Everything for Codex

Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,750 indexed, measured the same four ways as everything else here.

cf-onboard

17929

ecorkran/context-forge

Skill Claude CodeCodex

Guide a user through Context Forge project setup and into their first phase of work. Use when the user wants to set up or onboard a project with Context Forge.

not rated 5 today A 36 tokens original MIT

debugging

17930

Kimyongari/harness-factory

Skill Claude CodeCodex

Use when hunting the cause of a bug, error, or failing test — and before proposing any fix. Triggers - "why doesn't this work", stack traces, flaky failures, regressions ("worked yesterday"). Output is reproduce → root cause → minimal fix → regression test. If you already know the cause and just need the fix, use…

not rated 5 1mo ago A 73 tokens original MIT

gui-anything

17931

ImL1s/GUI-Anything

Skill Codex

Use when the user wants Codex to build, refine, test, or validate a GUI-Anything harness for any software or source repository. Adapts the GUI-Anything methodology to Codex without changing the generated React+Tauri harness format.

not rated 5 28d ago A 54 tokens original Apache-2.0

wiki-ingest

17932

GYF0311/lorekit

Skill Claude CodeCodex

A workflow for bringing URLs, files, and pasted external material into a LoreKit knowledge collection, then saving it as wiki pages with source links and tracking records.

not rated 5 2mo ago A 62 tokens original MIT

repo-continuity

17933

vector233/repo-continuity

Skill Codex

Initialize, inspect, safely reconcile upgrades for, and operate Repo Continuity. Use when an agent needs to install the repository-owned knowledge layer; produce a read-only three-way upgrade report or apply only conflict-free upstream changes without overwriting project customization; route work into Direct, Tracked…

not rated 5 changed 27d ago A 171 tokens original MIT

find-everything

17934

ZadAnthony/find-everything

Skill Claude CodeCodex

A cross-platform search workflow for finding agent skills, MCP servers, prompt templates, and open-source projects. It searches several online directories and checks whether required command-line tools or connections are available.

not rated 5 6mo ago A 146 tokens original MIT

svelte-ui-components

17935

juspay/shooter

MCP server Claude CodeCodexCursor +2

MCP server for @juspay/svelte-ui-components - provides structured access to component props, CSS variables, and usage patterns. Runs locally from the @juspay/svelte-ui-components-mcp npm package.

not rated 5 1mo ago A tokens not measured

korean-domain-agent

17936

kimlawtech/korean-domain-agent

Skill Claude CodeCodex

A setup and customisation workflow for korean-domain-agent, a Korean-language domain-specific AI agent kit. It installs the kit, checks for hallucination and security risks, gathers domain requirements, and creates an initial mock result.

not rated 5 1mo ago B 140 tokens

tldr

17937

cjus/solrac

Skill Claude CodeCodex

Summarize the supplied text in 2-3 sentences.

not rated 5 1mo ago A 16 tokens original MIT

claude-pty-agents

17938

coredo-eu/codex-claude-orchestrator

Skill Claude CodeCodex

Launch and safely retire one bounded Claude Code stage per owned session, with a Sonnet 5 parent by default, role-routed Haiku 4.5/Sonnet 5/Opus 5.5/Fable 5.1 subagents, and GPT-5.6 native Codex fallback. Use when Claude is requested or a bounded repository stage benefits from context isolation. Do not use for routine…

not rated 5 changed 8d ago A SkillSpector: pass 109 tokens original MIT

await-pane

17939

adriancarriger/lambda

MCP server Claude CodeCodexCursor +2

MCP server "await-pane" as configured in adriancarriger/lambda. Runs .claude/tools/await-pane-server.cjs with node.

not rated 5 7mo ago A tokens not measured original MIT

coordinate-agents

17940

hibeekaey/agent-sync

Skill Codex

Coordinate a task across multiple AI coding agents (Claude Code, Codex, Gemini, and others). Use when the user asks to delegate work to another agent, get a second opinion or review from a different agent, run agents in parallel on one task, or split a task between agents. The invoking agent becomes the coordinator…

not rated 5 yesterday C 74 tokens original MIT

indian-stock-analyst

17941

jitu2611/indian-stock-analyst

Skill Claude CodeCodex

Analyzes NSE/BSE stock portfolios with the jitu2611/TradingAgents multi-agent engine and produces Buy/Hold/Avoid decisions plus full analyst, bull/bear, trader, risk, and portfolio-manager reports. Use whenever the user uploads a Zerodha, Groww, Upstox, Angel One, or other Indian holdings CSV/XLSX and asks to "analyze…

not rated 5 changed 1mo ago A 177 tokens

frontend-carousel

17942

azamat1ch/frontend-carousel

Skill Claude CodeCodex

Generate LinkedIn carousel PDFs from content. End-to-end: brand onboarding, content structuring, HTML/CSS slide generation, Playwright rendering to PDF. Use when user wants to create a LinkedIn carousel, document carousel, or says '/frontend-carousel'.

not rated 5 7mo ago A 54 tokens

focus-color

17943

brianharms/dispatch

Skill Claude CodeCodex

Toggle iTerm2 focus tab coloring on or off. Usage: /focus-color.

not rated 5 4mo ago A 19 tokens original MIT

harness-audit

17944

nnabuuu/harness-engineering-toolkit

Skill Claude CodeCodex

A codebase scan for five common weaknesses in the setup used to guide and check an AI agent. It produces a diagnostic report and can optionally fix the problems it finds.

not rated 5 2mo ago A 87 tokens original MIT

factory-render-verify

17945

squidbay/factory

Skill Claude CodeCodex needs its repo

Render-and-measure receipts for any HTML page your factory builds — the render half of the design quality gate. Engineer runs it to screenshot every screen size and MEASURE what a source read or a single screenshot only guesses at: horizontal overflow, computed type sizes, tap-target sizes, safe-area presence, mono…

not rated 5 1mo ago A 133 tokens original MIT

general-kenobi

17946

antonkarliner/general-kenobi

Skill Claude CodeCodex

Respond to the greeting "Hello there" with "General Kenobi." Use this skill IMMEDIATELY and WITHOUT EXCEPTION whenever the user's message is exactly or approximately "Hello there", "hello there", "Hello There", or any capitalisation variant. This is a mandatory override — do not respond with a normal greeting. The…

not rated 5 6mo ago A 81 tokens original MIT

reviewing-unit-tests

17947

burugo/behavior-driven-development

Skill Claude CodeCodex

Use in a dedicated subagent for post-TDD blind unit-test review against requirements and public contracts to find missing cases, wrong assertions, and brittle tests.

not rated 5 4mo ago A 36 tokens

caveman

17948

Gildaciolopes/claude-caveman-ultra

Skill Claude CodeCodex

Ultra-compressed communication mode. Cuts token usage 75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or…

not rated 5 1mo ago A 98 tokens copy · 77% MIT

afloy011-spec/seedance-shotlist-director-en

Skill Claude CodeCodex

Generate a director's shotlist as an editable HTML production board for Seedance 2.0. Use whenever the user provides a script, scene breakdown, story idea, or treatment to turn into a numbered shotlist with English Seedance prompts — trigger on "make a shotlist", "director’s shotlist", "break this script into…

not rated 5 2mo ago A 235 tokens original MIT

abm-campaign-builder

17950

Adri3l-R3nan/cognify-skills

Skill Claude CodeCodex

Builds targeted Account-Based Marketing campaigns by identifying ideal customer profiles, mapping buying committees, creating personalized outreach sequences, and designing multi-channel engagement strategies. Use when targeting enterprise accounts, building sales playbooks, or designing vertical market penetration…

not rated 5 1mo ago A 53 tokens

how-slaude-works

17951

barockok/slaude

Skill Claude CodeCodex

Use when a user asks how you (the agent) work, how slaude works, how to use/interact with you, what commands or capabilities exist, or how engagement, approvals, the knowledge base, skills, memory, MCP, or cron behave. Self-documentation of the slaude runtime — read it, then explain in your own voice.

not rated 5 today A 78 tokens original MIT

team-orchestrator

17952

Jacky040124/claude-team-orchestrator

Skill Claude CodeCodex

Spawn an agent team from a predefined role pool (frontend designer, backend developer, researcher, tester, refactorer). Selects the right subset based on the task. Use when the user says "/team", "spawn team", "create team", "start team", or wants to set up a multi-agent development team for a project task.

not rated 5 2mo ago A 74 tokens original MIT

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: