For developers using OpenAI's Codex CLI who want to move past trial-and-error.This guide is built from the patterns that actually work when you're:- Running multi-agent (subagent) workflows in parallel- Managing your context window like a scarce resource- Making fast calls on "should this be inline or dispatched?"- Routing tasks to the right model + reasoning-effort tier (minimal vs xhigh, cheap model vs frontier)- Handling subagent failures gracefullyIt's not tutorial-level. Not "10 tips." It's how someone operates at the edge case of agentic Codex — what to do, when to do it, and why.Contents:- Dispatch decision trees (which subagent — default, worker, explorer, or custom — and when)- Model routing for cost + reasoning (when a cheap model at low effort saves tokens, when frontier at high effort pays for itself) — including a hard sensitivity gate for what never leaves your control- Context economy discipline (11 concrete practices, including /compact, /new, and AGENTS.md)- 6 reusable prompt templates (research, architecture, code review, data transformation, debugging, escalation) plus a ready-to-paste AGENTS.md starter-rules set- Output formatting that scales (tables, progress bars, structured thinking)- Risk gates: sandbox_mode + approval_policy — what needs human confirmation, what you execute autonomously- Real workflow examples with failure/recovery texture (sanitized, generalizable)Full table of contents:1. Principles: Agentic Thinking2. Dispatch Triage: Agent Type Decision Tree3. Model Routing: Cost + Capability Trade-offs4. Context Economy: Managing Your Window5. Reusable Prompt Templates6. Output Formatting That Scales7. Risk Gates & Confirmation8. Real Workflow ExamplesOne-time $79 purchase.Useful for: senior developers, agentic AI builders, solo operators running multi-tool orchestration.