Spawn specialized Codex CLI subagents for focused development tasks. Each profile injects a custom AGENTS.md persona that shapes the agent's behavior, focus areas, and output format.
The skill automatically checks for Codex CLI updates on each invocation and updates if needed. This prevents issues caused by outdated CLI versions.
| reviewer | Code quality, bugs, performance | Pre-commit review, PR assessment | | debugger | Root cause analysis, fixes | Investigating bugs, tracing issues | | architect | System design, component boundaries | Planning changes, evaluating architecture | | security | OWASP, vulnerabilities, secrets | Security audits, compliance checks |
Orchestrate OpenAI Codex CLI with specialized subagents for code review, debugging, architecture analysis, security audits, refactoring, and documentation. This skill should be used when delegating focused development tasks to Codex subagents (gpt-5.3-codex, gpt-5.3-codex-spark, gpt-5.2) via AGENTS.md persona injection. Source: tdimino/claude-code-minoan.