ai-agents plugins

3,236 tagged ai-agents, measured the same way as everything else here.

Browse within: agentic-ai 240claude-code-plugin 222LLM 186cli 138agents 126agents-md 108prompt-engineering 108Science 99ai-coding 72agentic-coding 65ai-tools 65skills 60mcp-server 53agent-orchestration 50

auto-itera

1105

clfhaha1234/auto-itera

Plugin Claude Code

Bundles 1 skill · 114 tokens together

Autonomous experimentation engine for AI engineering decisions. Define a goal + candidates + threshold, get a defensible ship-or-kill verdict in hours — sealed held-out test, pre-registered metric, sprint-and-generalize iteration.

not rated 6 3mo ago A tokens not measured original MIT

deckhand

1106

jonthebeef/deckhand

Plugin Claude Code

Bundles 2 skills · 345 tokens together

Drive a GitHub Projects v2 kanban board end to end. Two skills: plan the backlog (epics, sub-issues, board hygiene), then run tickets through implement, isolated adversarial review, fix-loop, and merge.

not rated 6 2mo ago A tokens not measured original MIT

okteto

1107

okteto/okteto-agent-skills

Plugin Claude Code

Bundles 4 skills, 2 commands, 2 hooks · 490 tokens together

Okteto development environment skills for AI agents. Teaches agents how to deploy, develop, debug, and test in Okteto environments — both collaboratively with developers and autonomously in CI/ticket-driven workflows.

not rated 6 8d ago A tokens not measured original Apache-2.0

skanna

1108

proluct/skanna

Plugin Claude Code

Bundles 3 skills, 1 hook · 205 tokens together

Security-scan a Claude Code skill, plugin, or MCP server before installing it. SAFE / CAUTION / DANGEROUS verdict with file:line findings. Read-only, never executes the target.

not rated 6 1mo ago A tokens not measured original MIT

ai-agents-skills

1109

Xakki/ai-agents-skills

Plugin Claude Code

Bundles 23 skills, 3 agents, 6 hooks · 2,103 tokens together

Skills + hooks for Claude Code: teamlead (main thread as team-lead: delegate code work to subagents, surface only decisions), roadmap (plan & autonomously build a whole app phase-by-phase), kanban (manage a .claude/kanban board), schedule-tasks (auto-pilot todo cards via at/tmux), git-flow (shared git core: commits.

not rated 6 19d ago A tokens not measured original MIT

sumo-qa

1112

sumithr/sumo-qa

Plugin Claude Code

Bundles 20 skills, 2 agents, 3 hooks, 1 MCP server · 2,022 tokens together

Sumo QA — a senior-QA-shaped MCP server for pre-coding QA planning, TDD scaffolding, mutation-testing follow-up, code review, and test-data discovery.

not rated 6 changed today A tokens not measured original Apache-2.0

fde-platform

1114

rpraharaj/forward-deployed-engineer

Plugin Claude Code

Bundles 3 skills · 317 tokens together

FDE archetype pack for integration and vendor-platform engagements: contract design, adapters against undocumented interfaces, and COTS configuration.

not rated 6 +1 23d ago A tokens not measured original MIT

taste-skill-zh-CN

1115

Hayatelin/taste-skill-zh-CN

Plugin Claude Code

Bundles 13 skills · 1,366 tokens together

A Chinese-language design guide for making AI-generated interfaces look more intentionally designed. It covers layout, typography, animation, and spacing.

not rated 6 +1 1mo ago A tokens not measured

consolidate-memory

1116

Zenetusken/consolidate-memory

Plugin Claude Code

Bundles 1 skill, 8 commands, 1 hook · 424 tokens together

Cross-project, verification-first memory for Claude Code — the layer beyond the built-in Auto Dream. Shares memory across enrolled projects in the same trust domain (a governed store, replicated into those projects) and verifies facts against the live code (grep/file/git), dropping what it can't confirm — fact-checked.

not rated 6 changed 2d ago A tokens not measured original MIT

verefi

1117

philchen00/verefi

Plugin Claude Code

Bundles 5 skills · 324 tokens together

AI-assisted pipeline that turns product specs into human-reviewed test plans and executable Playwright automation.

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

growth-os

1119

nocodework/growth-os

Plugin Claude Code

Bundles 8 skills · 837 tokens together

The open-source Growth OS for any AI agent. Point it at a business URL, extract USP/UVP/ICP into a persistent context file, run a growth audit (SEO, page speed, GEO/AI-visibility, competitors, live GA4/GSC baseline), then delegate to atomic marketing skills.

not rated 6 2mo ago A tokens not measured original MIT

scuttlepay

1120

jarrodwatts/scuttlepay

Plugin Claude Code

Bundles 1 skill · 100 tokens together

Interact with the ScuttlePay API to manage wallets, search products, make purchases, and view transactions using USDC on Base.

not rated 6 6mo ago A tokens not measured original MIT

pptx-plugin

1121

martgueritainaccurate875/skills

Plugin Claude Code

Bundles 5 skills, 5 agents · 315 tokens together

PowerPoint generation and editing plugin with text-only QA (no vision required). Uses subagents for cover, TOC, content, section dividers, summary slides, and template-based PPT editing workflows.

not rated 6 +1 yesterday A tokens not measured copy · 100% MIT

dev-flow

1122

lukedj78/dev-flow

Plugin Claude Code

Bundles 47 skills · 8,945 tokens together

An end-to-end product-development skill suite: one filesystem contract (.workflow/meta.json) and 43 skills that take an idea to production — web (Next.js 16), mobile (Expo/RN), an eve agent engine, Linear/scrum, plus GDPR/AI-Act and Vercel-cost pre-deploy gates.

not rated 6 changed yesterday A tokens not measured original MIT

intent-outreach

1124

jeremylongshore/intent-outreach

Plugin Claude Code

Bundles 4 skills, 3 agents, 2 hooks, 1 MCP server · 663 tokens together

Model-agnostic, Claude-Code-native SDR orchestrator: research → enrich → outreach over your own data-provider keys, fully local, with your own model. Built for technical founders who do their own outbound. An orchestrator skill dispatches phase sub-agents (research → enrich → draft) over a bundled MCP server that…

not rated 6 today A tokens not measured

hermeneutic-gate

1125

hermes-labs-ai/hermeneutic

Plugin Claude Code

Bundles 1 hook

Legacy advisory Stop-hook bundle for the fixed English gate. Current Claude Stop compatibility is not certified in v0.1.7; use the CLI directly. Requires the hermeneutic package.

not rated 6 +1 today A tokens not measured original Apache-2.0

postey-analytics

1126

posteyai/skills

Plugin Claude Code

Bundles 1 skill · 48 tokens together

Read what a post or account actually did and turn it into the next content decision.

not rated 6 +1 5d ago A tokens not measured original MIT

multi-model-team

1127

WatchAndyTW/multi-model-team

Plugin Claude Code

Bundles 3 commands, 4 agents · 1,210 tokens together

Delegates token-heavy, self-contained tasks to local CLI backends chosen by task size and type, with credit-exhaustion fallback through the backend chain to native Claude and a glanceable statusline HUD. Routing and shipped backend behavior are configured in config/roster.json; adding a new backend kind requires…

not rated 6 +1 26d ago A tokens not measured

ledger-metering

1128

Perseus-Computing-LLC/ledger

Plugin Claude Code

Bundles 1 hook

Meter Claude Code token usage to your self-hosted Ledger ledger. Each turn's usage is metered at session end so you can see your spend and efficiency (API-equivalent value vs. actual cost) on the Ledger dashboard. Sends token metadata only — never transcript content.

not rated 6 6d 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: