ai-agents plugins

3,207 tagged ai-agents, measured the same way as everything else here.

Browse within: agentic-ai 238claude-code-plugin 220LLM 186cli 140agents 131agents-md 109prompt-engineering 108Science 99ai-coding 79ai-tools 69agentic-coding 61skills 59mcp-server 55agent-orchestration 51

analytics-office

914

debabsah/analytics-office

Plugin Claude Code

Bundles 19 skills · 3,736 tokens together

A discipline harness for AI-assisted analytics, a bench of skills that grows by accretion — each read-only, all writing to one living knowledge base you (or the next agent) resume from. Skills:'groundwork' (orient on an inherited estate and build a living knowledge base), 'requirements-interrogator' (drive a…

not rated 9 2mo ago A tokens not measured original MIT

yolo

917

CoriChui/yolo

Plugin Claude Code

Bundles 11 skills, 1 command · 799 tokens together

Reasoning-first, feature-aware development workflow for Claude Code. Git is the source of truth; status is derived, never stored. Turns 'I want X' into a planned, executed, verified, and landed change through eleven yolo- skills Claude routes to from plain intent.

not rated 9 2mo ago A tokens not measured original MIT

john

918

kitchen-engineer42/joharnessburg

Plugin Claude Code

Bundles 28 skills, 5 commands, 5 agents, 3 hooks · 3,337 tokens together

John — a Claude Code and Codex harness for building knowledge-dense apps. Wraps the agent with skills, hooks, commands, and a small toolkit so it can take unstructured input through knowledge phases (knowledge engineering) and app phases (app building) in one long-running session; includes a deterministic…

not rated 9 2mo ago A tokens not measured original MIT

pluribus

919

johnnyjoy/pluribus

Plugin Claude Code

Bundles 6 skills, 1 agent, 3 hooks, 1 MCP server · 281 tokens together

First-party Pluribus memory loop for Claude Code: MCP, hooks (session wake-up + prompt recall, optional failure hint), skills, and a recall-first investigator agent. Server owns memory; plugin orchestrates.

not rated 9 2mo ago A tokens not measured

glasses

921

DanielGouveiah/glasses

Plugin Claude Code

Bundles 3 skills, 2 hooks · 216 tokens together

Evidence-first planning, diagnosis, technical research, and documentation capture for AI coding agents.

not rated 9 19d ago A tokens not measured original MIT

gitmem-hooks

923

gitmem-dev/gitmem

Plugin Claude Code

Bundles 1 command, 5 hooks · 12 tokens together

Enforces the GitMem institutional memory lifecycle through hooks — auto-starts sessions, reminds you to recall before consequential actions, and ensures proper session closure.

not rated 9 1mo ago A tokens not measured original MIT

spec-workflow

925

AnExiledDev/CodeForge

Plugin Claude Code

Bundles 1 skill · 113 tokens together

Specification lifecycle management with directory-based spec packages: /spec (create & refine), /build (implement & close), /specs (dashboard).

not rated 9 1mo ago A tokens not measured

shor

927

tr4m0ryp/shor

Plugin Claude Code

Bundles 1 skill · 0 tokens together

Shor — autonomous AI web pentester. Provides the /shor-setup slash-command: an interactive wizard that guides you from zero to a running scan (black-box or white-box, GCP deployment included).

not rated 9 1mo ago A tokens not measured

notion-memory

929

MSApps-Mobile/claude-plugins

Plugin Claude Code

Bundles 5 skills · 197 tokens together

Long-term memory for Claude across sessions via Notion — plus the 4 official Anthropic Notion skills (knowledge-capture, meeting-intelligence, research-documentation, spec-to-implementation) bundled in.

not rated 9 13d ago A tokens not measured original MIT

agent-workflows

930

sjarmak/agent-workflows

Plugin Claude Code

Bundles 28 skills, 4 agents, 4 hooks · 314 tokens together

Multi-agent workflow patterns for Claude Code. Skills for brainstorming, research, debate, prototyping, risk analysis, stress testing, and build planning. Includes hooks for auto-formatting, diff-aware scoping, guard rails, worktree setup, notifications, and verification.

not rated 9 1mo ago A tokens not measured original MIT

loctree

932

Loctree/loctree

Plugin Claude Code

Bundles 10 skills, 3 agents, 2 MCP servers · 2,073 tokens together

CANONICAL loctree agent plugin (suite). Structural perception — slice before edit, impact before delete, find before create (incl. multi-literal OR A|B on MCP/LSP/CLI), prism before vc-polarize. Powered by loctree-mcp + loctree-lsp. Deprecated peer path: suite ./plugin/ (redirect only).

not rated 9 5d ago A tokens not measured

coinlobster

933

CoinLobster/agent-skills

Plugin Claude Code

Bundles 6 skills, 1 MCP server · 809 tokens together

Live crypto whale trades across 15 exchanges plus Ethereum/Base/Arbitrum DEX swaps, Smart Money Radar, liquidations from the venues that publish them, and market snapshots. Six analysis skills plus the hosted MCP server, no API key required.

not rated 9 +1 26d ago A tokens not measured original MIT

robium

934

robium-ai/robium

Plugin Claude Code

Bundles 70 skills, 1 agent, 6 hooks · 7,932 tokens together

Self-improving robotics expertise for AI agents: skills for architecting, integrating, simulating, visualizing, testing, and training physical-AI applications (ROS 2, Nav2, Gazebo, LeRobot, Isaac, HuggingFace) — captured from real builds, mined from the ecosystem, evidence-verified.

not rated 9 yesterday A tokens not measured original MIT

multi

935

szarkans/multi

Plugin Claude Code

Bundles 6 skills, 5 agents · 734 tokens together

Several models on the same question at once — Claude sub-agents, OpenAI Codex and a cheap third via OpenCode. Review code (code-review), check whether the work is actually finished rather than finished-looking (check-if-done), brainstorm wide with a different model per cognitive frame (adhd), or just ask all of t.

not rated 9 +1 changed yesterday A tokens not measured original MIT

mora

936

pyranthus-hq/mora

Plugin Claude Code

Bundles 4 skills · 229 tokens together

Portable workflows for retrieving and safely using Mora memory through its local MCP server.

not rated 9 +1 3d ago A tokens not measured original Apache-2.0

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: