features and subagents orchestration.

Syllabus

Course 1: Codex Agent Setup & Session Operations
Course 2: Codex CLI Configuration, Skills, and Safe Workflows
Course 3: Codex Skill Engineering
Course 4: Codex Automation with the OpenAI SDK
Course 5: Codex Subagents & Multi-Agent Orchestration

Courses

0 reviews
2 hours
View details

Move beyond basic prompting by turning Codex into a consistent “agent” inside a real mid-size repository. Learn how to configure durable behavior with AGENTS.md, revisit the default slash commands that control execution and risk, run Codex in non-interactive mode for automation, and reliably resume work across sessions.
0 reviews
3 hours
View details

Configure Codex like a real developer tool by tuning core behavior in config.toml including web search while creating custom skills that work like project specific slash commands and building workflow templates for complex tasks. Learn to pass natural language arguments into commands and use inline shell capture with ! so your prompts include live repository state for grounded real time analysis.
0 reviews
2 hours
View details

Turn Codex into your reusable engineering playbook. Build skills that trigger automatically, enforce standards, and deliver bug triage, minimal patches, and test plans—so you ship faster with fewer surprises.
0 reviews
2 hours
View details

Use Codex beyond terminal chat by invoking it from scripts with the Codex CLI and the OpenAI Python SDK. Learn how the openai library powers Codex programmatically, and build small, deterministic AI-driven steps that save outputs as artifacts for developer tools and CI automation.
0 reviews
2 hours
View details

Scale from one assistant to a coordinated swarm. Run isolated subagents in parallel, enforce strict JSON outputs, and assemble gated pipelines with logs/retries—unlocking reliable, reviewable automation for big repos.