Agent Plugins Marketplace

Recently added

Plugins grouped by the day they were added to the directory, newest first.

Sep 20, 2026

  1. gmail0stars

    Work with Gmail using the configured Gmail app connector.

    Codex1 MCP server
  2. github0stars

    Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.

    Codex1 MCP server
  3. game-studio0stars

    Design, prototype, and ship browser games with guided 2D and 3D workflows, asset pipelines, and playtesting support.

    Codex9 skills
  4. figma0stars

    Figma workflows for design implementation, Code Connect templates, and design system rule generation.

    Codex12 skills1 MCP server
  5. expo0stars

    Official Expo skills for building, deploying, upgrading, and debugging Expo and React Native apps.

    Codex13 skills
  6. dropbox0stars

    The Dropbox plugin for ChatGPT connects your Dropbox files directly to ChatGPT. You can access files, save ChatGPT-generated content to Dropbox, and create sharing links without switching tools. Everything respects your existing Dropbox permissions, and ChatGPT only works with files you already have access to.

    Codex6 skills1 MCP server
  7. datadog0stars

    Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production applications, identify, visualize, and remediate issues in your critical services. Run agentic loops to ensure you continue to maintain good observability and service management posture.

    Codex1 MCP server
  8. data-analytics0stars

    Answer product and business questions with data

    Codex15 skills1 MCP server
  9. creative-production0stars

    Explore campaign ideas, concept images, mood boards, product placements, ad directions, listing images, social posts, and launch assets.

    Codex2 skills1 MCP server
  10. consensus0stars

    Consensus is the go-to MCP for academic research. Connect directly to 220M+ peer-reviewed papers to search, synthesize, and build structured research outputs from within your conversation. Run literature reviews, build boolean search strategies, generate bibliographies, identify research gaps, and draft cited content — grounded in studies from PubMed, Semantic Scholar, and ArXiv. Pre-built workflows handle complex tasks in minutes: systematic reviews, curriculum reading lists, grant research with novelty analysis, and clinical evidence synthesis. Built for researchers, students, faculty, and clinicians across biomedical, social science, STEM, and all academic disciplines.

    Codex1 MCP server
  11. codex-security0stars

    Codex Security workflows for security scans, analysis, and investigation.

    Codex15 skills1 MCP server
  12. coderabbit0stars

    AI-powered code review in Codex, powered by CodeRabbit.

    Codex
  13. cloudflare0stars

    Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.

    Codex9 skills1 MCP server
  14. clickup0stars

    Turn Codex into your ClickUp command center.

    Codex1 MCP server
  15. circleci0stars

    Build, test, and deploy any application. Includes 1 skill.

    Codex1 skill
  16. chatcut0stars

    Install, open, and connect the signed ChatCut Desktop app from Codex.

    Codex1 skill
  17. canva0stars

    Bring your Canva design workflow into Codex and create, refine, and review designs through natural conversation. Available skills: Resize for social media: Adapt a design for Facebook, Instagram, and LinkedIn in one step. Bulk create: Generate multiple designs from spreadsheet data using a brand template. Edit designs: Update text, media, and formatting, or reposition and resize elements. Get design feedback: Receive structured feedback on visual hierarchy, layout, readability, consistency, and accessibility. Implement feedback: Review comment threads and apply clear, actionable changes. Brand check: Check colors, fonts, logo usage, and copy against your Brand Kit. Once installed, describe what you want in plain language or invoke Canva directly with @Canva. Try prompts like: - @Canva, resize this design for social media. - @Canva, create designs from this spreadsheet using my brand template. - @Canva, update the headline in this design. - @Canva, review this design’s visual hierarchy and readability. - @Canva, implement the feedback in the comment threads. - @Canva, check this design against my Brand Kit. Requirements: Connect your Canva account to use the plugin. Bulk Create requires an eligible Canva Enterprise plan. Want to take a more hands-on approach? Instantly open your design in Canva’s powerful editor for the final touches.

    Codex8 skills1 MCP server
  18. build-web-data-visualization0stars

    Design, critique, implement, test, and export web data visualizations in Codex, including charts, maps, dashboards, Gantt, UML, scrollytelling, reports, slides, mobile views, shareable state, and advanced WebGL concepts.

    Codex18 skills
  19. build-web-apps0stars

    Build web apps with frontend asset design, browser testing, UI components, payments, and database guidance.

    Codex4 skills
  20. build-macos-apps0stars

    Build, run, test, debug, instrument, and implement local macOS apps using Xcode, SwiftUI, AppKit interop, unified logging, and shell-first desktop workflows.

    Codex11 skills
  21. build-ios-apps0stars

    Build iOS apps with workflows for App Intents, SwiftUI UI work, Simulator mirroring in the Codex in-app browser, performance profiling, leak investigation, and simulator debugging.

    Codex9 skills1 MCP server
  22. boltz-api-cli0stars

    Predict structures, screen molecules and proteins, and design binders.

    Codex8 skills
  23. atlassian-rovo0stars

    Manage Jira and Confluence fast. Includes 1 MCP server.

    Codex1 MCP server
  24. airtable0stars

    Bring operational data and context into the flow of your ChatGPT conversations. You can ask questions, create and update records, and analyze your data—all through conversation. Use the data in Airtable as input to the work you’re doing in ChatGPT, like building a landing page using content you’ve organized in Airtable. Make quick updates to Airtable without leaving the chat. Airtable for ChatGPT is ideal anytime you need quick access to structured internal data to inform your conversation. Airtable's App connects ChatGPT directly to your Airtable bases, so you can ask questions, create and update records, and analyze your data—all through conversation

    Codex3 skills1 MCP server
  25. adobe0stars

    Adobe unlocks more ways to create and get work done from the conversation. Previously available as Photoshop, the Adobe connector now brings creativity and productivity capabilities across Creative Cloud and Acrobat. Describe what you want to make or change, and Adobe can help turn ideas, images, videos, and documents into polished outputs — from editing photos and creating PDFs to designing social assets, resizing videos, searching Creative Cloud assets, and generating data-driven documents. Key capabilities: * Retouch portraits or edit photos in bulk: Drop in photos and describe the look you want — adjust color, lighting, and tone; remove distractions and generate new elements; apply Lightroom presets; remove backgrounds; blur, crop, resize, and expand images. * Design from template: Start from an Express template, update text and colors, and then animate for social media or convert to PDF. * Refine video for any platform: Upload a horizontal clip and ask to reformat it for YouTube Shorts, Instagram Reels, or any platform. You can also stitch clips into a single sequence. * Search and organize creative work: Describe what you're looking for and surface assets from your Creative Cloud library — by subject, style, mood, or content — without browsing folders. * Work with PDFs and documents: Create and convert polished PDFs and documents. * Create data-driven documents: Describe your output and provide your data — the connector turns raw data or content into formatted, shareable PDFs, including badges, cards, catalogs, and more. You can get started as a guest, and sign in with your Adobe account for more capabilities and tools, Creative Cloud storage, and saved work across sessions.

    Codex6 skills
  26. mineral-atlas-workbench0stars

    本机晶面分析、三轴/四轴构形、照片配准与可复现报告. Includes 1 skill and 1 MCP server.

    CodexAgent Plugins1 skill1 MCP server
  27. rpi-codex-harness0stars

    Evidence-driven Research, Plan, Implement workflow for controlled code changes in Codex.

    Codex1 skill
  28. relative-path-probe0stars

    Probe Codex relative MCP argument handling.

    Codex1 skill1 MCP server
  29. avaya-case-review0stars

    Evidence-grounded Avaya Siebel SR and ServiceNow incident reviews with exhaustive Gmail correlation, explicit QA scoring, and alarm auditing.

    Codex4 skills2 MCP servers
  30. workflow2stars

    文档驱动的多代理开发工作流（指挥/执行/评审三层）：/scaffold 在项目里铺设 CLAUDE.md + docs 八件套脚手架，/whats-next 读文档判断下一步该干什么，sop-generate 为已部署的 Web 应用生成带截图的中文业务 SOP；新会话自动认出「要做新项目」并静默铺设脚手架（auto-scaffold，可 opt-out）；docs-capture 三层 hook 自动把问答框拍板存入 DECISIONS.inbox、按信号词提醒决策/需求未落档、commit 前门禁催消化，防止关键决策与需求随对话蒸发；方法论含目标台账（需求当轮落账防蒸发）、四点评审纪律（链式对抗评审／评审报差异／安全加固措辞／生产红线前置到实现侧）、调研内部先行与组件索引收尾登记

    Claude Code3 skills
  31. workflow-en2stars

    Doc-driven multi-agent development workflow (Conductor/Executor/Reviewer three tiers): /scaffold lays down CLAUDE.md + an eight-doc set in place; /whats-next reads the docs and tells you what to do next; sop-generate generates a screenshot-backed business SOP for an already deployed web app; new sessions auto-recognize "wants to build a new project" and silently scaffold it (auto-scaffold, opt-out available); docs-capture — three hook layers auto-log AskUserQuestion decisions to DECISIONS.inbox, nudge on decision/requirement signal words, and gate commits until the inbox is triaged, so key decisions and requirements don't evaporate; the methodology carries a goal ledger (log requirements the same round so they never evaporate), four review disciplines (chained adversarial review / delta-only reports / neutral hardening wording / production red lines in the implementer prompt), internal-first research and component-index registration at wrap-up

    Claude Code3 skills
  32. workflow-codex2stars

    Codex 版:文档驱动的多代理开发工作流 —— scaffold 在项目里铺设 AGENTS.md + docs 八件套脚手架、whats-next 读文档判断下一步该干什么、sop-generate 为已部署的 Web 应用生成带截图的中文业务 SOP、parallel-do 拆分任务并用 Codex subagents 并行执行、speak-human 让 Codex 提问与表达遵守说人话纪律

    Codex5 skills
  33. ui-sweep2stars

    中文版:SOP 截图前/改完一批 UI 后,把全站可交互元素系统性点一遍——agent-browser(Rust CLI,自带 Chrome,a11y 快照)驱动 + 通用化遍历引擎(config 外置、默认拦截名单只增不减、八分类记账 + 可选孤儿功能对账:代码清单 vs 遍历实际到达,查「功能实现了但前端没入口/入口打不通」)。安全边界:破坏性按钮只记不点、confirm/prompt 一律驳回、出域双层防护(--allowed-domains 限显式导航 + 引擎逐击域名校验,出域即拉回),只用于自家或已获授权的站点。

    Claude Code1 skill
  34. ui-sweep-en2stars

    English version: before SOP screenshots or after a batch of UI changes, systematically click every interactive element on the site — driven by agent-browser (Rust CLI, bundled Chrome, a11y snapshots) plus a generalized traversal engine (externalized config, an append-only default denylist, eight-category ledger, plus an optional orphan-feature audit: code inventory vs what the sweep actually reached, finding features with no UI entry point or a broken one). Safety boundary: destructive buttons are logged, never clicked; confirm/prompt dialogs are always dismissed; two-layer domain guard (--allowed-domains for explicit navigation + per-click hostname check, off-domain clicks pulled back on the spot); only for sites you own or are authorized to test.

    Claude Code1 skill
  35. speak-human2stars

    中文版:让 Claude 说人话、会提问——提问前自检清单(先核实/交代背景/黑话带解释/选项留组合位) + 表达纪律(S1~S6,含 S6 更新日志式汇报:多项进展或有未做/问题时用「本次完成/未完成/已知问题」三段体),规则源自作者 548 次真实 AskUserQuestion 抉择记录的数据挖掘。touch ~/.claude/.speak-human-always 即常驻

    Claude Code1 skill
  36. speak-human-en2stars

    English version: make Claude speak human and ask well — a pre-question self-check (verify first / brief the context / gloss the jargon / leave room to combine options) plus expression discipline (S1–S6, incl. S6 changelog-style reporting: multi-item progress or anything undone/wrong gets a Done/Not done/Known issues report), mined from 548 real AskUserQuestion decision records. touch ~/.claude/.speak-human-always to keep it always on

    Claude Code1 skill
  37. send-to2stars

    中文版:/send-to <会话名> 把消息转达给本机另一个 Claude Code 会话——会话名前缀/子串模糊匹配,多个或零个命中亮列表让用户挑,消息强制自包含,[ref] 确认照抄重发,发送后如实汇报挂起状态;跨 profile 窗口发现互不可见但 uds: 地址可直发(标准路径),配 SessionStart 注册 hook 把 socket 清单翻译成身份注册表(默认开,touch ~/.claude/.cc-session-registry-off 全局停用),四级找目标阶梯,文件交接降级为最后兜底;HAPI 会话里 ping_peer 可用但绝不传 force(被拒即 force 会杀掉对方 Claude 进程),被拒改走 inspect_peer 的 claudeSessionId → 注册表 → SendMessage;经 ping_peer 发的消息须自报家门。基于跨会话消息功能(Claude Code v2.1.224+,macOS/Linux)

    Claude Code1 skill
  38. send-to-en2stars

    English version: /send-to <session-name> relays a message to another Claude Code session on this machine — fuzzy prefix/substring name matching, shows the session list on zero/multiple hits, enforces self-contained messages, verbatim [ref] retry, honest held-delivery reporting; cross-profile windows are mutually invisible but reachable via a direct uds: address (the standard path), a SessionStart registration hook translates the socket list into a shared identity registry (on by default; touch ~/.claude/.cc-session-registry-off to disable globally), a four-tier target-finding ladder, file handoff as the final fallback; inside HAPI sessions ping_peer may be used but never with force (a refusal means force would kill the target's Claude process) — on refusal go inspect_peer's claudeSessionId → registry → SendMessage; messages sent via ping_peer must identify the sending window. Built on cross-session messaging (Claude Code v2.1.224+, macOS/Linux)

    Claude Code1 skill
  39. fast-jev-compaction0stars

    Portable Agent MCP plugin for on-demand, verbatim Jev-guided transcript compaction.

    CodexAgent Plugins1 skill1 MCP server
  40. delivery-mentor0stars

    Delivery and collaboration discipline for fast builders and their coding agents, for Codex.

    CodexClaude Code1 skill
  41. architecture-mentor0stars

    Pragmatic architecture review and production-readiness mentoring workflow for Codex.

    CodexClaude Code1 skill
  42. typesafe2.2kstars

    Agent skills for building with the TypeSafe System One API.

    Claude Code1 skill
  43. work-router0stars

    Routes substantial agent work to the leanest reliable parent or subagent configuration on task shape, ambiguity, risk, latency, and token use. Carries a route table for Claude Code and one for Codex. Includes capability discovery and scoped deduplication of installed skills.

    CodexClaude Code4 skills
  44. ui-walkthrough-video0stars

    Record real UI walkthroughs with editable native-project handoffs, or produce standalone narration with provider auditions and reusable revoice exports.

    CodexClaude Code2 skills
  45. ui-router0stars

    Route UI work through focused skills, project-specific references, purposeful questions, and verified visual/media interactions. Updated 2026-09-20.

    CodexClaude Code2 skills
  46. natural-writing0stars

    Diagnose, edit, rewrite, or draft natural prose while preserving facts, formatting, intent, register, and author voice.

    CodexClaude Code1 skill
  47. deck-builder0stars

    Build and quality-check PowerPoint decks on top of any corporate template, with the brand supplied as configuration rather than baked into the skill.

    CodexClaude Code
  48. capability-storyboard0stars

    Build a capability-first, multi-tool HTML storyboard for a keynote, demo walkthrough, or narrative product doc.

    CodexClaude Code1 skill
  49. rel0stars

    Browse and build restartable crawlers with REL's persistent embedded Chromium sessions.

    CodexClaude Code2 skills1 MCP server
  50. krill-work1stars

    Work-axis krill plugin: MCP access to krill's spec surface plus the milestone/delivery-axis tools and the full task lifecycle (create/claim/heartbeat/complete/abandon/note/dependencies, M3-M5), plus planner/worker/validator/system-validator/mergepush personas and plan/implement/validate skills forked from project-manager. Swimlane execution is krill-native (no GitHub Issues/Projects) whenever a krill Milestone scopes the work; GitHub remains the fallback only for a FeatureSet with no Milestone -- see CONVENTIONS.md.

    Claude Code4 skills6 MCP servers