Codex agents and team instructions
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.
What 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.
claude-code-survival-kr Guards Working Code
A Show HN repo turns vague AI coding advice into hard repo rules that keep agents from breaking stable code.
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.
MCP training for engineering teams
Practical mcp training for engineering teams using agentic coding, review guardrails, and connector boundaries.
Codex workspace agents need repo rules
Codex workspace agents and Codex cloud agents need repo rules: scoped boundary files, connector cards, and replay receipts reviewers can check.
Agent-talk Adds Agent-to-Agent Messaging
Agent-talk lets Claude Code sessions message through retalk, and shows how to test agent collaboration safely.
Codex CLI, Appshots, and Goal Mode
A practical Codex CLI comparison for codex cli vs claude code, with AGENTS.md, MCP, and verification loops.
Related training topics
Bring this into your team
We tailor the training to your codebase, adoption stage, and review standards.
Book a 15-minute sync