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. 267,758 indexed, measured the same four ways as everything else here.

payment-skill

7753

TencentCloudBase/awesome-miniprogram-skills

Skill Claude CodeCodex

A WeChat Pay workflow for creating payments, checking or closing orders, handling refunds, and making or checking merchant transfers.

not rated 37 3mo ago A 34 tokens original MIT

binance-mcp

7754

nirholas/Binance-MCP

MCP server Claude CodeCodexCursor +2

MCP server for Binance exchange - spot trading, staking, wallet, NFT, pay, mining, and more. Runs locally from the @nirholas/binance-mcp-server npm package. Needs 2 environment variables to run.

not rated 37 +2 2d ago A tokens not measured

clj-skill-eval

7755

humorless/clj-native-agent

Skill Claude CodeCodex

Evaluate Clojure skills through rigorous real-project testing with and without skills enabled. Use this skill whenever you need to assess whether a Clojure skill (like clj-discover, clj-debug, clj-replace) actually improves development outcomes. Compare behavior differences via context-logs, code quality…

not rated 37 +1 3mo ago A 91 tokens

scientific-writing

7756

Xevos117/mcp-zotero

Skill Claude CodeCodex

Use this skill whenever the user asks to write a scientific article, literature review, research paper, case report, systematic review, or any academic/scholarly document. Triggers include: "write a paper", "write an article", "literature review", "review article", "case report", "research paper", "scientific…

not rated 37 4mo ago A 141 tokens

find-skills

7757

Rifteo/skills

Skill Claude CodeCodex

Helps users discover and install Rifteo agent skills when they ask questions like "is there a skill for X", "how do I write a finding", "find a skill that can...", or want to extend their agent for security and audit work.

not rated 37 +1 changed today A SkillSpector: warn 55 tokens original MIT

tiacommander-mcp

7758

a4webdev/tiacommander-mcp

MCP server Claude CodeCodexCursor +2

MCP server "tiacommander-mcp" as configured in a4webdev/tiacommander-mcp. Launched with https://github.com/a4webdev/tiacommander-mcp/releases/download/v2.26.3m/TiaComma.

not rated 37 +3 10d ago A tokens not measured

manage-skills

7759

umutbozdag/agent-skills-manager

Skill Claude CodeCodex

Discover, list, create, edit, toggle, copy, move, and delete AI agent skills across 11 tools (Cursor, Claude, Agents, Windsurf, Copilot, Codex, Cline, Aider, Continue, Roo Code, Augment).

not rated 37 +2 5mo ago D 57 tokens original MIT

thesis-writing

7760

santifs/thesis-writing-skill

Skill Claude CodeCodex

Use when writing, structuring, drafting, or reviewing a thesis, dissertation, undergraduate thesis/TFG, master's thesis/TFM, or empirical research write-up — scoping the topic, outlining chapters, drafting sections from evidence and data, editing drafts, or planning the work. Covers undergraduate through…

not rated 37 +1 3mo ago A 69 tokens original MIT

record-and-replay

7762

ugarchance/record-and-replay-skill

Skill Claude CodeCodex

Record the user's actions — browser (Playwright event stream + trace) or native desktop (lightweight event/window/screenshot stream) — on macOS, Windows and Linux for up to 30 minutes, then turn the demonstration into a reusable agent skill. Use when the user asks you to watch them perform a task, record a workflow…

not rated 37 +1 1mo ago A 106 tokens original MIT

system-information

7763

symfony/ai-mate

Skill Claude CodeCodex ✓ vendor

Resolve which dependency versions are actually installed, from composer show and composer.lock, when diagnosing version-specific behavior such as a method, argument or class that does not exist in the release that is really running. For the PHP runtime itself (version, OS, loaded extensions) use the…

not rated 37 +4 4d ago A 65 tokens copy · 98% MIT

novel-writing

7764

wgwtest/novel-writing

Skill Codex

Use when planning, drafting, revising, or reviewing fiction where character anchoring, viewpoint drift, implausible knowledge or decisions, unnatural dialogue, scene or chapter continuity, style fidelity, or grounded physical and institutional causality matter.

not rated 37 +2 changed 4d ago A SkillSpector: pass 51 tokens original MIT

clip-skills

7765

appergb/ClipSkills

Skill Claude CodeCodex

A video-editing skill that turns professional editing practices into repeatable rules for an AI agent. It covers tasks such as cutting spoken videos, adding music and B-roll, adjusting color, using keyframes, masking, tracking, compositing, and exporting.

not rated 37 +2 3mo ago A 295 tokens

vivado-debug

7766

adeleempurpled290/FPGA-Agent-skills

Skill Claude CodeCodex

Use this skill when the user needs help with Vivado in-system debugging, hardware programming, or debug core configuration. This includes ILA (Integrated Logic Analyzer) configuration and trigger strategies, VIO (Virtual I/O) usage for signal monitoring and control, JTAG-to-AXI Master for AXI transaction generation…

not rated 37 +2 yesterday A 183 tokens GPL-2.0

appstore-connect-mcp

7767

ryaker/appstore-connect-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Apple Store Connect API integration with OAuth authentication support. Runs locally from the @ryaker/appstore-connect-mcp npm package. Needs 10 environment variables to run.

not rated 37 +1 20d ago A tokens not measured original MIT

handoff

7768

PVRLabs/aibadger

Skill Claude CodeCodex

Transfer the current coding, debugging, planning, or architecture session to AI Badger. Use for broad session continuation; use badger-review for an independent review.

not rated 37 +2 changed 14d ago A SkillSpector: pass 35 tokens original MIT

director-agent

7769

6174/recut

Skill Codex

Skill "director-agent" from 6174/recut, covering director agent, core rule, usability and anti-laziness contract, output must be usable and modes.

not rated 37 +4 changed today A 0 tokens

wit

7770

deltadbu/WIT-skill

Skill Claude CodeCodex

Apply WIT (Writing Is Thinking) as a human–LLM collaborative scientific reasoning skill for scientific question formulation, finding-driven research planning, next-experiment selection, Results or Discussion review, claim–evidence and reviewer stress tests, manuscript logic audits, deadline closure, and researcher…

not rated 37 +2 changed 13d ago A 93 tokens

devboards

7771

GumbyEnder/agent-relay

Skill Claude CodeCodex

Client agent loop for Dev Boards over HTTPS only.

not rated 37 1mo ago A SkillSpector: warn 13 tokens original MIT

agents-spec

7772

leftzzzz/agents-spec-skill

Skill Codex

Audit, reorganize, split, migrate, and maintain AGENTS.md, optional platform instruction files, and non-business engineering Specs with cross-agent routing and SDD-aligned docs/specs, docs/requirements, and docs/technical directories. Use when cleaning up agent instructions, organizing engineering standards…

not rated 37 28d ago A SkillSpector: warn 98 tokens original MIT

krouter-obsidian

7773

398894496-arch/runtime36

Skill Claude CodeCodex

KRouter Obsidian — route knowledge-dependent tasks to the smallest current evidence set in an Obsidian vault using deterministic local search. Use when a request depends on durable user preferences, prior corrections or superseded claims, long-term project history or results, reusable methods or evidence, or the…

not rated 37 changed 11d ago A SkillSpector: pass 85 tokens original MIT

code-trace-tree

7774

saidake/code-trace-tree-vscode

Skill Claude CodeCodex

Read, edit, and refresh Code Trace Tree plugin data (VS Code and JetBrains). Use when the user asks to add/update/remove trace points (line, file, or directory), inspect or modify Code Trace Tree profiles, sync agent-written traces into the IDE, ask the IDE to reload plugin data, or select/navigate to trace points in…

not rated 37 changed 13d ago C 230 tokens copy · 100% MIT

vibium

7776

prebid/salesagent

MCP server Claude CodeCodexCursor +2

Browser automation for AI agents and humans. Runs locally from the vibium npm package.

not rated 37 yesterday A tokens not measured original Apache-2.0

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: