codex

Switchable output styles for Codex and Claude Code, enforced by hooks and switched from the chat with ::

Run Codex from Claude Code for adversarial review, feedback triage, in-scope fixes, and task delegation.

Route code discovery across exact search, semantic search, LSP navigation, and call-graph analysis.

The definition loop: decide WHAT to build. Competitive industry research -> product spec (SPEC.md) -> plan with the…

Investigate reproducible Codex instruction failures and compare proposed repository rules with independent checks.

The video step for Claude/Codex UGC workflows: skills and a hosted MCP server for captioned vertical videos, narrated…

Compresses large Codex tool outputs with sift and reports saved tokens.

24 YouTube skills and 11 local analysis tools for ChatGPT and Codex: ideas, scripts, packaging, Shorts, retention,…

Healthcare administration skills, six deep workflows and a custom workflow builder.

Resume work from a recent Claude Code, Codex, or Cursor session. Shared reader runtime plus per-tool aliases.

A Codex engineering toolkit with orchestration, task ledgers, solve loops, policy-gated effects, async GitHub Stack…

Pool Claude Code and Codex logins, switch on pace pressure, and expose safe ops tools to agent clients.

Safely configure and verify a Terminalbox SSH host for the official Codex app.

Skills that audit and fix agent plugins so one DRY repository works in GitHub Copilot CLI, VS Code, Claude Code and…

A dual-path memory system for proactive agents: a typed knowledge graph with evidence, contradictions and supersession,…

Learning-first development in Codex and T3 Code, adapted from VibeWise.

Prepare bounded mission prompts and coordinate scoped work with Astra, Sol, Luna, and optional GPT-6 Pro Web.

Skills for forward-deployed engineering (FDE): discovery, AI solution design, enterprise integration, agent evaluation,…

Discover grouped Agent Sessions peers and orchestrate durable Codex, Claude, Grok, and Qwen lanes from Qwen Code.

Ask about your Codex usage in plain words: spend, usage limits, why a session was expensive, and whether Codex or…

VibeWise learning workflow ported to Codex: learner-owned design, guided implementation, and project continuity.

VoltPeer: battery data plotting, Figure assembly, original mechanism diagrams, scientific writing, planning and…

Independently falsify or approve implementation plans before execution with ACCEPT, MODIFY, or REJECT verdicts per task…

Durable channels, threads, search, subscriptions, and idempotent agent collaboration.

Codex-only SessionStart hook that injects ancestor AGENTS.md files and repo-configured instruction files.

Project-neutral, multi-agent workflow core: a fixed backbone of steps that drives an issue from backlog to done,…

Automatically prefix Codex task titles with a model-specific colour marker.

Run reproducible local OpenEconometrics analyses directly from Codex.

Codex-native skills and specialist agents for disciplined software delivery.

Run long repository roadmaps through fresh sequential Codex workers without a model-backed coordinator.

Connect ChatGPT to your own Codex Desktop projects and conversations.

Minimal runtime-neutral engineering policy with proactive execution optimization and objective-level review DAG…

Reusable skills for agent-asset audits and upgrades, project setup, and reliable agent behavior.

Turn local web projects or hosted web URLs into macOS Dock apps on a local agent host.

Shared company agent skills for Codex and Claude Code.

Local WhatsApp MCP tools and a graphical UI candidate for Codex on macOS: scoped reads and confirmed replies. Native UI…

Coordinate local coding agents to turn GitHub issues into tested pull requests, with dependency-aware scheduling,…

Closelly MCP App: skills y connector portable para ChatGPT/Codex, Claude Code y GitHub Copilot CLI.

UX and visual judgment for agent-built UI: a build brief before you build, a scored review after.

Agent guidance for the deterministic git-slop repository token-defragmenter.

Agents often drift and waste time on the wrong work. Correction Guy watches from the sidelines and steers them back on…

Agent skills for research, App Store readiness, Codex model routing, repository and Swift review, PR feedback triage,…

A zero-friction Codex usage governor with task-aware routing, soft budgets, focused context, local audits, and layered…

A toolkit for working with AI agent harnesses: detect which one is running, query its managed-policy locations, plugin…

Darkroom Engineering coding standards and reusable engineering workflows for Codex.

Harden rough coding tasks into scoped, testable instructions before execution.

Native, persistent user-attention alerts for local ChatGPT desktop and Codex workflows.

Automatically chooses and coordinates GPT models for project tasks, with the right effort and safeguards for each job.

Event-driven After Action Review with scoped improvements, evidence, feedback, journal and rollback.

Modernize legacy systems with evidence-backed discovery, architecture maps, business rules, behavior tests, and…

Harness-agnostic scheduled tasks for AI coding agents: Codex-automations-style recurring runs with any harness and any…

Portable developer-workflow and design skills: canva-studio, codex-review-loop, fable-mode, figma-studio,…

Connect Codex to HarnessMesh collaboration, review, knowledge and MeshCommit tools.

Canonical agents, skills, MCP integrations, and Expertise Pack authoring for Plugin Factory.

Host guidance for bounded Agent delegation and evidence-based acceptance, with tools for explicitly supported executor…

Portable, reproducible agent workflows, skills, and MCP setup for modern coding agents. wagent (main) + wagent-hacker…

Memory abstraction layer for Claude Code, Codex CLI and Pi: deterministic capture hooks plus model-driven skills over a…

Open the shared Better Codex task board through the existing local Runtime.

Research you can inspect: source-linked dossiers using native Codex or Claude, with retrieval gates and explicit…

開発セッションの終わりに、関連Issue・未着手タスク・Issue作成案・追加テストや軽微な整理を確認する。

Medical research planning, literature review, data analysis, manuscript writing, peer review, revision, and submission.

Isolated project memory, planning, and task context for Codex and Claude Code

Scientific figures with upstream PaperVizAgent, separate roles, configurable model providers and Codex subscription…

Design, refine and rebuild scientific figures in one Codex conversation. Editable SVG, PDF and PPTX.

Evidence-backed, diff-scoped CodeRabbit-style review handoffs for Codex.

한국어 AI 기능 125개의 안내 목록과 선택 설치·보관·복원 도우미 2개.

Personal agent skills for launching, inspecting, coordinating, and reviewing multi-agent development work.

Agent capabilities for independently selectable repository standards, with optional adoption assets.

pstack の設計・実装・レビューを Codex・Devin などの Agent Skills 対応環境で使う共通ラッパー

Let Codex delegate development tasks to your local ZCode runtime and review their progress and results.

Open-source engineering skills for repository work, Python, host-native MARGOS orchestration, ReThinking audits, and…

Unofficial Codemagic build operations and iOS/Android signing guidance for coding agents.

Local recovery anchors for Claude Code and Codex sessions, plus evidence-gated evaluation prompts

Offline installer for the DeepSeek V4 Flash custom subagent for Codex

Check Codex reset credits and local rate-limit reset windows without exposing authentication secrets.

Managed Codex and Claude autonomy, local scheduling, CI isolation, and guarded maintenance for Hraness repository work.

Build, extend, port, and test coding-agent plugins: skills, commands, hooks, MCP wiring, subagent orchestration, and…

Self-evolving second brain with 36 AI agent skills, 10 agents, and people CRM. Closed-loop harness: a V-model…

Secure HydraDB automation for Codex with workspace sync, prompt recall, and conversation capture.

AL and Business Central development skills and MCP tools for Codex and GitHub Copilot.

Context and workload governance for Codex Desktop and ChatGPT Work using Orquestrador Maestro.

CoDesign gives AI agents like Claude Code, Codex and PI a real design engine for genuine, editable designs, not flat…

A quiet, risk-scaled engineering method layer for Codex.

Portable Codex delegation wrapper. It validates one codex.delegation.v1 envelope, supervises one codex exec, and writes…

impstack, imperfect operator.

사용자 의도를 먼저 판별하고, 제품·기능·연구 실험·버그에 맞는 서로 다른 승인 흐름을 적용하는 한국어 워크플로우입니다.

Local test plugin for validating Codex-compatible hook behavior in Owls.

Create, position, format, and update native think-cell charts from user-supplied donors with native verification.

Inspect, measure, preview, and verify live web and Electron interfaces with Mesurer Solid.

Analyze any repository and generate AI-ready configuration — AGENTS.md, copilot-instructions.md, skills, CI workflows,…

Read local Codex conversation history by deeplink or thread ID without modifying Codex state.

Composable agent-workflow skills for planning, communication, knowledge work, and media analysis.

Luna-first orchestration with a local Rust control plane, durable runs, and an MCP Apps workbench.

Portable AI agent harness — curated review/build/test agents, secret-hardening + worktree + plan-gate hooks, and…

A full Google Cloud delivery team for your coding agent: vendor-objective solution designer, GCP architect,…

Turns your coding agent into an architecture diagrammer: describe a system in plain language and it writes, checks and…

Route Codex Office edits to a connected document, desktop app, cloud document, or local file.

Portable Meta-Architect skills for architecture, evidence, review, and bounded autonomous coding workflows.

281 Agent Skills for researchers: scientific and research paper writing, journal formats, literature review, citations,…

Search, screen, draft and apply to jobs on 51job / 前程无忧 using user-defined career preferences and verified resume…

Generate a private, evidence-labeled report of capability signals in local Codex task history or a supplied task export.

Obsidian Vault knowledge tools, native setup, and note handoff to Codex.

Make the code you choose easier to read and maintain while preserving its behavior.

Human-first skills for writing cleanup and evidence-based work reports. Built by Long.

Lightweight, evidence-first software delivery for Codex. 中文优先的 AI 软件交付工作流。

External State-of-Thought controller with evidence routing, explicit state checkpoints, uncertainty tracking, and…

Delegate bounded work to an explicitly selected local model through an existing Forjal connection.

Self-contained Codex dispatch and backend-turn bridge with exact dispatch model selection, scoped project reads,…

Delegate independent Codex work to parallel OpenCode workers in isolated Git worktrees.

Publish games with FanZero and connect with content creators through launch visibility and revenue-share pacts.

Self-coordinating Codex engineering team for interfaces that expose agent conclusions, supporting evidence, provenance,…

Bounded GrepMesh search for unknown locations and cross-host scopes, with rg preferred for known local paths.

Collect required NA Engineering skill inputs in a Codex form.

AGT governance hooks for the OpenAI Codex CLI

Official-source Indian legal research, judgment briefs, drafting (including Bombay High Court s.528 BNSS quashing…

Repository-specific workflow for the Codex Rust workspace, CLI, SDKs, generated configuration schema, and project…

Optional, explicitly invoked delegation to Codex or its CLI

Trust over speed for coding agents — the router (AGENTS.md + WORKFLOW.md), 11 discipline skills, and the mechanical…

Operate the connected server through persistent shell commands and original file retrieval.

Discover and load Agent Skills from configured local directories, plugin marketplaces and Git sources through MCP tools…

Orquestación de modelos por roles: delegación selectiva, continuidad, verificación y registro de uso real.

Team delegation, focused delivery and explicit Codex project setup with an optional model guard.

Método comum de equipe multiagente: ativação explícita, níveis, rodada em fatias com prova, passagem entre ferramentas…

High-integrity multi-agent orchestration bridge connecting orchestrators with local CLI coding agents (OpenAI Codex,…

Evidence-first application-security Agent Skill for repositories and environments you are authorized to test. Maps the…

Build source skills and plugins into Claude, Codex, and Cursor outputs.

Portable skills for repository setup, private remote development, code-native design exploration, design-system…

Plan project-specific agent skills and retrieve repository context with RODS.

Codex engineering with Astra XHIGH planning and advice, Luna MAX Fast workers, Sol MAX design, independent Sol review,…

Visual prompting, reference analysis, craft construction, digital form, spatial concepts, and result diagnosis with 23…

Reference for authoring, running, inspecting, and resuming quiet-choir workflows.

Risk-adaptive software engineering operating skill for reliable AI-assisted vibe coding, architecture, staged…

Use Claude Code from Codex: delegate coding tasks with independently verified results, get Claude code reviews, pair…

Intent to implementation: ready, then go.

Evidence-bound architecture review and target design across compatible agent clients, with a local CPython 3.11–3.14…

Create, audit, and convert Agent Plugins 1.0.0 packages, then guide reviewed marketplace release. Agent Plugins 1.1.0…

An opinionated workflow for shipping production-ready changes with coding agents.

Initialize standards-based agent configuration across agent harnesses

Saint Tibo language-server matrix: one pinned LSP per language, wired to the stack pin.

Legalcode for Codex with public Legalcode MCP access and 10 core legal research and drafting skills.

CSV preflight validation and batch CSV quality checks that fail fast before pipeline runs.

Portable ESRA skills with a guarded autonomous controller for OpenClaw and Hermes Agent.

Persistent Pi coding subagents for Codex: bounded inspection, steering, interruption and recovery through MCP and CLI.

AICQ End-to-end Encrypted Chat — exposes AICQ friend management, chat, file transfer, and group messaging to OpenAI…

Let Codex delegate development tasks to your local ZCode runtime and review their progress and results.

Coalesce, schedule, and stream cargo so concurrent agent sessions share compiles instead of fighting locks.

Compress language, not information. Preserve reasoning, risks and useful insights with less reading.

A collection of agent skills: brand asset audits, comprehensive docs, READMEs, deep bug hunts, repo CI setup, and…

The open-source governance layer for AI agents. Spawn parallel agents in per-task git worktrees, verify their work, and…

Search skilld.dev, a curated registry of agent skills, read who wrote each skill, and get the command that runs it.

A local desk note that helps Codex resume the right job after context compaction.

MGR 主控空间的可移植 Agent Skills。

Build public social-data pipelines, competitor trackers, creator research, comment analysis, transcripts, summaries,…

Local-first RAG memory for AI agents: hybrid BM25/semantic search, GraphRAG, and an MCP server with OAuth 2.1. Index…

Reviewed developer skills and local SSH management: a reusable TypeScript library, authenticated local API, terminal…

Substrate long-term memory for ChatGPT Work, Codex in the ChatGPT desktop app, and Codex CLI.

Evidence-driven engineering workflows for Codex and ChatGPT.

Cross-agent catalog of reusable Agent Skills with provenance-aware lifecycle management.

pstack-mod is takahudi's personal pstack port for Codex and Claude Code. Original pstack by Lauren Tan; host adaptation…

Show the shared ChatGPT and Codex quota in the macOS menu bar or Windows system tray.

Maintained public skills for Codex, starting with contextual image enhancement and verified 8K export.

Techsio UI Kit AI — skills for developing and consuming the @techsio/ui-kit design system (libs/ui): component usage…

Run Claude Code as a department: roles, a shared protocol, and the skills that drive them.

A deliberately small collection of personal Agent Skills.

Connect AI Employee Builder across supported hosts and optionally keep a private, local cross-runtime improvement…

Connect Codex to a Google Colab browser session through Google's official Colab MCP server.

OMP extension that auto-resumes a session after every Codex account is exhausted

Automatic model and reasoning-effort routing for eligible new local Codex subagents, and for tasks started from the…

Personal agent skills for Codex and Claude Code.

Software documentation specialist with arc42 DESIGN_DOC.md, architecture docs, Mermaid-first diagrams, and PlantUML…

OpenAI developer and ChatGPT plugin workflows paired with the official read-only documentation MCP.

Conservative weekly quota planning, observed horizon forecasts and quality-aware team advice for Codex.

Connect Codex (and other clients) to a local role-model runtime via the codex-role-model adapter CLI.

Codex operating guidance, browser and Vercel troubleshooting, external app integrations, CMS studio workflows,…

Repository-native project context workflows and a version-pinned pm MCP server for Codex.

Privacy-first Agent Skill and CLI for evidence-based job discovery, application completion, and outcome tracking.…

Connect ChatGPT and Codex to your Vaiz workspace: tasks, boards, documents, Space Memory, and GitHub links via remote…

Interaction routing for agents, with a bridge that exposes macOS Codex Computer Use as MCP tools.

Claude bridge, optional house rules, and general code review skills for Codex.

Denglema Agent usage adapter: Codex local snapshots plus a harness-agnostic Skill and schema v2 upload contract.

Reusable agent skills and a public workbench for harness setup.

Shows real Codex lifecycle status on TonyTouchBar.

Reduce context bloat deterministically without requiring an OpenAI API key.

Richtet CLIProxyAPI und eine claudex-Funktion für Claude Code mit GPT auf macOS ein — installieren, aktualisieren,…

Open once, then let Codex and Claude collaborate automatically in the native chat.

Package the Codebase Video Explainer Agent Skill for Codex and ChatGPT. Analyze repositories, build evidence-backed…

A personal library of reusable skills for Codex and other agents that consume SKILL.md-based skills.

The remotion-director 甲乙环 pipeline for Codex: one public entry skill, native role lifecycle guidance, and…

Hosted CentricMem librarian: organise and retrieve Markdown memory via host MCP.

Trade-Bot engineering workflows for implementation, root-cause debugging, safe OpenAI SDK integration, parallel agent…

Agent-driven client POCs: shared skills, MCP tools, and scripts for live demo environments.

The build and verification loops: take one Ready issue at a time from the board to a merged PR, and prove each change…

Keep Claude Code, Codex, and other coding-agent terminals available after disconnects, using the least infrastructure…

Run and resume sustained project work with a durable task ledger, bounded attempts, evidence checks, and morning…

Generic Sessionbus guidance for managed Qwen launches and lanes. Ordinary Qwen discovers the skill without starting a…

Orchestrate complex multi-task work by separating advisor reasoning, delegated execution, and independent verification…

Source-only isolated Better Codex development Mockup.

ast-grep の構造検索・lint・安全な rewrite・ルールテストをプロジェクトで使う。一般的な linter で表現しにくい構文パターンに適用する。

OPL agent design, review, takeover, and evolution.

Build an agent tool once; ship it as Agent Skills, MCP servers, Agent Plugins / Claude / Codex / Cursor bundles,…