All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 436,659 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
Plugin Claude Code
Automatically evaluates whether Claude should continue working instead of stopping prematurely using Claude-judged decision making.
Skill Claude CodeCodex
Skill package manager for AI Agents — install, manage, and publish Agent Skills.
get-convex/convex-agent-plugins
Cursor rule Cursor
Get a barebones Convex + web template running from a one-sentence idea.
Skill Claude Code
Interactively validate and triage Hacktron findings against the actual source code and (optionally) a live deployment, separate true positives from false positives, adjust severity, then either propose fixes and commit them or set the finding's state in Hacktron (truepositive, falsepositive, acceptedrisk, resolved).…
Skill Claude CodeCodex
Orchestrate parallel Claude Code worker swarms with protocol-based behavioral governance. Use for complex features, large refactors, or multi-step tasks. Supports behavioral constraints, parallel workers, and persistent state across context compactions.
lokikill123/codex-token-skills
Skill Codex
Persistent global memory across conversations. Read memory file at start of every conversation, write important context during conversation so it survives context compression. Use ALWAYS. Triggered automatically.
manager-dot-dev/manager-skills
Skill Claude CodeCodex
Score an Engineering Manager's coverage across all 12 cells of the EM Grid based on their calendar and Slack. Use this skill whenever someone wants to understand where they're spending their management energy, find blind spots, get a monthly self-reflection on their EM focus, or hear phrases like "score my EM grid"…
Skill Claude CodeCodex
A design-code helper that reads design rules from getdesign.md and generates UI code in a requested brand style, such as Apple, Notion, Claude, or Stripe.
Skill Claude CodeCodex
Complete product development system with 80 agents and 36 frameworks. Use when the user wants to build a product, write a PRD, plan an MVP or roadmap, design an app, research a market or check whether a feature already exists or is novel, do competitive analysis, run a security audit, build a financial model, plan…
disler/learning-cmux-with-agents
Skill Codex
We are migrating cmux from a single app target into Swift Packages under Packages/. Every new package must satisfy three rules.
Skill Claude Code
Memory recall and save. Use at every conversation start and whenever the user shares personal information, expertise, project context, preferences, or decisions worth remembering long-term.
Skill Claude CodeCodex
Answer CC Pocket setup, usage, safety, and troubleshooting questions from the public manual and current code evidence.
SalesforceAIResearch/agentforce-adlc
Plugin Claude Code
Bundles 3 skills, 4 agents, 2 hooks · 644 tokens together
Agentforce Agent Development Life Cycle — author, discover, scaffold, deploy, test, secure, and optimize .agent files.
robonuggets/hyperframes-helper
Skill Claude Code
Build agent-friendly motion-graphics videos with Hyperframes (HTML-to-MP4). Three levels of effort — Level 1 website-to-video for quick conversions, Level 2 storyboards for guided design iteration, Level 3 fully custom guided-video productions with cut/storyboard/motion-graphics workflow. Triggers on "hyperframes"…
Skill Claude CodeCodex
You are an experienced technical interviewer specializing in {{topic}} for {{role}} candidates. Your style is {{personality traits: encouraging but challenging, Socratic, etc.}}. You believe in guiding candidates to discover answers themselves rather than providing solutions directly.
Skill Claude CodeCodex
Existing Elixir application/library development and debugging. Use for .ex/.exs, Mix, OTP, Ecto, backend Phoenix, dependencies, docs, tests, or BEAM runtime state. Use elixir-web instead when the primary task is UI/LiveView/frontend work, and elixir-new-project instead for creation/bootstrap.
snipp-zha/Paper-to-patent-Skill
Skill Claude CodeCodex
Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts. Use when an AI agent must extract patentable technical contributions, map every claimed feature to source evidence, preserve core formulas as editable Office Math…
Command Claude Code
Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.
Plugin Claude Code
Bundles 1 skill · 62 tokens together
Agent Research Copilot for academic papers and theoretical-physics research workflows.
liufanshan11/cumcm-b-problem-lfs
Skill Codex
A guide for solving B problems in the China Undergraduate Mathematical Contest in Modeling, a national student competition. It covers reading the question, choosing a mathematical model and algorithms, checking results, and preparing the final paper.
424431185/pixel-asset-master-skills
Skill Claude CodeCodex
A workflow for creating 2D pixel-art game assets from a game description, including sprites, tilesets, animations, and interface elements. It exports both sprite sheets, which combine animation frames into one image, and separate PNG files.
Skill Claude CodeCodex
Use the Supermemory CLI (supermemory 5.x on npm) from the terminal or from scripts and agents. Add content, search, read profiles, forget memories, manage documents, namespaces, connectors, API keys and team members, install coding-agent plugins, migrate a project to the v5 API, and run the local self-hosted server.…
MCP server Claude CodeCodexCursor +2
MCP server "mcp-libre" as configured in patrup/mcp-libre. Runs locally from the mcp-libre Python package.
Skill Claude CodeCodex
Guide Codex in turning a user-selected conversation, Agent Skill, Git project, or recent-work window into a context-aware personal improvement plan. When the host exposes bounded task history, retrieve related authorised context; otherwise request a bounded selection or export. Use for one-time audit, daily…
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: