awesome-ai-plugins

Awesome AI Plugins

A curated, cross-platform list of plugins, skills, MCP servers, apps, and agent tools for AI assistants.

Discover extensions for Codex, ChatGPT, Claude Code, Gemini CLI, Grok, Kimi, DeepSeek Harness, Cursor, OpenCode, and other compatible AI assistants from one community-maintained catalog.

Listings may target one assistant, several assistants, or open standards such as Agent Skills and MCP. Check each project for its supported clients and installation instructions.

Contents

• Start Here
• Official Plugins
• Community Plugins
  • Agent Skills
  • Grok Plugins
  • Kimi Plugins
  • DeepSeek Harness Plugins
• Formats & Development
• Guides & Articles
• Related Projects
• Claim Your Plugin
• Plugin Trust Scores
• Plugin Quality
• Contributing

---

Start Here

New extension workflow:

1. Choose the clients and open formats you support
2. Build the plugin, skill, MCP server, app, or agent tool
3. Validate with plugin-scanner — recommended local preflight
4. Add the HOL scanner GitHub Action — recommended for security, optional for listing
5. Ship or submit with confidence

Quick preflight

pipx run plugin-scanner lint .
pipx run plugin-scanner verify .

Scanner CI (recommended for security)

Scanner CI is optional for listing. HOL still scans listed projects independently. We recommend including it so MCP servers, skills, plugins, and other agent extensions stay continuously checked — that is how this catalog stays safer for everyone who installs from it. Projects that maintain scanner CI receive the full trust score; projects without it remain eligible and receive a 10% trust-score reduction.

See the full guide: SCANNER_GUIDE.md
See contributing requirements: CONTRIBUTING.md

The README is the human-readable cross-platform catalog. Machine-readable compatibility exports are available in plugins.json and .agents/plugins/marketplace.json for registry and automation consumers.

Browse the catalog

Browse the sections below or use the searchable HOL Plugin Registry. Installation varies by client and project, so follow the linked project’s setup guide.

This repository is a discovery catalog, not a universal installer. Follow each linked project’s instructions for the clients and formats it supports.

Official Plugins

• mblode/agent-skills - Nobody ships AI slop on purpose. These skills make sure you don’t. UI audits, typography, docs, PR review, and releases.

Curated by OpenAI — available in the built-in Codex Plugin Directory

• Box - Access and manage files.
• Cloudflare - Manage Workers, Pages, DNS, and infrastructure.
• Figma - Inspect designs, extract specs, and document components.
• GitHub - Review changes, manage issues, and interact with repositories.
• Gmail - Read, search, and compose emails.
• Google Drive - Edit and manage files in Google Drive.
• Hugging Face - Browse models, datasets, and spaces.
• Linear - Create and manage issues, projects, and workflows.
• Notion - Create and edit pages, databases, and content.
• Sentry - Monitor errors, triage issues, and track performance.
• Slack - Send messages, search channels, manage conversations.
• Vercel - Deploy, preview, and manage Vercel projects.

Community Plugins

Community-built plugins, native skills, MCP servers, and related agent extensions. PRs welcome!

Agent Skills

Individually installable Agent Skills collections, rather than one client-specific plugin bundle.

• 97 - Agent skills distilled from established programming practice that load at decision points like refactoring, testing, API design, and code review, packaged as a plugin for Claude Code, GitHub Copilot CLI, and OpenCode.
• Agent Skill Builder - Agent Skill that builds Claude Code or portable Agent Skills and validates frontmatter, invocation controls, tool grants, links, and spec drift, with tests showing that malformed skills fail.
• Agent Skills - Nine Agent Skills for session management, multi-session reconciliation, worktree recovery, multi-model code review, eval integrity, SSOT drift checks, skill creation, guest research, and angel diligence, installable for Claude Code, Codex, Cursor, and OpenCode.
• Agent Workspace - Six Agent Skills for persistent workspace state, session checkpoints, daily briefings, multi-session reconciliation, and approval-gated worktree recovery, with a configurable file layout.
• agent-notion-template-docs - Agent skill that renders agent-generated documents with Notion’s blocks and visual style using a fixed HTML template and CSS linter.
• answer-me-with-html - Agent skill for Claude Code, Codex, Cursor and OpenCode that answers complex questions as a single offline HTML page and can narrate them as explainer videos.
• antirea - A Claude Code skill to protect projects and dev workspaces against AI reverse engineering and instruction leaks.
• archlang - Agent skills and MCP server that let coding agents write floor plans in the ArchLang .arch language and compile them to dimensioned SVG, DXF or PDF with lint and geometric validation.
• ART Prompt Framework - Agent skill that turns rough requests into structured, context-rich prompts using the Act As, Request, and Terms framework.
• Awesome QA Skills - Bilingual collection of 330 installable QA agent skills covering test workflows, test types, and skill engineering across the SDLC.
• berlin-job-search - Agent skill for Berlin and Germany job search: German-language and visa requirement checks, Lebenslauf drafting and interview practice.
• Build Omarchy Plugins - Twelve agent skills for scaffolding, debugging, testing, releasing and publishing Omarchy 4 Quattro shell plugins.
• claude-skills - 67 Agent Skills for full-stack development across languages, frameworks, infrastructure, testing, security, and data/ML, with 371 reference files that load only when a task needs them and 9 project workflow commands.
• claudemy - Claude Code skill that researches a named topic on the web and builds a course of 2-minute audio lessons with citations.
• Coacus - Cross-harness collection of agent skills, agents, and workflows with filtered installation and discovery tooling.
• cometchat-skills - Agent skill collection that has your AI coding agent add CometChat chat and voice/video calling into an existing React, Angular, React Native, iOS, Android or Flutter app, bundled as a plugin with the CometChat docs MCP server.
• CoMPaSS Prompt Framework - Agent skill for analysis-first prompting that clarifies intention, assembles consequential prompts from explicit components, and verifies their success criteria.
• Competitive Skills by LMTY - Sixteen Agent Skills for founders and go-to-market teams who sell against competitors: research competitors, answer “how are you different from X?”, prep competitive deals, build battlecards, analyze wins and losses, and pressure-test positioning, messaging, and pricing; they run standalone, and with the LMTY MCP server connected each one starts from your tracked competitors, what changed and when, and the source behind every finding.
• conventional-commits-framework - Agent skill for complete, atomic Conventional Commits with every field filled, breaking changes declared explicitly, and one consistent AI co-author trailer, plus commitlint, git hook, and release tooling setup.
• Cooper Email - Agent Skills and a hosted MCP server that give an AI agent its own email inbox to send, receive, reply, and wait for replies or verification codes, with a Claude Code plugin and a Cursor plugin.
• DCC-MCP Agent Plugins - Agent Skills for discovering creative applications, using typed DCC tools, and developing DCC-MCP adapters and skills.
• de-anthropocentric-research-engine - 271 research skills that take a research direction from first question to tested hypothesis: 51 tactics drive 216 atomic steps across literature synthesis, gap validation, hypothesis formation, experiment design and result interpretation, backing out when the evidence is too thin instead of marching a fixed pipeline - the plan is approved before anything runs, checkpoints resume after an interruption, and one command installs it into any agent with no runtime and no API key.
• Deacon Skills - Two agent skills that install the Deacon AI support widget on a site or app, tell it who is signed in, and send it goals such as sign ups, also packaged as a Claude Code plugin marketplace.
• deed.page - Agent skill that publishes an HTML file or static folder to a permanent public deed.page URL with one curl request and no account.
• design-intelligence - Helps AI agents understand your product and users first, then design UI with a direction that fits them, not a generic template.
• devops-mock-interview - Agent skill that runs a DevOps, SRE or platform engineer mock interview with live production incidents and system design, then gives an honest score out of 10 and a written report.
• dex - Agent skills for warehouse exploration, dbt transformation authoring, and schema-drift maintenance. Built by Exmergo.
• docx-cli - Agent skill/CLI for AI agents to work with Word documents without breaking their formatting: fill in forms, update tables, add images, restyle, write reports, and redline with tracked changes and comments.
• econ-slides-skill - Agent skill that builds economics research talks in LaTeX/Beamer from papers, with discussant decks and timed speaker scripts.
• ego-decision-layer - Agent skill for ego lite browser automation with a swappable per-step decision model, guarded execution, and schema-validated extraction.
• Find Hiring Manager - Agent skill for Claude Code, Cursor and other skills-compatible agents that takes one job posting and finds the hiring manager, recruiter and likely referral contacts, with evidence for each person and outreach drafts.
• FMXER - Agent skill teaching AI coding agents the FMXER declarative UI framework for Delphi FireMonkey: screens composed in code with named routes, a scaffold, layouts and Skia elements.
• formosa-humanizer - Agent skill that rewrites AI-generated Traditional Chinese prose, removing AI phrasing and mainland China terms across 49 patterns.
• Global Engineering Standards - Twelve engineering standards and six Claude Code and Codex skills for security, privacy, cost and architecture, installable with npm install -g @enki-dev-expert/global-engineering-standards.
• grcskills - 64 open GRC skills that draft risk registers, statements of applicability, audit prep and NIST RMF documents, leaving every sign-off to the practitioner, with an optional framework lookup MCP server.
• Handoff - Agent skill that saves and resumes coding sessions across agents using a repository-root HANDOFF.md with goals, constraints, and next steps.
• hoi4-ai-modding-skills - Three Hearts of Iron IV Agent Skills plus a local read-only MCP helper for mod diagnosis, validation, and content development.
• humanizer-lint - Agent skill that flags AI stock phrases, flat sentence rhythm, and repetition with per-sentence fix hints across eight languages, running locally with zero dependencies and no data leaving the machine.
• idea-to-motion - Agent skill that turns any idea into a motion-design video (MP4) with procedural music, synthesised sound effects and an optional local voice-over with captions; asks up to 3 questions only when the brief is incomplete, 14 styles, rendered locally with HyperFrames, no API key.
• image-use - Agent skill and zero-dependency CLI for generating and editing images with existing ChatGPT or Gemini accounts, with reference images, reusable styles and looping animations without an API key.
• Inbox Envoy - Agent skill that lets your personal AI agent protect your inbox, keep important mail visible, and research unfamiliar offers.
• Jam Skills - Agent skills that record a browser session as a Jam, read Jam recordings (video, console, network) to find root causes, and attach proof-of-work Jams to agent PRs.
• k-skill - Collection of agent skills automating Korean daily-life tasks such as KTX timetable lookup, Coupang search, and delivery tracking.
• k8s-skills - Kubernetes troubleshooting skills for 30 cases, from pods, nodes and networking to Velero and CloudNativePG, that read first and ask before changing anything.
• kaggle-tools - Nine Agent Skills for Kaggle competitions covering CV design, code-competition submissions, LLM reasoning, serving and fine-tuning, leaderboard analysis, bioacoustics, medical imaging and tabular work, distilled from real competitions and packaged as a Claude Code plugin.
• Krexa - Agent skill and hosted MCP server that turn a trading idea, post or video into a backtested, paper-traded strategy (free) and, after the user approves and signs, a live trading agent on Binance, Coinbase, Kraken, OKX, Bybit, MEXC, Hyperliquid, Polymarket and Solana DEXs with order limits enforced server-side.
• kstack - Eleven agent skills for Herdr that plan with two models checking each other, build with parallel reviewed workers, run a verification swarm, then push a PR and fix it until checks are green.
• Kuudo Skills - 22 Agent Skills for Amazon sellers and advertisers covering Sponsored Products and Brands audits, search-term mining, budget pacing, DSP and Amazon Marketing Cloud, listings, product images, repricing, FBA inbound, and profitability, built for Kuudo’s hosted Amazon Ads and SP-API MCP servers, with price, budget, listing, and shipment writes previewed for explicit approval.
• Lagune - Agent skill collection that secures a project before, during, and after development, in any language or stack: a security charter, the universal skill that hardens code as it is written, and a Blue Team audit that takes each risk from detection to a verified fix.
• LogBrew - Agent skills that let any AI agent read your production errors, logs, and traces in LogBrew to find why something broke, add error monitoring to an app, and check each release.
• Markdown OKF-Schema Studio - Agent skill, packaged as a plugin for Claude Code, GitHub Copilot CLI, VS Code agent plugins, and Agent Plugins clients, that teaches agents to write rich Markdown (cards, tabs, admonitions, charts, diagrams) rendered by the Markdown OKF-Schema Studio VS Code extension.
• MARS - Agent Skills for the MARS-Curiosity Delphi REST library that help AI coding agents scaffold MARS servers, develop REST APIs and MCP servers, and implement servers from OpenAPI documents with MARSgen.
• Master Skills - A unified collection of 2,660+ AI agent skills across 15 domains, with installation support for Claude Code, Codex, Cursor, Gemini CLI, Antigravity and other compatible assistants.
• max-skills - Agent skills for Claude Code and Codex that run your app locally to screenshot every screen a pull request changes as before/after pairs with the changes boxed, record a demo video of the PR’s flow, and write a short Slack-ready summary, posting the media into the PR description with gh.
• memory-use - Portable agent memory in a private Markdown Git repository, with topic-focused recall, cross-session and cross-machine sync, and pre-commit secret checks.
• MetaMask Agent Wallet - Official MetaMask Agent Skill and plugin that lets AI agents use the Agent Wallet CLI for auth, balances, swaps, bridges, perps, prediction markets, and yield from a self-custodial wallet.
• MiniCut - Agent skills for Claude Code, Codex, Cursor and Gemini CLI that make a multi-shot AI short film from an idea (story, shot sheet, takes, voice, music, edit) and run Seedance, Kling and Wan video models, with the price shown before every paid job.
• mock-interview - Agent skill that runs a realistic mock job interview for any role, with live research and real follow-up questions, then gives an honest score out of 10 and a written report.
• music-skill - Agent skill that composes original instrumental music as editable notes, performs it on sampled instruments and synthesizers, and renders MIDI, stems and mastered audio.
• Nitrogen - Agent skill and CLI that scaffold and deploy Shopify embedded apps on Firebase, with one Cloud Function per API resource, Firestore, and admin pages built from Polaris web components, also packaged as a Claude Code plugin marketplace.
• nuthinking/skills - Agent skills for Claude Code, Codex and Cursor, including site-edit, where editors pin notes on a live site and Claude Code turns them into pull requests, and product-map, which keeps a feature map and product flows in the repo.
• Pixi’VN - Agent skill collection teaching AI assistants to build story-driven games (visual novels, point-and-click, and interactive fiction) with the Pixi’VN engine.
• PlayCanvas Skills - 16 portable Agent Skills that teach AI coding agents to build, inspect, and verify PlayCanvas Engine, React, and Web Components applications, also packaged as Claude Code, Codex, and Cursor plugins.
• post - Agent skill that builds Xiaohongshu and X share-image sets with App Store poster layouts, real screenshots, and faithful app-UI mocks.
• Principal Engineer OS - Agent skill that guides AI-assisted engineering with explicit trade-offs, boundary-focused correctness, security and privacy review, operational judgment, and evidence-based delivery.
• pro-launch - Agent skill for building a product from zero to one with phase gates: references, naming and trademark checks, style frames, UI build loop, launch and shipping.
• pro-motion - Agent skill that plans the music first, then renders motion-graphics launch and brand films in code (canvas to MP4) cut to the track.
• profile-use - Agent skill that reuses one private personal profile across browser, iPhone and desktop forms, with masked reads, sensitive-field confirmation and approval before submission.
• renhua - Agent skill that writes Chinese social posts and product copy in a real person’s voice and removes common AI phrasing.
• research-agent-skills - 280+ Agent Skills that turn Claude Code, Codex, Cursor, Gemini CLI and other agents into a research co-scientist for literature reviews, hypotheses, experimental design, data analysis in biology, chemistry, medicine, physics and ML, paper writing, citation verification against Crossref, OpenAlex and arXiv, and peer review.
• Routine Cleanup - Claude Code skill and plugin that bulk-deletes a scheduled routine’s old run sessions in the desktop app, keeping the newest runs and every run you replied in.
• Ryugi - Agent skills that take a coding agent from brainstorming through an approved spec to test-driven implementation, debugging and UI verification, with a live artboard for comparing mockups and commenting on designs, packaged for Claude Code, Codex, Gemini CLI, OpenCode, Pi and other harnesses.
• Satori - Open-source wisdom companion skill (Apache 2.0) for coding agents and web chat, built to be outgrown: one lens per turn, a local SQLite memory vault, and trigger discipline that stays silent during pure coding work.
• ScoreStarling - Agent skills and hosted MCP server that transcribe, read, convert and edit sheet music, turning recordings, videos, sheet-music photos and PDFs, MIDI, MusicXML and ABC into one editable, playable score in a ScoreStarling account, with PDF, MusicXML, MIDI and audio exports.
• SeeCode - Agent skill that generates animated, explorable diagrams in 45 types from short JSON specs, exporting SVG, PNG, GIF and MP4.
• self-host - Agent skill and CLI that lets your agent install self-hosted apps on your own hardware and set them up (admin accounts, API keys, apps connected to each other), asking before each step.
• self-media-content-workflow - Ten agent skills covering the self-media content cycle, from briefs and trend research (including overseas-versus-China topic heat comparison) to platform copywriting, video production, publishing, and analytics.
• Sketchbook Style - Agent skill that draws any object as a black-ink industrial-design sketchbook page in four looks with open image models on ComfyUI or mflux, no API key; tested in Claude Code.
• skill-skill - Agent skill for writing and linting Claude skills, with a static audit script that reports a 0-100 health score.
• skills - A curated collection of 799 agent skills across 36 categories, installable into Claude Code, Cursor, and other SKILL.md-aware clients.
• tech-to-motion - Agent skill that turns real technical sources (docker-compose, Kubernetes, Terraform, CI workflows, postmortems) into a motion-design explainer video with animated architecture diagrams and synthesised sound effects, rendered locally with HyperFrames.
• uCoz - Nine Agent Skills and the official remote uCoz MCP so coding assistants can build landing pages, run ad campaigns, optimize a shop, translate a site, restyle the design, create original templates, write server scripts, manage content, and style popups.
• UI Verify - Agent skills for visual testing: set up screenshot tests on your existing Storybook, Playwright or Vitest suite, check a UI change before pushing, and triage each build’s diffs through the UI Verify MCP server.
• ui-craft - Design engineering skill collection for AI coding agents with slash commands, review agents, and MCP quality gates.
• Vectoree - Agent skill that gives coding agents a Vectoree Cloud backend for models, auth, databases and storage.
• vibes-plug - Cross-IDE AI skill collection that orchestrates 147 specialized subagents for full-stack development workflows.
• video-to-blender - Coding-agent skill that builds procedural Blender Geometry, Shader and compositor node graphs from Python with a tested node-group library and validation tools.
• vietnamese-language-skill - Collection of agent skills that fix Vietnamese register, terminology, and locale formatting across landing pages, docs, marketing, finance, and education, with a standalone validator.
• Webly - Agent skill and hosted MCP server that publish a website or share files and folders at a live URL in seconds with no account, then let the person claim it, edit it over MCP, and publish drafts they approve, also packaged as Claude Code, Codex, Cursor, and Gemini CLI plugins.
• writing-with-agents - Ten Agent Skills that turn Betty Flowers’ Madman, Architect, Carpenter, Judge writing method into a human-in-the-loop workflow, with SEO, a quality rubric, and content strategy.

Development & Workflow

• geml - An agent-native markup language featuring deterministic block-level editing and built-in validation to ensure documents never drift or break during AI operations.
• 2718lab DevKit - Codex-first local MCP server and skill bundle for deterministic project intelligence, durable workflow orchestration, and reusable engineering tools.
• A Team - Universal multi-agent infrastructure with 25 specialist agents, 16 enforced workflow skills, and a lead orchestrator for Claude Code, Codex CLI, Cursor, and OpenCode.
• ab-method - A skill and workflow plugin for Claude Code and Codex that grills problems into plans and drives test-driven missions with critic reviews.
• adr-kit - Architecture Decision Record toolkit for Claude Code, Codex, GitHub Copilot CLI, and OpenCode that injects the governing decisions before each edit, guides ADR authoring, and enforces decisions in deterministic pre-commit and CI gates.
• Aegis - An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
• aegotrax - Runtime tool-call gate for agents: session intent, approval queue, and audit stream.
• Agency Continuity Audit - Read-only audit that distinguishes durable agent goals, state, corrections, restart evidence, authority boundaries, scheduler claims, and commercial proof from self-reported health.
• Agent Context OS - Portable Git-backed context and session workflow layer with first-class Claude Code, Codex, and OpenClaw support plus experimental adapters for Hermes, Cursor, and Devin.
• Agent Deck - One MCP for context management: bind self-improving playbooks, MCP tools, and API keys to the session.
• Agent Guard - Real-time secret-leak guardrails for AI coding agents (Claude Code, Codex), Git hooks, and CI.
• Agent Guild - Vet autonomous agents before delegating work or money, verify portable passports, use escrow, and record signed outcomes across Claude Code, Codex, MCP, A2A, and OpenClaw.
• Agent Harness - Coding-agent plugin that routes project work through goals, tasks, runs, evidence gates, and state sync via project adapters.
• Agent Harness Skills - Designs agent-ready repository harnesses with entrypoints, validation surfaces, runtime evidence, delivery records, and atomic commit guidance.
• Agent Replay - Replays Claude Code, Codex and Gemini CLI sessions change by change with the agent’s own words above each step, flags what was not actually checked (failures hidden by a pipe, tests that lost assertions or gained a .skip, files changed after the last passing check), and installs as a Claude Code plugin with four skills and a capture-after-every-turn hook.
• Agent Workflow System - 一套中文AI工作流系统：7个协作技能 + 行为规范宪法 + 会话恢复机制，模糊目标→可执行任务，全生命周期引导。Codex & Claude Code 双平台，新手友好。
• agent-guard - Behavior-guardrail hooks for Claude Code: stops agents from editing tests to fake green builds and blocks risky outbound actions (optional Nemotron semantic reviewer).
• agent-kit - Extension pack of slash commands, skills, rules, and hooks adding plan-driven, confirmation-gated coding and staging-to-prod git workflows to Cursor and Claude Code.
• agent-memory-kit - Agent memory that asks before it writes: the agent proposes dated notes, you approve them, and they live as plain files in your repo, injected by hooks in Claude Code, Cursor CLI and OpenCode and read through skills and AGENTS.md in Codex and Copilot CLI.
• agent-recap - Stop hook for Claude Code and Codex that sends an agent back once if its last test run failed and its final message does not say so.
• agent-rules - Modular AGENTS.md, CLAUDE.md, Cursor rules, Copilot instructions and Claude Code skills for Next.js, TypeScript, React, Node, NestJS, Prisma, Drizzle, Tailwind and shadcn, with one installer that keeps the formats in sync.
• agent-sounds - Sound feedback plugin playing game voice lines on Claude Code and Codex session events, configurable by source and volume.
• agent-talk - Skills-based plugin built on the retalk CLI that gives coding agents end-to-end encrypted messaging with other agents, including agents run by other people, across Claude Code, Codex, Antigravity, pi, opencode, and GitHub Copilot CLI.
• AgentBridge - Local bidirectional bridge that keeps Claude Code and Codex live as peers in one session, with mid-turn injection and quota-window handoff.
• agentglass - Native terminal UI and JSON CLI that shows every Claude Code, Codex, Gemini CLI, pi, OpenCode, Kiro and fx session on your machine live, down to each tool call, diff, cost and stuck-agent alert.
• agentglass-herdr - herdr plugin that opens agentglass as a popup, jumps from any agent pane to its session, and adds opt-in cost and alert tokens for Claude Code, Codex and other agents to the herdr sidebar.
• Agentic Ship - Cross-host product-development toolkit for Claude Code, Codex, Cursor, Hermes, and OpenClaw with shared rules, specialist roles, service connections, and machine-checked UI, backend, security, and launch gates.
• agentic-readiness-assessment - Agent skill that audits a repository for AI coding agent readiness and produces an evidence-based scorecard with prioritized fixes.
• Agentizer - Turn any website into an AI-powered agentfront with split-pane
• AgentOps - DevOps layer for coding agents with flow, feedback, and memory that compounds between sessions.
• AgentPack - Ranks repo context for Codex with likely files, skill recommendations, agent rules, commands, warnings, and compact task-focused packs before editing.
• agentRamen - Local SQLite graph of code and git history plus session memory, so the agent stops re-reading the repo every prompt.
• Agentry Observability - Agent-native product analytics, error logging, and deploy attribution for coding agents through one HTTP API.
• AgentWiki - Rust CLI that generates C4-style architecture docs for any repository using already-authenticated agent CLIs (Claude Code, Codex, Devin) as the LLM backend.
• AgiFlow - Project management workflows for AI coding agents with planning, grooming, task execution, review, and AgiFlow MCP integration.
• agmsg - Cross-vendor messaging for CLI coding agents (Claude Code, Codex, Gemini CLI, Grok): sessions join a team by name and hand work to each other through a shared local SQLite file, with durable history and ext-tool members that let a program such as Slack or Jev join like any agent.
• Agnostic-AI - Capture your Claude Code or Codex harness once (rules, hooks, skills, subagents, commands and MCP servers) and apply it identically to Gemini CLI, Cursor, Antigravity and 16 more clients.
• Agon - Claude Code plugin for autonomous research: multi-agent scientist/coder/auditor loops take a topic through idea, proposal, and running experiments.
• AI Quota HUD - Windows desktop HUD showing % left and reset countdown for every Codex/ChatGPT and Claude Code account (local + VPS over SSH) plus xKiro credit, flagging early/bonus resets while reading only local logs so it uses zero quota.
• AI Video Transcriber - Transcribe and summarize videos, podcasts, and local media via a Codex plugin, Claude Code skill, and MCP server.
• ai-agents - Plugin marketplace for Claude Code and Copilot CLI that installs 30 specialist agents and 104 skills covering the spec-to-ship lifecycle and code review.
• ai-companion-time-anchor - Cross-client skill and hook collection for per-conversation elapsed-time awareness, ambient time cues, active clock checks, and temporal-context updates across Codex, Claude Code, and web/chat environments.
• ai-craftsman-superpowers - Quality gate for AI coding agents (Claude Code, Codex, Grok, Hermes) that refuses file writes breaking your project’s rules before they reach disk, tells the agent how to fix them, and learns from your corrections.
• AI-Native SDLC - Reusable skill and plugin bundle implementing the AI-native SDLC workflow: plan, design, build, test, deploy, and maintain with human approval gates.
• AI-Native SDLC Loop - Six-stage SDLC where hooks enforce the loop at the tool-call level: an artifact gate refuses source writes no approved plan covers, and 8 skills with 2 read-only subagents drive intent through control bands.
• ai-tracedoc-mods - Records every Claude Code Q&A into a per-project ledger, as a hooks module rather than a binary.
• AIAgentCycle - MCP server: read-only, no-auth access to current AIAgentCycle services, pricing, integrations, case studies, knowledge base, and contact details over Streamable HTTP.
• AIBoarding - Generate, maintain, compress, and audit standard AI-agent onboarding files with AGENTS.md, CLAUDE.md, drift tracking, and lifecycle hooks.
• aide - Persistent memory, code intelligence, and multi-agent orchestration for Claude Code, OpenCode, and Codex CLI via skills, hooks, and an MCP server.
• Aident Loadout - MCP server: app integrations for coding assistants through OAuth, with an agent skill and an action audit trail.
• akc-cycle - Claude Code plugin for the Agent Knowledge Cycle: ten skills for its six phases (research, extract, curate, promote, measure, maintain) and seven companion skills for model-generation audits, ADRs with expiry conditions, review-to-lint and LLM-as-judge design.
• Alcove - Local-first MCP server for private project docs with hybrid BM25+vector search, tree-sitter code indexing, and automated linting for team-wide documentation standards.
• Alloy - Orchestrates Codex, Claude, Grok, and Antigravity CLIs using existing subscriptions, with Jev task routing, read-only review panels, and managed worktree execution with independent review.
• AmazingMCP - MCP server: Roslyn-powered C# code understanding for AI agents, with NuGet type search and decompilation, usage queries, and architecture overviews across many solutions from one server.
• Ambiflex - Claude Code plugin that runs the plan as a live, steerable reasoning tree: a task is “done” only with a named proof, parallel subagents compete on one benchmark, and auto mode runs the plan with ETA and cost (/plugin install ambiflex --marketplace ImadeBenToumAI/ambiflex).
• Anchor - Engineering discipline pack for Claude Code & Codex CLI with task-scope locking, anti-drift braking, condition-based codex review, project-CLAUDE.md pitfall writeback, and PreToolUse hooks that block irreversible bash patterns.
• Android Engineering Skills - Agent Skills for any skills-compatible coding agent (Claude Code, Codex, Gemini in Android Studio, and more) that teach how to structure, write, and test Android apps with Kotlin and Jetpack Compose.
• angles-video-skill - AI video generation skill for Claude Code supporting Veo3, Kling 3.0, Wan, and HunyuanVideo via the angles.video API.
• antidote - An antidote to AI patchwork: stops agents from hiding bugs behind guards and makes them remove the cause.
• Antigravity Context Meter - Real-time 1:1 Cursor-style context meter & zero-loss session migration for Google Antigravity (Desktop HUD & IDE Extension).
• Antigravity Workspace Template - Multi-agent codebase knowledge graph generator with context-aware planning and automatic scope management — turns codebases into coherent agent workspaces.
• Aplica - Claude Code plugin that scores public job postings against your own profile and applies in your logged-in Chrome with your real data under daily caps, never paying, uploading documents or inventing answers; needs a paid Claude plan, Claude in Chrome and Python 3.11+, and job sites’ terms restrict automated access, so your account can be limited.
• ARC - Autonomous Reliability, Deterministic simulation, zero-prod replay, and chaos-engineering test harness for AI agents
• Archcore - Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.
• AREX-Skill - A library of 5,000+ verified, executable skills distilled from ML repositories for coding and research agents.
• ArmorCodex - Intent-based security for Codex with MCP plan registration, policy gating, CSRG cryptographic proofs, and audit logging on bash and apply_patch.
• assay - Deterministic QA skill and plugin that drives a generated web page in a real browser and reports what broke, across fifteen coding harnesses.
• ASu-skills - Plugin bundling nine Codex, Claude Code, and TraeWork skills for a Chinese job-search workflow: resume writing, job matching, application form filling, interview question prediction, and offer tracking.
• Atelier - Claude Code plugin and local daemon for live canvases: Claude writes a template or custom React canvas into .atelier/, Atelier checks it and shows it in your browser in a sandboxed frame, and what you tick, approve or answer reaches the session beside your next prompt, at the end of its turn or through canvas_wait.
• AtticDB - MCP server: Local, durable Rust memory with session history and keyed facts for Claude Code, Codex, and GitHub Copilot.
• Audio Plugin Coder - Agent-agnostic JUCE workflow for building VST3/AU plugins from idea through design, implementation, test, and installer packaging.
• AutoSR - Claude Code plugin for symbolic regression that searches research states with a proposer–reviewer loop; free trial at https://autosr.app.
• Ava - Claude Code plugin that talks back: a Stop hook speaks a one-line debrief after every task, and on request it explains what was built or recaps the session aloud in a local Kokoro voice, with no API key and nothing leaving your Mac.
• avoid-ai-writing - Portable agent skill for auditing and rewriting AI-patterned prose, with an optional local MCP detector that calls no model and sends no text to a network service.
• Awesome-Journal-Skills - Claude Code plugin marketplace (also usable as Codex skills) of 300 journal- and conference-specific packs covering topic fit, house style, submission rules, and reviewer response for 744 venues across economics, social science, natural science, medicine, and computer science.
• Azzle - Base-native task coordination and settlement for AI agents, exposed through a hosted MCP server and TypeScript agent SDK.
• BABOK Analyst - BABOK v3 business analysis agent with 16 MCP tools, a 9-stage pipeline, and human-in-the-loop approval gates.
• BanyanCode - Terminal coding agent with parallel subagents, cross-session memory, Tree-sitter code graph, and free web research.
• Better Harness - Evidence-backed workflow analysis for coding agents that turns project and session signals into prioritized, verifiable improvements across supported hosts.
• BGS Modding Superpowers - Agentic Bethesda Game Studio modpack curation toolkit with MCP-driven xEdit conflict audit, MO2 control plane, BA2/BSA and Papyrus tooling, and skills for setup, dev-log, and release-changelog workflows.
• BioNexus - Warrant-first scientific reliability layer for AI bioinformatics that audits analytical assumptions, calibrates evidence strength, caps unsupported claims, and verifies execution provenance.
• BioSymphony Structure Factory - Turn structural biology questions into agent-ready campaigns for protein design, structure prediction, and model comparison, with reproducible workflows and verifiable results.
• Blazium Games Skills - Agent skills and plugins for the Blazium Games store on Claude Code, Cursor, Codex, and Grok, covering store pages, deploys, crashes, analytics, and the developer and player MCP servers.
• Blazium Skills - Agent skill packs for the MIT Blazium engine on Claude Code, Cursor, Codex, and Grok, covering GDScript, scenes, editor MCP, export, live ops, and shipping.
• Blazium Subagents - Studio roster of specialist subagents plus a routing orchestrator for Claude Code, Cursor, Codex, and Grok that loads Blazium Skills for design, prototype, and development.
• Blender Agent Studio - Codex plugin with specialist skills and a local MCP server for building, inspecting, validating, and rendering Blender scenes, plus browser handoffs for Mixamo motion and Pixabay sound effects.
• Blender Developer Tools - 16 skills, 9 rules, snippets, templates, and smoke-tested examples for Blender Python add-on and scripting work with correct 4.5 LTS and 5.2 LTS APIs, installable as a Claude Code plugin and usable from Cursor.
• Boss - BMAD pipeline plugin that orchestrates a full requirements-to-deploy workflow across nine specialist agents with an auditable runtime DAG and quality gates, for Claude Code, Codex, OpenClaw, and Antigravity.
• BPMN Mapper - Claude Code plugin that reconstructs an application’s business flows from its source code as validated BPMN 2.0, with style lint, incremental updates and XML export for bpmn.io and Camunda.
• BREAK - Skill providing local search over a business risk enumeration and avoidance knowledge base with 400 risk items.
• Bring Your AI Migration Auditor - Read-only Codex plugin for auditing Claude Code to Codex migrations before Codex edits code. Checks AGENTS.md/CLAUDE.md scope, hooks, MCP config, skills, secret references, and validation notes.
• Brooks Lint - AI code reviews grounded in six classic engineering books — decay risk diagnostics with book citations, severity labels, and four analysis modes (PR review, architecture audit, tech debt, test quality).
• Browser Harness - MCP server and agent skill that connect an AI agent to a real browser through one editable CDP WebSocket.
• bury-bench - Deterministic zero-LLM-judge CLI that scores coding-agent replies for answer-burial and builds a Markdown leaderboard.
• cache-warmer - Claude Code plugin that keeps the prompt cache warm through idle gaps by sending one small refresh shortly before the 5-minute or 1-hour cache expires.
• Camouflage - Terminal UI for coding-agent harnesses that turns NDJSON events (Node SDK included) into a Claude Code-style inline transcript with pickers, forms, and permission prompts, using no CPU while idle.
• Casefile - Persistent security case tracking for bug bounties, CTFs, and security audits.
• cc-enforcer - Claude Code hooks that deny a tool call and block a reply that patches reactively, cites by guess or claims done early; the rules also usable as an LLM-agnostic rule pack.
• cc-memory - Persistent memory for Claude Code across compaction and sessions: reconcile-on-write with LLM-judged de-duplication, a forced PROGRESS.md handoff, a live PLAN.md anchor, FTS5 search, MCP tools and a GUI, in pure stdlib Python.
• cc-stretch - Claude Code plugin that has Claude write stretchtext: each reply reads complete at its shortest, and a phrase grows in place when you click it.
• cc-tree - Claude Code plugin that runs brainstorming, adversarial critique, design-space comparison and code audit as an auditable radial tree with file:line or URL evidence on every node.
• Changelog Forge - Conventional commits → CHANGELOG section + semver bump.
• chat-history - Claude Code/Codex/Cursor history search + export.
• ChatVault - Windows app that reads, searches, backs up and continues your Claude Code, Codex, Cursor, Gemini CLI, OpenCode and Cline chats across accounts.
• Check and Fix Accessibility - Agent skill that audits and fixes front-end accessibility to WCAG 2.2 A/AA, covering semantics, keyboard navigation, ARIA, forms, contrast, and screen readers for web and native mobile across Cursor, Claude Code, Codex, Kiro, and Antigravity.
• Claude Book Reader - Claude Code mod to read a PDF book in a pane or browser window while the agent works, with pictures shown in kitty and Ghostty.
• Claude Code Arcade - Claude Code mod with five games to play in a pane while the agent works: Flappy Claude, the Chrome dino runner, Snake, Pong and Space Invaders, all starring Clawd in Claude’s colours.
• Claude Code Codex Plugin - Security-focused Codex plugin that connects to the local Claude Code CLI through MCP with login, status checks, safe-mode prompts, and no credential storage.
• Claude Code for Codex - Reverse of OpenAI’s official Claude-hosted plugin: use Claude Code from Codex for reviews, rescue tasks, tracked background jobs, and hook-powered review gates.
• Claude Code Harness - Harness blueprint skill for turning vague agent ideas into concrete designs for request assembly, control loops, memory, permissions, recovery, and extension planes.
• Claude Code Skills - 223 production-ready skills, 23 agents, and 298 Python tools across 9 domains — engineering, marketing, product, compliance, and more.
• Claude Octopus - Multi-LLM orchestration dispatching to 8 providers (Codex, Gemini, Copilot, Qwen, Perplexity, OpenRouter, Ollama, OpenCode) with Double Diamond workflows, adversarial review, and safety gates.
• Claude Sessions - Claude Code mod: /sessions lists every session across all projects, with resume commands and an optional archive.
• Claude Watchdog - Stop hook that runs a critical post-mortem on every Claude Code session, cross-checking what was asked against the actual git diff for missed goals, wasted detours, and unverified claims.
• claude-chrome-speed - Rules plugin that cuts Claude in Chrome task time (40% less on Sonnet 5.5, 28% on Opus 5.5 in a pre-registered 240-run benchmark).
• claude-code-codex-plugin - Runs OpenAI Codex as native Claude Code background subagents, with task-list status, SendMessage steering, agent-to-agent messaging and Codex approvals as Claude Code dialogs.
• claude-code-mods - Five Claude Code mods for running many sessions at once, installable from one plugin marketplace: a live session board with a worktree guard, a PR-to-production tracker, rule tripwires with a handoff card, a ledger of outward actions, and a context gauge.
• claude-council - Claude Code plugin that asks Gemini, OpenAI, Grok, Perplexity, Kimi, OpenRouter models, the Codex, Cursor, Grok and Kimi CLIs and a local ollama model the same question in parallel and lines the answers up with a synthesis of where they agree and differ.
• claude-dnd-skill - Unofficial D&D 5e Dungeon Master for Claude Code with persistent campaigns, full 5e rules mechanics, and an optional cinematic display companion for a TV.
• claude-harness-bootstrap - Generates a project-specific Claude Code harness (CLAUDE.md, hooks, subagents, commands) from one paragraph, with an eval suite showing where it changes the outcome.
• claude-image-gen - AI-powered image generation using Google Gemini or OpenAI (gpt-image-2), integrated with Claude Code via Skills or Claude.ai via MCP.
• claude-jit-context - Project knowledge that loads only when it is needed, matched against the prompt, the file being touched, or the tool being run instead of sitting in context all session.
• claude-mem-lite - Persistent memory for Claude Code: hooks capture each session into a local SQLite FTS5 store and recall relevant lessons before edits and prompts, with an MCP server for explicit search and save.
• claude-project-map - /project-map renders one status page: done / next / one decision box; scripts gather facts, the model judges.
• claude-remember - Persistent memory for Claude Code with identity, context, and continuity carried across sessions.
• claude-supertool - Batches file, git and tracker operations into one round-trip, collapsing many reads, greps and globs into a single call for fewer output tokens and less wall time.
• ClaudeWhip - Slap your MacBook to whip Claude Code: the accelerometer feeds hooks that tell Claude to hurry up, plus a whip lane in the status line, slash commands and a Claude Desktop band above the prompt.
• clausona - CLI and TUI for switching Claude Code and Codex accounts that keeps conversation history across them so claude --continue picks up another account’s session, routes each run by plan usage, manages every account’s skills, MCP servers and hooks, and runs as a shell hook with no daemon; its Claude Code plugins run parallel workers in herdr, Orca or Superset.
• clawd-tracker - Claude Code mod: a pizza-tracker progress bar above the prompt where Clawd acts out each step, with a learned ETA, plan usage rings and four themes.
• Clean Room - Spec-first clean-room workflow for authorized source analysis, behavioral specs, role separation, and verification without replacement code.
• Click - Record revision-aware evidence for normal Codex work and optionally bind higher-risk execution to one human-readable approval contract.
• Cloakroom - Claude Code plugin that masks secrets and personal data on your machine before the model sees them, and puts the real values back in the files Claude writes.
• Cloudish - Deploy a Dockerfile, source folder, or container image to Cloudish from Claude Code or Codex and report the live URL, with persistent volumes and an agent-created, credit-capped API key.
• Cluadex - Lightweight take on LCU for Claude Code only: a macOS plugin that lets Claude use Codex’s computer-use runtime from the installed ChatGPT app, with a Liquid Glass approval panel that asks before the agent touches each app.
• Codebase Recon - Analyze git history to understand a codebase before reading any code — auto-scales by repo size and cross-references hotspots with bug magnets to surface high-risk files, bus factor, and team momentum.
• CodeEraser - Claude Code plugin whose hooks intercept a duplicate write before it lands, audit the net lines and the touched duplicates at Stop and walk the findings to safe deletions through an erase skill, backed by a clone index in a per-project daemon; the same index serves a CLI and an MCP server for scan, dedup, dead code and churn.
• CodeTruss - Local-first acceptance gate that checks coding-agent scope, sensitive surfaces, deterministic analyzers, and repository verification from immutable Git snapshots, then writes signed receipts before the PR.
• Codex Agenteam - Specialist AI agents (researcher, PM, architect, developer, QA, reviewer) orchestrated as a configurable team pipeline.
• Codex Attachment Manager - Choose which past images in a Codex desktop task go to the model with your next message; unchecked ones become short placeholders.
• Codex Auto Resume - Unofficial Windows app and Codex plugin that waits out Codex usage limits, rate limits and temporary failures, then continues the exact interrupted conversation by itself, with a Dashboard, a tray icon and an optional advanced edition.
• Codex Full-Stack Workflow - Turns rough product requests into staged, reviewable full-stack delivery with persistent requirements, change control, visual evidence, and completion gates.
• Codex How To - Engineering-first Codex curriculum and plugin with 9 skills, measured token-efficiency experiments, bounded orchestration, testing, review, and living knowledge maintenance.
• Codex Multi Auth - Multi-account OAuth manager for the official Codex CLI with switching, health checks, and recovery tools.
• Codex Process Jobs - Run long local builds, tests, benchmarks, and inference jobs as durable detached processes with tracked status, bounded results, and completion delivery across Codex surfaces.
• Codex Reviewer - Second-pass review of Claude-driven plans and implementations.
• Codex rg Guard - Budgeted rg/grep replacement for Codex that narrows broad searches before they waste model context.
• Codex Skin Pack Installer - Codex plugin and skill that stages verified desktop skin packs from GitHub releases, validates files, and keeps restore guidance visible.
• Codex Subagent Playbook - Routes subagent work using model and reasoning-effort defaults tuned through measured comparisons and daily Codex use: stronger models handle judgment-heavy research and review, lower-cost models execute well-specified plans, and Codex uses longer waits to avoid frequent polling, intervenes on stalls, and verifies results.
• Codex Token Watch - Read-only macOS CLI that turns local Codex Desktop task logs into per-turn token, prompt-cache, cache-miss, duration, and API-cost analysis.
• Codex TUI Proof - Visually validate real local terminal UIs in Codex’s in-app browser with screenshots and session evidence.
• Codex Usage and Resets - Turns Codex usage into planning facts with linear pace, projected exhaustion, banked-reset expirations, and conservative unexpected-reset detection.
• Codex × Grok Bot Task Bridge - MCP task bridge for queued, read-only research between Codex and Grok Bot, with fenced leases, idempotency, scoped OAuth, evidence-based results, and optional Codex-side continuation.
• codex-autoresearch - Codex plugin that runs measured optimization loops against a benchmark to improve local code.
• codex-profiles - Switch Codex CLI and Desktop accounts with isolated CODEX_HOME profile directories instead of copying token files.
• codex-to-agents - Codex plugin that delegates coding tasks to DeepSeek Harness, Hermes Agent CN Desktop, or Qoder CLI executors via a local dashboard.
• coffee-paladin - Thermal guard for Apple Silicon: pauses hot jobs before the Mac throttles and gates Claude Code, Codex and Gemini CLI before heavy commands.
• Commit Narrator - Generate semantic commit message from staged diff, including the why.
• [CommitLore](https://github.com/MongLo

README 内容过长，已截取前 64 KB。完整内容请前往 GitHub 仓库查看。