ai-agents plugins

3,203 tagged ai-agents, measured the same way as everything else here.

Browse within: agentic-ai 239claude-code-plugin 222LLM 186cli 139agents 126agents-md 108prompt-engineering 108Science 99ai-coding 75agentic-coding 65ai-tools 64skills 59mcp-server 53agent-orchestration 52

sandy-cli

1036

jamestelfer/sandy

Plugin Claude Code

Bundles 1 skill · 54 tokens together

Sandy: sandboxed TypeScript execution for AWS queries via the sandy CLI.

not rated 7 1mo ago A tokens not measured original Apache-2.0

formio-ai

1039

formio/ai

Plugin Claude Code

Bundles 16 skills · 3,639 tokens together

Form.io MCP server + skill library. Bundles the Form.io MCP server and a skill library covering every endpoint in the Form.io API, plus form JSON schema guidance for generating and editing Form.io forms and resources.

not rated 7 changed 5d ago A tokens not measured original MIT

ai-skills marketplace

1040

Amey-Thakur/AI-SKILLS

Plugin Claude Code

Plugin marketplace listing 68 plugins: accessibility-skills, ai-coding-tools-skills, ai-memory-rag-skills, api-integration-skills, apis-skills.

not rated 7 3d ago A tokens not measured original MIT

claude-core

1041

BjornMelin/dev-skills

Plugin Claude Code

Bundles 4 skills · 379 tokens together

Claude-Code-native orchestration skills: subagent fan-out, custom-agent authoring, PR review-thread resolution, and complexity/perf hotspot optimization. Opus-first, Task- and Workflow-aware replacements for Codex-coupled originals.

not rated 7 +1 yesterday A tokens not measured

developer-skills

1042

sgomez/developer-skills

Plugin Claude Code

Bundles 5 skills, 3 agents, 1 hook · 671 tokens together

Unattended spec delivery pipeline: /developer loops over a spec's sub-issues with dispatcher → code-author → diff-reviewer workers, review→fix cycles, and a configurable merge policy (auto or hand-off), with parallel or sequential execution.

not rated 7 +1 changed 6d ago A tokens not measured EUPL-1.2

webmcpify

1043

TueJon/webmcpify

Plugin Claude Code

Bundles 1 skill · 64 tokens together

WebMCP agent skill for curated core coverage or route-by-route parity — inventory an existing web app, integrate approved tools, then verify and heal them in a real browser.

not rated 7 yesterday A tokens not measured original MIT

eterdis-culture

1044

eterdis/strategy-skills

Plugin Claude Code

Bundles 1 skill · 127 tokens together

Culture assessment — surface the gap between declared culture and actual culture. Three modes: Diagnostic, Review, Alert Triggers.

not rated 7 5mo ago A tokens not measured

programasweights

1045

programasweights/skills

Plugin Claude Code

Bundles 1 skill · 215 tokens together

Compile a natural-language spec into a tiny neural function that runs locally - classification, extraction, format repair, fuzzy matching, log triage, and routing.

not rated 7 +1 2mo ago A tokens not measured original MIT

core-memory-kit

1046

LH8PPL/core-memory-kit

Plugin Claude Code

Bundles 4 skills, 8 hooks · 635 tokens together

Per-project in-repo memory system for Claude Code. Frozen-snapshot session loads, auto-extract Stop hook, memory-write + memory-search + troubleshooting skills, keyword search, optional auto-curation crons.

not rated 7 5d ago A tokens not measured original MIT

collate

1048

MidnightDarling/collate

Plugin Claude Code

Bundles 15 skills, 2 commands, 2 agents · 2,286 tokens together

A plugin that provides an end-to-end workflow for OCR and proofreading historical Chinese documents. OCR turns scanned page images into editable text.

not rated 7 +1 3mo ago A tokens not measured original Apache-2.0

doc-bridge

1050

AgentsKit-io/doc-bridge

Plugin Claude Code

Bundles 1 skill, 2 MCP servers · 14 tokens together

Fail closed before Claude edits the wrong files: resolve the right docs, ownership boundaries, edit roots, and checks for each change.

not rated 7 7d ago A tokens not measured original MIT

vd

1051

vanducng/skills

Plugin Claude Code

Bundles 80 skills, 14 agents · 12,040 tokens together

A daily-driver collection of skills for agentic coding, namespaced under vd: to avoid conflicts with other plugins.

not rated 7 changed 5d ago A tokens not measured original MIT

email-cleaner

1052

EveryInc/garbage-man

Plugin Claude Code

Bundles 1 skill · 84 tokens together

Provider-neutral email review and future-mail cleanup for AI agents.

not rated 7 +2 1mo ago A tokens not measured original MIT

shiploop

1053

anshss/shiploop

Plugin Claude Code

Bundles 2 skills, 7 commands, 3 agents · 227 tokens together

Self-improving multi-agent harness that dispatches the tickets you name across every repo in your product — guarded auto-merge on green CI, and every resolved ticket writes a lesson into your git-tracked CLAUDE.md. Every ticket starts on a cheap tier and escalates once, on measured failure, instead of being predicted…

not rated 7 +1 changed today A tokens not measured original Apache-2.0

meteor

1054

meteor/agent-skills

Plugin Claude Code

Bundles 19 skills · 2,367 tokens together

Build, migrate, debug, test, secure, and deploy Meteor 3 applications.

not rated 7 changed today A tokens not measured original MIT

sessionwiki

1055

youdie006/sessionwiki

Plugin Claude Code

Bundles 1 skill, 1 command, 1 hook · 135 tokens together

Recall and reuse your past AI coding sessions as long-term memory. Searches the local sessionwiki index so the agent can find prior work, pull context, and trace which session wrote a file.

not rated 7 +1 yesterday A tokens not measured original MIT

at

1056

patforna/auto-task

Plugin Claude Code

Bundles 13 skills · 539 tokens together

An opinionated set of AI-agent skills to automate a large slice of the software development lifecycle including planning, implementation, review, and shipping.

not rated 7 +4 yesterday A tokens not measured original MIT

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: