Use when creating, auditing, upgrading, or validating Codex hook packs, hooks.json files, hook scripts, or repo-local/user-level .codex hook installs.
Configure, repair, or tune Ian's Codex HUD plugin and Claude-HUD-style Codex CLI footer/title. Use when the user asks for codex-hud, a clean Codex status line,…
OpenAI Codex CLI(`codex exec`)의 내장 `image_generation` 툴로 이미지를 생성하는 스킬. 단일/배치/병렬 생성 지원. 핵심 강점은 **최대 5장 동시 병렬 생성** (실측 직렬 대비 2.4~2.85배 속도).
Start or reuse a self-contained local web gallery for browsing Codex-generated images. Use when the user asks to browse Codex generated images, open a local image gallery, inspect…
Use when dispatching implementation tasks to Codex CLI (GPT-5.5) as the coder while this session plans and judges — a written plan or task brief exists and coding labor should be…
Ask Codex CLI (gpt-5.5) to implement scoped code changes in the current repository, then have Claude inspect the resulting diff and verification.
Delegate implementation work to Codex (via the codex-companion runtime), then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR.
Codex CLI를 sub-agent로 활용하여 실제 구현 작업을 수행합니다. Claude가 작업을 분석/분해하고, Codex가 코드 작성/수정/리팩토링을 담당합니다. "Codex로 구현", "구현해줘", "코드 작성해줘", "병렬 구현" 요청 시 활성화됩니다.
Use OpenAI Codex from inside Claude Code — code reviews, adversarial reviews, and delegating tasks to Codex.
Provides codex-plugin-cc integration workflow for cross-checking, development delegation, and idea generation with OpenAI Codex.
Invoke OpenAI Codex CLI with the correct configuration for autonomous code generation. Use when you need Codex to generate or regenerate code files, implement features, or execute…
Autonomous issue planning and execution workflow for Codex. Supports batch issue processing with integrated planning, queuing, and execution stages.
Execute tasks using the OpenAI Codex CLI (GPT-5.2). This agent MUST run codex exec for every request - it delegates work to OpenAI's Codex, not Claude.
Cross-provider LLM judge using Codex (GPT-5) to evaluate implementations written by Claude. Internal skill invoked by the insistir lead during the review loop. Not user-facing.
Codex-specific complement to the generic kickoff skill — install the GoC Codex plugin from the repo marketplace, explain plugin hook activation, and verify the goc CLI path.
Use the Codex Kit CLI to initialize, update, or inspect a Codex-ready project scaffold in the current workspace.
Run a codex review on my latest edits. Use when the user says things like "review my changes with codex", "run codex on my edits", "start an edit-review loop", "check my code with…
Configure a local luna_max Codex agent only after a Luna spawn route was rejected and the user explicitly approves the fallback. Do not use for ordinary subagent routing.
Master behavior rules for Codex. Use as the top-priority baseline for request classification, coding quality, dependency awareness, and completion checks across all coding…
Use this `codex-mcp` skill to instruct another AI Agent to invoke a tool or execute a workflow on your behalf for the following scenario, 1.When you are requested to invoke a mcp…
Use when wiring MCP servers or plugins into Codex CLI and the AgentOps Codex skill bundle. Triggers:
Use when the user wants to set up or sync Codex MCP servers for Polaris workflows. Trigger: 'codex mcp', '同步 mcp', '設定 codex mcp', '讓 codex 接 mcp', 'codex mcp setup'.
在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务，由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流；也用于用户明确要求模型路由、后台 Worker、Agents Team…
Browse OpenAI Codex session logs stored in ~/.codex/sessions. Provides list/show/watch helpers via the local Swift project at ~/Developer/CodexMonitor.
マルチエージェントでタスク分解・委譲・並列実行・結果統合を行うための共通運用スキル。Use when: 「マルチエージェントで進めたい」「並列で進めたい」「サブエージェントに任せたい」「複数 agent で調査/実装/レビューしたい」。Claude Code / Codex のどちらでも使える共通原則を定義し、末尾にツール別の読み替えを置く。
Onboards a non-Claude-Code agent (GitHub Copilot CLI / Cursor / Aider / Codex / Devin) to this repo on session start.
OpenAI Codex CLI + Claude Code (Hizir) birlikte kullanim rehberi. Is dagitim pattern'leri, GitHub Actions workflow ornekleri, review dongusu ve iki AI yazilim asistaninin guclu…
[DEPRECATED] Run multiple AI agent threads in parallel with bounded concurrency. Use evolving-workflow instead.
Use this when updating the codex submodule or when patch files in codex-patches/ need to be added, regenerated, or repaired.
[TMUX MODE] Send plan to Codex via tmux file-based IPC. Only use when user explicitly runs /codex-plan-review command.
Use when the user mentions plugin-dev, wants a plugin-dev-like toolkit inside Codex CLI, asks how to start creating skills/agents/MCP/commands/hooks, or wants a guided menu to…
Use when the user asks how to structure Codex skills (folders, SKILL.md, supporting files), wants plugin-dev-like organization, or needs conventions for templates/scripts bundled…
Use when the user suspects a Codex skill is not triggering, wants to validate SKILL.md frontmatter (name/description), check description quality for discovery, or needs a…
Use when managing Codex CLI plugins, plugin marketplaces, local marketplace refreshes, cache visibility, MCP server list/get/add/remove/login/logout, MCP bearer token environment…
Critic phase for codex-pr-lessons playbook — analyze a PR and extract quality signals
Distillation phase for codex-pr-lessons playbook — compress raw learnings into patterns and update skills
Plan phase for codex-pr-lessons playbook — load state, determine next batch of PRs to analyze
Loop a GitHub PR through @codex review until clean or blocked on user judgement.
Threshold verification for codex-pr-lessons playbook — determine if distillation should trigger
Use codex-profiles to run Codex CLI or Codex Desktop with isolated CODEX_HOME profiles for separate accounts, projects, and local state.
Diagnose and resolve codex project recency sort failures. Use when Use only when Codex Desktop is grouped by project, Last updated is selected, a recently updated project remains…
Use when improving Codex-style task prompts, AGENTS.md instructions, review briefs, subagent handoffs, or implementation requests so they are precise, scoped, testable, and safe…
Read and integrate response from Codex. Use when user says codex read, get codex response, or check codex results.
Force deliberate, evidence-backed, non-generic reasoning for complex engineering work. Use when the user asks for deeper thinking, less generic output, higher specificity, better…
Guide to capturing, refining, and publishing workflows using Codex Record & Replay (launched June 18 2026).
Iteratively review and refine a design doc or plan using Codex reviews until no significant issues remain.
Open one new native Codex task with a compact handoff, end this turn, and receive a single completion or blocker message back.
Use when you need Codex to coordinate multiple agents through Agent Relay for peer-to-peer messaging, lead/worker handoffs, or shared status tracking across sub-agents and…
Use to resume a previous Codex conversation. Triggers on "continue codex", "resume codex", "pick up where codex left off", "continue the codex session".
Use when you want Codex to review its own recent history (last N days or specific period) and improve its behavior.
Run a Codex code review as a second-opinion gate. Returns structured result with findings or graceful skip. Used by /bug-sweep and /workday-complete.
Professional code review with auto CHANGELOG generation, integrated with Codex AI — from BenedictKing/codex-review
Use when running codex exec in a least-privilege sandbox with machine-checkable proof. Triggers:
Use at the start of a Codex session (especially sandboxed) to run `scripts/codex-sandbox-preflight.sh` and interpret network + writable_roots constraints.
List and inspect local Codex session history by reading `~/.codex/session_index.jsonl`, `~/.codex/sessions/`, and `~/.codex/archived_sessions/`.
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality.
Запускает Codex в режиме falsification-first: ломает идею/код/архитектуру ДО реализации. Ищет hidden assumptions, failure modes, edge cases.
VMware vCenter/ESXi read-only monitoring. Code-level enforced safety — no destructive operations exist in this codebase.
Codex-only skill administration for auditing, enabling, disabling, restoring, and verifying local Codex skills.
Curate Codex skills with a Hermes-style maintenance pass: usage telemetry, stale/archive candidates, pins, backups, dry-run reports, and rollback guidance.