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. 272,697 indexed, measured the same four ways as everything else here.

enso-researcher

17161

Proxy2021/Enso

Skill Claude CodeCodex

Deep multi-angle web research with AI synthesis, images, videos, and persistent history.

not rated 6 4mo ago A 22 tokens original MIT

tempera

17162

anvanster/tempera

MCP server Claude CodeCodexCursor +2

Persistent episodic memory for AI coding: capture, retrieve, brief, dream cycle, cross-project. Runs locally from the @astudioplus/tempera-mcp npm package.

not rated 6 4mo ago A tokens not measured original Apache-2.0

outlook-snds

17163

optipub/outlook-snds-mcp

MCP server Claude CodeCodexCursor +2

MCP server "outlook-snds" as configured in optipub/outlook-snds-mcp. Launched with https://github.com/optipub/outlook-snds-mcp/releases/download/v1.0.4/outlook-snd.

not rated 6 2mo ago A tokens not measured original MIT

concept-fable

17164

hawkongz/concept-fable

Skill Claude CodeCodex

Trigger when users say "explain with a story," "tell me a fable," "give me an analogy," "ELI5," or "help me understand intuitively" about a concept. Uses fables to illuminate abstract concepts — the story never mentions the term, only revealing it at the end.

not rated 6 4mo ago A 67 tokens original MIT

brat-architecture

17165

neul-labs/brat

Skill Claude CodeCodex

Architecture phase skill. Input: product requirements + current arch KB. Output: architecture design as zkb notes.

not rated 6 3mo ago A 27 tokens original MIT

termpeek

17166

0xNyk/termpeek

Skill Claude CodeCodex

Preview images, video, PDFs, code files, diffs, and tweets from inside an agent CLI that cannot render them. Use when the user asks to see, view, preview, show, or look at a file — screenshots, generated images, charts, mockups, video clips, PDFs, or a code diff — or says "show me", "let me see it", "preview that"…

not rated 6 1mo ago A 129 tokens original MIT

coding-quality-loop

17167

zaingz/coding-quality-loop

Skill Claude CodeCodex

Use when a coding agent must turn a software goal, bug, issue, or refactor into a small, verified, independently reviewed code change.

not rated 6 +1 1mo ago A 33 tokens original MIT

blindspot

17168

IdanTayree/Blindspot

Skill Codex

Turn an idea or under-planned project into a buildable blueprint through a focused interview, decision-gap audit and verified open-source component research. Use for PRDs, project scoping, unresolved or conflicting requirements, and finding reusable components. Read existing decisions before asking questions. Works…

not rated 6 +1 changed 10d ago A 76 tokens original MIT

niuer/wechat-editorial-layout-skill

Skill Codex

A formatting workflow that turns Chinese Markdown, Word, or plain-text articles into HTML ready to paste into the WeChat public-account editor, with a preview page that includes one-click copying.

not rated 6 2mo ago A 85 tokens

clean-commit

17170

zyl100200/clean-commit-skill

Skill Claude CodeCodex

Writes git commit messages in a pure human-authored voice and strips AI attribution, tool watermarks, model names, co-author footers, and AI self-references. Use whenever creating, amending, rewriting, or reviewing a git commit message, including when running git commit, writing PR titles, or drafting commit bodies.

not rated 6 5mo ago A 69 tokens original MIT

stack-changes

17171

Ishtiaqhossain/claude_stack_changes

Skill Claude CodeCodex

Splits a large change into small, single-purpose units of review — PRs, diffs, or CLs — each making one argument (one diff, one thesis) and each buildable and testable on its own. Use when a change is too big to review, when a feature builds on existing code, when working in a large monorepo with stacked diffs, or…

not rated 6 3mo ago C 123 tokens

Azhi-ss/html-effectiveness

Skill Claude CodeCodex

A guide for creating illustrations and diagrams directly in a web page with inline SVG, a built-in format for scalable vector graphics. It covers document illustrations, flowcharts, state machines, and deployment pipelines.

not rated 6 4mo ago A 95 tokens original MIT

generate-docs

17173

mfbari/claude-skill-generate-docs

Skill Claude CodeCodex

Generates a complete, verified documentation suite for a codebase and wires it into AI-agent context files. Runs a multi-phase explore → generate → verify loop: scans the repo, writes 15 docs in docs/ (architecture, API reference, database schema, services, glossary, error catalog, security, and more) with Mermaid…

not rated 6 2mo ago A 169 tokens original MIT

save-context

17174

pioneerjeff-labs/packwright

Skill Claude CodeCodex

Use this skill at milestone handoff, session close, or when the user asks Atlas to preserve state.

not rated 6 +1 1mo ago A 0 tokens original MIT

pencil-ig-carousel

17175

stivenrosales/pencil-ig-carousel

Skill Claude CodeCodex

Use when creating Instagram, TikTok or LinkedIn carousel posts inside Pencil (.pen files) using MCP tools and publishing via Buffer API. Triggers: pencil carousel, ig carousel, carousel design pencil, instagram slides, crear carrusel, carrusel instagram, publicar carrusel, programar post, buffer carousel.

not rated 6 +1 5mo ago B 67 tokens original MIT

Thanarak-q/graph-engineering-workflow

Skill Codex

Plan and verify bounded agent graphs for complex coding work. Use when a coding agent needs to coordinate independent implementation, research, verification, auditing, isolated writers, merge ownership, or targeted repair loops. Prefer a single loop for small or genuinely sequential tasks.

not rated 6 1mo ago A 56 tokens original MIT

agent-security

17177

olanokhin/agent-security-skill

Skill Codex

Use when reviewing or writing LLM, RAG, MCP, tool, or agent code for OWASP-aligned security issues; triggered by "owasp my code", "owasp this PR", AI security review, PR review, or changes to AI system code.

not rated 6 3mo ago A 57 tokens original MIT

skill

17178

Rebel028/gauntlet

Skill Claude CodeCodex

A bias-check technique: spawn 2+ independent subagents, each attacking the idea from a different angle, to catch the flaw BEFORE it's set in concrete.

not rated 6 changed 24d ago A 0 tokens original MIT

weather-fetcher

17179

ashp15205/scankii

Skill Claude CodeCodex

Fetch weather data for any city using the OpenWeather API.

not rated 6 2mo ago A 16 tokens

cosbort/agent-skills

Skill Claude CodeCodex

Enterprise-grade Spring Boot 3.5.x/4.x development guide. Use when building Spring Boot APIs, microservices, or enterprise Java applications. Covers Java Records as DTOs, Virtual Threads, ProblemDetail (RFC 7807), RestClient, structured logging, Testcontainers, observability, sealed exception hierarchies, and GraalVM…

not rated 6 2mo ago A 104 tokens original MIT

spec-first

17181

zzusp/doc-first-dev

Skill Claude CodeCodex

A Chinese-language, document-first workflow for handling a complete software change from requirements through delivery.

not rated 6 5mo ago A 78 tokens original MIT

serpsmith

17182

emiliojohann/SERPsmith

Skill Claude CodeCodex

Publish SEO articles, verify unattended health, and gate source-to-runtime releases.

not rated 6 changed 2d ago A 19 tokens AGPL-3.0

askama

17183

uwuclxdy/agenticat

Skill Claude CodeCodex

Askama Rust templating reference (0.16).

not rated 6 6d ago A SkillSpector: pass 14 tokens original MIT

pe-plots-paper

17184

Zane456/pe-plots-paper

Skill Claude CodeCodex

Publication-quality plotting for power electronics / electrical engineering: IEEE-paper-grade figures via matplotlib (3.5in single-column or 7.16in double-column, 8pt, 600dpi PNG, no in-figure title). Covers waveforms (switching, DAB, multi-channel, double-pulse, resonant, three-phase), efficiency curves, loss…

not rated 6 2mo ago A 218 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: