Official
Official Pinecone plugin: an agent creates indexes, searches them, builds a RAG assistant and cites your files.
Plugins
A plugin is a ready-made bundle for an agent: a set of commands, skills and settings installed in one step. This section collects plugins for Claude Code and compatible agents, with a description of what is inside, an install command and an access level.
Match with Foxx AI
Describe the task or paste package.json, and Foxx AI will pick matching skills, MCP servers and CLI tools.
Found: 1603
lessloc uses hooks to keep an agent to the least code: it refuses placeholders and junk and sends unfinished work back
A library of 31 manipulation skills and 8 tool bundles for the GaP robotics engine in the Agent Skills format.
A Claude Code plugin for phased project execution: planning, parallel agents with TDD, security and quality gates, then shipping.
Official Mobbin skills: search real app screens and flows and redesign a screen grounded in them, plus the Mobbin MCP server.
A plugin for Codex and Claude Code that explains Rust by syntax and rationale, sets exercises and saves PR reviews as Markdown.
A prompt rail for Claude Code: hover to read a prompt, click to jump back, with three layouts and commands
A skill set for agent UI work: scope, restraint and motion rules plus checks of the result in the live app
A local researcher workspace for papers, evidence and drafts in one project, with AI proposals that people review and approve.
An Emacs package for Claude Code: per-project sessions and an MCP server exposing buffers, LSP and diffs to the agent.
A Claude Code and Codex handoff plugin: a clean session with decisions and tasks kept, or history moved to the other client.
A Hermes plugin and OpenClaw skill: memory over Obsidian and markdown notes through a concept graph and local semantic search
Mempalace keeps Claude Code and Codex memory in local SQLite with no Python or API keys, as a single binary of about 13 MB.
Skills and the porch CLI for agent orchestration: a strong model plans, cheaper ones code, several model families review.
DoneWhen keeps agent work in tickets with checklists and MCP: the server will not close a ticket while any checklist item is open
A Claude Code plugin for development with separated roles: spec, review, TDD, QA and verification by different agents
Two skills for micro-frontend architecture: eight boundary rules from the O'Reilly book, violation detection and fixes
The kairos plugin and the cdd engine carry a code change from design to close in small verifiable steps with review.
Skills from an idea to proven results: a spec, building and verifying a PR and a verification skill for your app.
herdr-agent-usage (senna-lang)
herdr-agent-usage
A Herdr plugin with a limits pane: context fill, prompt cache and remaining subscription allowance for each agent.
A DeepSeek Harness plugin with a skill on plugin quality: three layers ENTRY, FLOW and BOOST, with checks routed to dsh-standards.
A Google Antigravity template: the BMad method with a pinned version, an orchestrator plugin and a Russian or English preset
Liuyao divination skills for agents: casting by coins, hexagram layout and a reading under school rules with limited conclusions.
Ten software lifecycle skills for Claude Code: requirements, design, tests, adversarial review and release checks with hooks.