Agent skills for Codex CLI

Create production-grade agent .md files aligned with the Anthropic 2026

Build, validate, and troubleshoot deep links for Codex, Cursor, VS Code, Visual Studio, and similar tools.

Use when rendering multi-agent debate, discussion, or review output in the terminal.

Multi-agent orchestration enforcement for /team command.

Testing and benchmarking LLM agents including behavioral testing,

Designs and runs agent evaluation frameworks to measure and improve performance.

Agent eXperience Interface (AXI) — ergonomic standards for building CLI tools that agents use via shell execution.

Coordinates multi-agent workflows, sub-agent task routing, and collaborator configurations within your project.

Meta-skill that orchestrates the full agent creation pipeline.

Claude Agent SDK build harness with a Planner/Builder/Evaluator loop.

Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.

Design spec with 98 rules for building CLI tools that AI agents can safely use.

Generate AGENT.md files with proper YAML frontmatter, role definitions, expertise areas, and prompt templates following Babysitter SDK…

Installs and manages standardized design collaboration rules in AGENTS.md to enforce disciplined AI coding practices.

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

Analyzes and improves AI agent collaboration environments based on the 12 principles of Agent Harness maturity.

Use when creating, editing, or deploying custom agent instructions or skills shared by Codex and Claude.

Use when writing or editing instructions for agents, including AGENTS.md, CLAUDE.md, SKILL.md, project rules, or reusable agent prompts.

Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last).

Builds self-verifying experiment laboratories and measurement feedback loops for optimization, debugging, visual fidelity, quality, cost…