codex-orchestration
SolidOpenAI Codex CLI + Claude Code (Hizir) birlikte kullanim rehberi. Is dagitim pattern'leri, GitHub Actions workflow ornekleri, review dongusu ve iki AI yazilim asistaninin guclu yanlarini birlestiren orchestration stratejileri.
Install
Quality Score: 86/100
Skill Content
Details
- Author
- vibeeval
- Repository
- vibeeval/vibecosystem
- Created
- 2 months ago
- Last Updated
- 1 months ago
- Language
- C#
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
codex-cto
Inverted orchestration—Codex CLI acts as CTO (planning and reviewing), Claude Code executes with native tools. Use when a task benefits from external architectural oversight before and after implementation.
codex-agent
MANDATORY for code review - must use Codex CLI for all code reviews, then apply fixes based on Codex feedback. Also use for cross-verification, debugging, and getting alternative implementations.
codex
Delegate coding tasks to OpenAI Codex CLI agent. Use for building features, refactoring, PR reviews, and batch issue fixing. Requires the codex CLI and a git repository.
codex-orchestrator
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-5.4, gpt-5.4-pro, gpt-5-mini) via AGENTS.md persona injection.
codex-cli
Run OpenAI Codex CLI for coding tasks and second-opinion audits. Use when a user asks to run/ask/use Codex, says "codex prompt", or wants Claude to delegate a logic/code review to OpenAI models. Covers direct `codex` CLI invocation (exec, review, resume, apply, doctor, mcp), the six reasoning-effort levels (none/minimal/low/medium/high/xhigh), sandbox + dangerous flags, background execution, rate-limit safety, and when to defer to the official OpenAI Codex Claude Code plugin (`codex:rescue`) instead. Preflights with `codex doctor` to read the current default model + surface available updates; never hardcodes model/effort, letting Codex pick its own current best default unless the user explicitly names one.