ai-agents plugins

3,284 tagged ai-agents, measured the same way as everything else here.

Browse within: agentic-ai 237claude-code-plugin 217LLM 191cli 134agents 128prompt-engineering 111agents-md 107Science 99ai-coding 80agentic-coding 63ai-tools 60skills 60ai-governance 54claude-plugins 53

deep-research

1346

Hayes-Zhang/deep-research

Plugin Claude Code

Bundles 1 command, 8 agents · 290 tokens together

A 7-perspective Agent Team + adversarial critic for Claude Code: 7 researchers (Product, UX, Tech, Practice, Academic, History, Social) run in parallel; the critic traces primary sources and tags per-finding confidence; the team lead synthesizes one HTML + Markdown + Notion report.

not rated 4 3mo ago A tokens not measured original MIT

hubspot

1347

promptmetrics/hubspot-claude

Plugin Claude Code

Bundles 1 skill, 1 hook · 64 tokens together

HubSpot CRM administration via natural language — specialist sub-agents, human-in-the-loop write approval, and a warm-client daemon.

not rated 4 6d ago A tokens not measured original MIT

devloop

1349

compforge/devloop

Plugin Claude Code

Bundles 7 skills, 3 commands, 9 hooks · 513 tokens together

TypeScript dev-loop runtime with shared Board and policy: git/PR (GitHub + GitLab), cwd-aware context, lint/test gates, and thin Claude Code hooks.

not rated 4 changed today A tokens not measured

neuraforge-ai

1350

vikisingh23/neuraforge-ai

Plugin Claude Code

Bundles 38 skills, 22 MCP servers · 768 tokens together

AI-powered development platform — 24 agents, 19 MCP servers, 21 skills for end-to-end software development across React, React Native, Flutter, .NET, and NestJS.

not rated 4 3mo ago A tokens not measured original Apache-2.0

kyzo-plan

1351

kyzodb/plan

Plugin Claude Code

Bundles 5 skills, 3 agents, 1 hook, 1 MCP server · 385 tokens together

A GitHub Projects work board as typed MCP tools: pure reads (readboardstatus, readcolumn, ...), gated epic/story lifecycle (startepic, startstory, finishepic), free column moves, and authoring verbs — plus the kyzo-plan-manage-board skill that carries the operating model.

not rated 4 2mo ago A tokens not measured

deep-ass-research

1352

Kaos599/Deep-Ass-Research

Plugin Claude Code

Bundles 1 command, 7 agents · 144 tokens together

Deep Ass Research (DAR) — deep, multi-source, primary-sourced research into a backlinked Obsidian vault: fan-out scout/diver subagents, adversarial verification, and a synthesized Map-of-Content + report.

not rated 4 1mo ago A tokens not measured original MIT

mantle

1353

aotter/mantle

Plugin Claude Code

Bundles 8 skills · 274 tokens together

Build and embed Mantle applications with version-matched Core skills and deterministic examples.

not rated 4 changed 5d ago A tokens not measured original Apache-2.0

code-reviewer

1355

techgangboss/agentstore

Plugin Claude Code

Bundles 1 skill · 70 tokens together

AI-powered code review that analyzes your code for bugs, security issues, and best practices.

not rated 4 7mo ago A tokens not measured original MIT

mnema

1356

felipesauer/mnema

Plugin Claude Code

Bundles 1 hook

Puts the project's committed mnema record into the session's opening context without the agent asking, and connects the mnema MCP server so it can record its own work.

not rated 4 changed 2d ago A tokens not measured original MIT

ai-crew-sync

1357

joaquinbejar/ai-crew-sync

Plugin Claude Code

Bundles 1 skill, 4 commands, 3 hooks · 109 tokens together

Your team's coordination bus: shared channels and DMs between teammates' AI coding agents, task claims with leases and dependencies, presence, shared notes, resource locks and real-time wakeups. Requires BUSURL and BUSTOKEN in the environment.

not rated 4 1mo ago A tokens not measured original MIT

belmont

1360

blake-simpson/belmont

Plugin Claude Code

Bundles 17 skills · 458 tokens together

Structured AI coding sessions with PRD-driven planning, implementation, and verification.

not rated 4 25d ago A tokens not measured original Apache-2.0

piratebao

1361

d4551/piratebao

Plugin Claude Code

Bundles 5 skills, 5 commands · 459 tokens together

Kraken-compressed PirateBao communication mode. Cuts 77% average tokens (committed eval gate) while keeping complete technical accuracy.

not rated 4 1mo ago A tokens not measured original MIT

prompt-pocket

1362

lxb12123/prompt-pocket

Plugin Claude Code

Bundles 1 skill, 1 command, 1 hook · 169 tokens together

Cross-agent prompt pocket: remember your most-used prompts and pick one to run; auto-scans Claude Code, Codex and OpenCode sessions to record prompts repeated 7+ times. Forged by agent-plugin-kit.

not rated 4 2mo ago A tokens not measured original MIT

actual-cli

1363

actual-software/actual-skill

Plugin Claude Code

Bundles 1 skill, 2 hooks · 157 tokens together

Feature-complete companion for the actual CLI — runs and troubleshoots sync, status, auth, config, runners, and models across all 5 runners and 3 output formats, and gates implementation plans against the ADR rules committed in .actual/rules/.

not rated 4 changed 8d ago A tokens not measured original Apache-2.0

aimhooman

1364

rmyndharis/aimhooman

Plugin Claude Code

Bundles 1 skill, 2 hooks · 106 tokens together

AI works. Hoomans ship. Keeps AI session files and unwanted attribution out at the agent and Git boundary.

not rated 4 1mo ago A tokens not measured original MIT

10x-analyst

1367

OpenAnalystInc/10x-analyst

Plugin Claude Code

Bundles 7 skills · 124 tokens together

Agentic data analysis swarm — ingest, clean, profile, analyze, visualize, report, and build interactive dashboards from CSV/Excel/JSON data. A multi-agent pipeline with specialized data-engineer, statistician, visualizer, reporter, and strategist agents coordinated by an orchestrator.

not rated 4 6mo ago A tokens not measured

googlecloud-plugin

1368

jpantsjoha/googlecloud-plugin

Plugin Claude Code

Bundles 17 skills, 2 MCP servers · 1,864 tokens together

A full Google Cloud delivery team for your coding agent: vendor-objective solution designer, GCP architect, agentic-systems architect (ADK / Agent Runtime / MCP / A2A / AP2), plus security, SRE, and QA — wired into a design-first, security-first delivery gate. Eleven service skills (Cloud Run, GKE, IAM, BigQuery…

not rated 4 1mo ago 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: