Codex MCP Go

MCP server wrapping Codex CLI for stdio-based tool calls.

Cross-Model Review (Claude reviews Codex)

After Codex completes development and local validation passes, invoke the local Claude CLI for heterogeneous-model review. Different models have different blind spots; cross-model review surfaces issues that self-review cannot catch.

codex-review-loop

Adversarial PR code review using Codex CLI. Codex review (~20-50 min) -> structured findings -> HITL approval -> fix loop.

agpair

Use agpair to delegate coding work to supported executors (currently Antigravity, Codex, and Gemini), check doctor/status/watch, and drive retry flows.

Real-time tmux dashboard to monitor, manage, and orchestrate AI coding agents — Claude Code, Codex, and more

codex-orchestrator

DEFAULT PIPELINE for all tasks requiring execution. You (Claude) are the strategic orchestrator. Codex agents are your implementation army - hyper-focused coding specialists. Trigger on ANY task involving code, file modifications, codebase research, multi-step work, or implementation. This is NOT optional - Codex agents are the default for all execution work. Only skip if the user explicitly asks you to do something yourself.

agenttrace-session-audit

Audit local AI coding-agent sessions with agenttrace. Use when the user asks to inspect Claude Code, Codex CLI, Gemini CLI, Qwen Code, Aider, Cursor, OpenCode, Oh My Pi, Kimi, Copilot-style, or generic JSON/JSONL sessions for cost, tokens, tool failures, latency, anomalies, health, diffs, or CI gates.

🕹️ Autonomous Agent Patterns

> Design patterns for building autonomous coding agents, inspired by [Cline](https://github.com/cline/cline) and [OpenAI Codex](https://github.com/openai/codex).

claw-orchestrator

Manage persistent coding sessions across Claude Code, Codex, Gemini, and Cursor engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, or switching models/tools at runtime. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "switch model", "multi-agent", "coding session", "session inbox", "cursor agent".

loro

Comprehensive guide for using Loro across document modeling, synchronization, versioning, rich text editors, app-state mirroring, performance tradeoffs, and wasm bindings. Use when Codex needs to work with `loro-crdt`, `loro`, `loro-prosemirror`, `loro-mirror`, or `crates/loro-wasm` for: (1) Choosing CRDT container types and document structure, (2) Designing sync, persistence, checkout, or history workflows, (3) Integrating rich-text editors and stable selections, (4) Mirroring app state with schemas and React, (5) Reasoning about versions, events, import status, or Inspector output, or (6) Maintaining the WASM binding layer.

genshijin 原始人 🗿| Claude Code / Codex 向けの超圧縮コミュニケーションスキル。caveman の日本語版をベースに、日本語特有の冗長表現に最適化。

capture-usage4claude-screenshots

Automate Usage4Claude interface screenshots with CleanShot X on macOS. Use when Codex needs to capture localized Usage4Claude menu-bar popover screenshots, switch Usage4Claude display/language settings, save files such as detail.claude.en@2x.png, or troubleshoot CleanShot/window-capture automation that depends on macOS Accessibility, osascript, CoreGraphics mouse movement, and the Usage4Claude Debug app.

synapse

Codex-led multi-model workflow (Codex + Claude + Gemini). Use when the user asks to run `synapse <cmd> ...` to generate draft diffs/audits and persist artifacts to `./.synapse/**`.

babysit-pr

Babysit a GitHub pull request after creation by continuously polling CI checks/workflow runs, new review comments, and mergeability state until the PR is ready to merge (or merged/closed). Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and stop only when user help is required (for example CI infrastructure issues, exhausted flaky retries, or ambiguous/blocking situations). Use when the user asks Codex to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.

learned-codex-proxy-tool-calls-parse

Parse ChatGPT Codex backend SSE for tool_calls (content_part.added, output_item.done, function_call_arguments.delta/done) and return OpenAI Chat Completions format. Use when implementing or fixing tool call parsing in a Codex reverse proxy (OpenAI-compatible /v1/chat/completions) that consumes Responses API-style SSE.

Entroly-Daemon: Self -Evolving Daemon. Compress 2M-token repos into a razor-sharp Principal Engineer's context. 95% fewer tokens—built for Cursor, Claude Code, Opus,Codex,GPT & Copilot.

Spec-driven CLI for orchestrating multiple AI coding agents (Claude, Gemini, Codex, Cursor) with research, feature, and feedback workflows

git-memento-workflow

Use git-memento to initialize repository-level AI provider settings, create commits that attach AI session transcripts as git notes, and sync notes to remote. Trigger this skill when users ask to create or troubleshoot memento commits, configure providers (Codex or Claude), verify note attachment, or share notes with team remotes.

spool

Search your local Claude Code and Codex CLI session history

codex-code-reviewer

Systematic code review workflow using zen mcp's codex tool. Use this skill when the user explicitly requests "use codex to check the code", "check if the recently generated code has any issues", or "check the code after each generation". The skill performs iterative review cycles - checking code quality, presenting issues to the user for approval, applying fixes, and re-checking until no issues remain or maximum iterations (5) are reached.

agents-consilium

Query external AI agents (Codex, Gemini, OpenCode, Claude Code headless) in parallel for independent second opinions, code review, bug investigation, and consensus on high-stakes decisions. Agents and models are configurable in config.json. Use for architecture choices, security review, or ambiguous problems where independent perspectives matter. Not for simple questions answerable from docs or the codebase — use web search or repo exploration instead.

Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents.

Inter-agent communication via the msg CLI. Use this when you need to send messages to other agent sessions, read incoming messages, or coordinate with other agents in tmux panes.

Notes

Centralized note store across AI clients: Claude, ChatGPT, Cursor, Codex, Windsurf. Save in one clie

Io.Github.MkXultra/Ai Cli Mcp

MCP server for AI CLI tools (Claude, Codex, and Gemini) with background process management

merge-worktree

워크트리 브랜치를 main으로 squash-merge + conventional commit 자동 생성. codex-swarm 워크트리 자동 인식. '머지해', 'merge worktree', '워크트리 머지', '결과 수집', 'squash merge' 요청에 사용.

juya-news-card-operator

Operate juya-news-card as a local CLI text-to-image card tool. Use when Codex should transform user text into final card content itself and render PNG directly with Playwright plus SSR-ready templates, without starting the Next.js app.

sidecar

Spawn conversations with other LLMs (Gemini, GPT, ChatGPT, Codex, o3, DeepSeek, Qwen, Grok, Mistral, etc.) and fold results back into your context. TRIGGER when: user asks to talk to, chat with, use, call, or spawn another LLM or model; user mentions Gemini, GPT, ChatGPT, Codex, o3, DeepSeek, Claude (as a sidecar target), Qwen, Grok, Mistral, or any non-current model by name; user asks to get a second opinion from another model; user wants parallel exploration with a different model; user says "sidecar", "fork", or "fold". CRITICAL RULES: (1) ALWAYS launch sidecar CLI commands with Bash tool's run_in_background: true. Never run sidecar start/resume/continue in the foreground. (2) The fold summary returns on stdout when the user clicks Fold in the GUI or the headless agent finishes. Use TaskOutput to read it when the background task completes. (3) Use --prompt for the start command (NOT --briefing). --briefing is only for subagent spawn. (4) NEVER use o3 or o3-pro unless the user explicitly asks for it by name. These models are extremely expensive ($10-60+ per request). If the user asks for o3, warn them about the cost before proceeding. Default to gemini for most tasks. (5) When the user asks to query MULTIPLE LLMs simultaneously (e.g., "ask Gemini AND ChatGPT", "compare Gemini vs GPT"), ALWAYS use --no-ui (headless) for all of them unless the user explicitly requests interactive. Opening multiple Electron windows at once is disruptive. Launch them all in parallel with run_in_background: true.

Claude Code × Codex Collaboration Framework

Claude Code is the architect and coordinator; Codex is the autonomous implementer.

agentic-rules-writer

Interactive tool to generate tailored rules and instruction files for any AI coding agent. Use when the user asks to set up agent rules, configure Claude Code instructions, create Cursor rules, write Windsurf rules, generate Copilot instructions, or establish consistent AI coding standards for a team. Supports 13+ agents (Claude Code, Cursor, Windsurf, Copilot, Gemini, Codex, Cline, OpenCode, Continue, Trae, Roo Code, Amp) with global, team-shared, and dev-specific scopes. Defers to the `using-virtuoso` meta-skill for ecosystem discovery (skills, agents, recommendations) and runs an interactive questionnaire for workflow preferences.

collab

Gemini and Codex collaboratively brainstorm solutions, building on each other's ideas across rounds. Agent synthesizes the best ideas into a plan.

ava

Codex-native operational orchestration for protoLabs Studio. Use when the user wants autonomous triage, backlog supervision, board operations, agent coordination, or multi-step operational decision-making.

agentic-legibility

Score a repository's agentic legibility from repo-visible evidence only. Use when Codex needs to audit how easy a codebase is for coding agents to discover, bootstrap, validate, and navigate, especially for harness-engineering reviews, developer-experience audits, repo cleanup, or before/after comparisons after improving docs, tooling, or architectural constraints.

sourcesage-cli

Generate AI-friendly repository documentation with the SourceSage CLI. Use when Codex needs to run `sage` or `sourcesage` to create `.SourceSageAssets/Repository_summary.md`, analyze the current repository or another local repository, switch the output language between English and Japanese, use `--lite` to keep the summary small, change the output directory, or optionally create a deprecated tag-diff release report with `--diff`.

collaborating-with-codex

Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSION_ID.

hyperfocus

ADHD-friendly output formatting for Codex. Restructures responses with evidence-based cognitive accessibility: chunking, visual hierarchy, front-loaded key points, and progressive disclosure. Three modes: clean, flow (default), zen. Use when user says "hyperfocus", "focus mode", "adhd mode", "adhd friendly", or invokes /hyperfocus.

ai-pair

AI Pair Collaboration Skill. Coordinate multiple AI models to work together: one creates (Author/Developer), two others review (Codex + Gemini). Works for code, articles, video scripts, and any creative task. Trigger: /ai-pair, ai pair, dev-team, content-team, team-stop

Io.Github.X51xxx/Codex Mcp Tool

MCP server bridging AI assistants to OpenAI Codex CLI for code analysis and review

GNO Agent Skill System

Create a skill distribution system that enables AI agents (Claude Code, Codex) to use GNO perfectly.

codex-upcoming-features

Fetch and summarize upcoming unreleased Codex features using a durable local clone synced from GitHub, with source-file mining as primary evidence. Use when asked for latest upcoming/openai-codex features, what is coming next but not in the latest stable release, or a live release-gap summary with links and as-of timestamp.

Default agent backend

[agent] default = "claude" # or "codex"

Io.Github.Dr12hes/Engrm

Shared memory across devices, sessions, and agents for OpenClaw, Claude Code, and Codex.

ai-coding-workflow

Use when the user wants to work with Codex, Claude Code, or other AI coding agents more efficiently, especially to avoid long-session slowdown, split large tasks into bounded steps, define scope and non-goals, separate diagnosis from implementation, compress context between sessions, or turn a vague coding request into a tighter execution prompt. Also use when the user asks for an AI coding prompt/template, asks why AI coding gets slower later in a task, or wants a repeatable collaboration workflow for medium-to-large codebases.

Codex Assistant

通过 OpenAI Codex CLI 执行代码任务。使用前请确保： 1. Codex 已安装并配置 (`codex` 命令可用) 2. 工作目录在信任列表中

CAR Ticket Skill

Use this with ChatGPT, Claude, Codex, or any other assistant when you want help converting a plan into CAR-compatible tickets.

harness-engineering-orchestrator

Repo-backed PRD-to-code orchestration for Claude and Codex. Use when the user wants a new app or existing repository run through discovery, architecture, milestones, execution, and validation instead of ad-hoc prompt-only delivery. Supports greenfield and existing codebases across web, iOS, Android, CLI, agent, API, and desktop projects, with first-class workspace-first support for Bun, npm, and pnpm repositories plus reference templates for additional ecosystems.

markstream-angular

Integrate markstream-angular into an Angular app. Use when Codex needs standalone component imports, signal-based examples, CSS wiring, custom HTML tags or customComponents setup, or optional peer integration in an Angular repository.

codex-opencode-pi

Codex CLI, OpenCode CLI, and Pi CLI runner protocols for Untether. Covers JSONL event types, event translation, resume mechanisms, and key differences between engines. All three are non-interactive (no control channel).

hooks-management

Manage hooks and automation for coding agents (Claude Code, Codex CLI). Use when users want to add, list, remove, update, or validate hooks. Triggers on requests like "add a hook", "create a hook that...", "list my hooks", "remove the hook", "validate hooks", or any mention of automating agent behavior with shell commands.

cp

Local verify-commit-push wrapper for Codex. Use only when the user explicitly says `/cp` or clearly asks to finish the current work by running the relevant local checks, staging intended files explicitly, committing on the current branch, and pushing. This workflow may commit directly to `main` or `master` when that is the repo's chosen operating model.

Tap into Claude Code API requests via a local reverse proxy. Inspect system prompts, messages, tools, and token usage.

Run real E2E tests against Codex CLI (OpenAI Responses API) through claude-tap proxy