Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 275,044 indexed, measured the same four ways as everything else here.
lubochka/xiigen-general-skills
Skill Claude CodeCodex
Ensure project-specific rules are read before meaningful action. Use at task startup, before editing files, running commands, or adapting skills.
Skill Claude CodeCodex
A local tool for viewing and organising conversation history from the OpenAI Codex command-line tool and desktop app. It works with saved sessions, archived sessions, and the history index on the computer.
Skill Codex
Coordinate substantive software work with a configurable Astra or Sol root and verified advanced and Luna executors. Covers durable assignments, isolated writer worktrees, candidate review, validated delivery, and human-confirmed Ultra takeovers. Invoke it before planning, delegating, coordinating, or validating…
Skill Claude CodeCodex
Encrypted peer-to-peer text messaging between agent sessions (Claude Code or other CLI agent harnesses on the same machine) running in separate terminals. Use this whenever the user wants to talk to another agent, message another Claude, coordinate with another agent, open/create/join/enter a room, send text to a…
Skill Claude CodeCodex
Use when you are spawned as the PM of a simply harness project and your brief references a .simply/LEDGER.md work ledger or this skill. Grants fleet authority, routing doctrine, safe worker lifecycle, and the signal protocol back to the auditor.
Skill Claude CodeCodex
Plan a repository change first, then implement only after approval.
Skill Claude CodeCodex
Anti-sycophancy protocol (明辨). Use whenever the user contradicts, corrects, or pushes back on one of your conclusions; when you notice you are about to reverse a position mainly because the user insisted; or when a disagreement has run two or more rounds without new evidence. Classifies the dispute (fact / tradeoff /…
Skill Claude CodeCodex
Use when the clodex router hands off a run at stage open or plan, when a run the router resumed shows no recorded plan or a plan with no standing approval, or when plan-review findings on such a run still need dispositions before work can start.
yingwang/codex-telegram-bridge
Skill Codex
Activate, monitor, stop, or use the private Telegram bridge for the current Codex CLI session. Use when the user asks to enable Telegram for Codex, receive Telegram text, images, Markdown, PDFs, voice notes, or audio in the current session, send Telegram messages/files/optional TTS audio from Codex, check bridge…
Skill Claude CodeCodex
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
stevennana/mina-ralph-loop-bootstrap-nextjs
Skill Codex
Bootstrap or extend a new or early-stage Next.js App Router + TypeScript repository around a Ralph-style task-promotion loop. Use when Codex needs to ask the founder product and architecture questions, generate or update the repo-local markdown knowledge base, create the initial scaffold or the next feature wave…
Skill Codex
Reduce Codex context and token use while preserving evidence and correctness. Use for long coding, research, debugging, repository exploration, noisy logs, large command or MCP outputs, repeated file reads, cost-sensitive work, or when the user asks for concise, cheap, low-token, or context-efficient execution. Also…
Skill Codex
Repair and synchronize Codex CLI model catalogs for OpenAI-compatible third-party providers. Use when /model shows stale, missing, duplicated, or nested "All models" entries; reasoning efforts or context windows disagree with upstream; a provider exposes /models but Codex does not refresh it; or modelcatalogjson and…
gabrielrovesti/ai-agent-skills
Skill Claude CodeCodex
Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.
DragonJames2026/wechat-article-format
Skill Claude CodeCodex
A macOS workflow for formatting the body of a WeChat public-account article using inline styles while keeping its wording unchanged. WeChat public accounts are channels for publishing articles in the WeChat app.
Skill Claude CodeCodex
name: ship description: Plan and ship a feature. Explores codebase, writes specs/.md, then runs ship CLI for autonomous execution. Use when asked to build something substantial. user-invocable: true.
Skill Codex
A workflow layer for running long, mostly unattended Codex development sessions with saved state, task queues, isolated workspaces, retries, and verification records.
yelinwang668-debug/ai-code-factory
Skill Codex
A workflow for splitting a code change into independent tasks and assigning them to multiple command-line AI coding agents. Each agent works in its own Git worktree, an isolated copy of the repository.
MCP server Claude CodeCodexCursor +2
MCP server "hahow-watcher" as configured in htlin222/hahow-mentor-agent. Launched with bun ./channels/hahow-watcher/hahow-watcher.ts. Needs 2 environment variables to run.
lastmindforever36/agent-grounded-infrastructure
Skill Claude CodeCodex
Evidence-grounded autonomous engineering router. Use when the user invokes $agi or asks for broad, ambiguous, long-running, production-grade, benchmark-driven, or high-leverage software work that should choose its own tools, skills, agents, validation, and checkpoints from live repo evidence.
Axelendometrial4386/russian-text-quality
Skill Claude CodeCodex
Use when reviewing or writing code that contains Russian-language UI strings, i18n locale files (ru.json, ru.yml, ru.po), Russian comments, or transliterated identifiers (polzovatel, tovar, kolichestvo). Triggers on mixed English-code + Russian-content projects. Does not cover typography, spelling, or ё/е.
Skill Claude CodeCodex
Generate CLAUDE.md / AGENTS.md + TODO.md for the current project, following the minimal HumanLayer pattern and Karpathy 4 rules. Bakes a Session Maintenance Protocol into the root file so future agents auto-update rules and TODO when they load the file. Use when user mentions CLAUDE.md, AGENTS.md, project rules, init…
Skill Claude CodeCodex
Use when the user wants to review a pull request, understand what a PR changes, assess risk of merging, or check for missing test coverage. Examples: "Review this PR", "What does PR #42 change?", "Is this PR safe to merge?".
RaphLorr/claude-skill-image-gen
Skill Claude CodeCodex
Generate an image from a text prompt using OpenAI gpt-image-2 through the local codex CLI — uses the user's ChatGPT plan quota, requires NO OPENAIAPIKEY. Use whenever the user asks to generate, create, draw, render, paint, or make an image, picture, illustration, logo, icon, banner, avatar, or artwork.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: