Codex agents: AGENTS.md, skills, team use
Adding more subagents rarely speeds a team up; runs get abandoned and review piles up when nobody owns the result. Effective subagents delegation starts with agent boundaries: which tasks delegate safely, and which instructions, MCP, and skills control each run. This guide covers AI team skills and team AI workflows, plus the skill integration that lets engineers inspect and improve delegated work.
Book a callWhat teams need before scaling subagents
Subagents create leverage only when teams define clear delegation boundaries, review expectations, and repeatable context. The training focus is not more parallelism by default, but knowing which work can be delegated safely and which AGENTS.md, Codex MCP, skills, or team instructions control the run.
What the workshop installs
Teams leave with shared agent instructions, repository conventions, Codex code review checklists, and examples for turning repeatable engineering work into skills that engineers can inspect and improve.
How we measure success
The target is smaller review burden, faster setup on real tasks, fewer abandoned agent runs, and clearer rules for when engineers delegate, review, or own the work themselves.
Official references
Current product documentation we use when shaping this training topic.
Selected research
Representative field notes connected to this topic.
May 15, 2026
Codex mobile CLI docs your team can read anywhere
The codex mobile cli question is a docs question: how a team keeps AGENTS.md rules, run notes, and verification transcripts readable away from the desk.
May 24, 2026
Codex CLI Goal Mode, Appshots, and the Real Workflow
What Codex CLI Goal Mode and Appshots change day to day, and the AGENTS.md and verification habits that make them worth using.
May 14, 2026
Codex workflows: governance that lives in the repo
How to govern codex workflows from the repo: a connector roster, a ten-line done checklist, a slash catalog, and a verification latch reviewers can replay.
May 11, 2026
Is Codex CLI Giving MCP Too Much Reach?
Codex CLI does not widen MCP reach on its own. The fix for reviewer anxiety is an AGENTS.md line naming what each connector may do.
How to Set Up Agentic Coding Workflows and Guardrails
How to set up agentic coding workflows and guardrails for Codex, Claude Code, and Cursor, with receipts a reviewer can actually check.
May 20, 2026
Codex CLI 0.132.0, AGENTS.md and MCP Official Docs
What the Codex CLI 0.132.0 release changes for AGENTS.md rules and MCP connectors, and how to keep diffs reviewable.
Related training topics
AI code review habits for generated code
Codex workflows: CLI, MCP, and review
Safe AI coding practices for development teams
Codex team conventions for engineering orgs
Have you tried these?
Run the change on one branch. The methodology puts that in Review: an engineer still owns the merge. Training is the team version of that step.
Bring this into your team
We tailor the training to your codebase, adoption stage, and review standards.
Book a callPrefer to measure first? Take the free team check.