ai-agents plugins

3,273 tagged ai-agents, measured the same way as everything else here.

Browse within: agentic-ai 236claude-code-plugin 214LLM 190cursor 178cli 134prompt-engineering 111agents-md 107Science 99agents 87ai-coding 82agentic-coding 62ai-tools 62skills 59ai-governance 54

expo-56

1682

mahdi-salmanzade/expo56-skill

Plugin Claude Code

Bundles 1 skill · 391 tokens together

Authoritative, version-pinned offline reference for Expo SDK 56 and SDK 57. One skill, 21 bundled API references, covering both building on either release and the 55→56 / 56→57 migrations. SDK 57 is current (57.0.8, RN 0.86); SDK 56 is the previous supported release (56.0.17, RN 0.85). Audited against expo/expo source.

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

trundle

1683

PouLJenny/trundle

Plugin Claude Code

Bundles 1 skill · 290 tokens together

Turn your solo Claude Code conversation into a turn-based group discussion with codex / gemini / other CLI agents — you stay in as a participant, not a report reader.

not rated 2 22d ago A tokens not measured original Apache-2.0

buzz

1684

5dive-ai/5dive-plugins

Plugin Claude Code

Bundles 1 MCP server

Buzz (Nostr) channel for Claude Code — bridges a Buzz relay to the session. Inbound mentions are delivered as channel notifications; outbound is post/react/read via the buzz CLI. Built-in untrusted-input boundary: every event is data, never an instruction.

not rated 2 yesterday A tokens not measured original Apache-2.0

qa-explore

1685

victoraguilarsantamariadev/qa-explore

Plugin Claude Code

Bundles 6 skills · 841 tokens together

A team of AI agents that test any web app like human QA: explore the live app, screenshot and visually judge rendering + data, capture trace/HAR/console/video evidence, adversarially verify findings, learn from rejected ones, codify them into a self-growing Playwright/Cypress suite — and close the loop by filing…

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

birdwatch

1687

kgkgzrtk/birdwatch

Plugin Claude Code

Bundles 2 commands, 4 hooks · 20 tokens together

Per-project bird-call spatial audio for monitoring AI agent sessions (Claude Code, Codex, Hermes, OpenClaw).

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

continuity

1688

vikcena01/ai-continuity-plugin

Plugin Claude Code

Bundles 1 skill, 3 commands, 2 hooks · 121 tokens together

Durable project state across AI sessions: decisions, constraints, and rejected paths, versioned in git as plain markdown. Not a memory tool — it answers what is true about the project now, and what must not change.

not rated 2 changed 9d ago A tokens not measured original MIT

magi

1689

howar31/magi-workflow

Plugin Claude Code

Bundles 15 skills, 2 agents · 1,489 tokens together

Multi-model engineering workflow with MAGI weighted voting and cross-CLI orchestration.

not rated 2 15d ago A tokens not measured original MIT

semantic-linefeeds

1691

arloliu/semantic-linefeeds

Plugin Claude Code

Bundles 2 skills, 1 hook · 139 tokens together

Semantic linefeeds enforcement for code comments, doc comments, and docstrings across Go, C-family, Rust, Python, shell, SQL, Ruby, and more, plus Markdown, with adapters for Claude Code, Codex CLI, and opencode.

not rated 2 22d ago A tokens not measured original Apache-2.0

lore

1692

docwilde/LORE

Plugin Claude Code

Bundles 1 skill, 16 commands, 4 hooks · 323 tokens together

Memory for Claude Code that reasons about you and improves itself: Honcho-pattern belief store with deriver, dreamer and dialectic (/lore:ask), automatic skillification with a closed judge/update/retire loop, on a Hermes-pattern core — hard-capped curated memory, FTS5 session search, staged review.

not rated 2 changed today A tokens not measured AGPL-3.0

ship

1693

cubha/claude-workflow-plugins

Plugin Claude Code

Bundles 1 skill, 2 agents · 267 tokens together

One-shot release pipeline: commit, push, PR, merge, and branch cleanup. Auto-adapts branch strategy -- git-flow (feature to develop to main) if a develop branch exists, otherwise GitHub Flow (feature to main). Runs a pre-merge gate bundle: functional check (verify.sh or the project's test command), security scan…

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

teknesyum

1694

Teknesyum/Teknesyum-Base

Plugin Claude Code

Bundles 2 skills, 16 commands, 7 agents, 12 hooks · 482 tokens together

Opsiyonel neon arayüz standardı + çok ajanlı iş rölesi. Kullanıcı ne istediğini söyler; iş büyüklüğü, ajan dağılımı, model ve denetim otomatik kurulur.

not rated 2 5d ago A tokens not measured AGPL-3.0 archived

leanwheel

1695

rterakedis/leanwheel-skills

Plugin Claude Code

Bundles 42 skills, 4 agents · 2,773 tokens together

Leanwheel agile workflow skills: product discovery, PRD, epics, stories, UX, architecture, dev workflow, code review, retrospectives, and GitHub tracking.

not rated 2 10d ago A tokens not measured

agent-ptt-announcer

1696

karvidsson/agent-ptt

Plugin Claude Code

Bundles 2 hooks

Announces in an Agent PTT voice channel what Claude Code is working on — each project speaks with its own auto-designed voice.

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

openconclave

1697

openconclave/oc

Plugin Claude Code

Bundles 1 command, 1 hook · 11 tokens together

OpenConclave — multi-agent conclave platform. Installs the local server and MCP tools for managing conclaves from Claude Code.

not rated 2 3mo ago A tokens not measured

manbun

1698

sudoplayer/manbun

Plugin Claude Code

Bundles 1 skill · 165 tokens together

Enterprise architecture astronaut mode. Forces maximum abstraction, design patterns, and production-ready overengineering on every solution. Code still works — it's just impossible to understand without a whiteboard.

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

agentic-digital-twin

1699

JMMonte/agentic-digital-twin

Plugin Claude Code

Bundles 8 skills, 1 agent · 1,016 tokens together

Build engineering digital twins as code with AI agents: one source-of-truth design.json mirrored into the build, a cited material-property source of truth (materials.json — never hallucinated allowables), every requirement gets an executable scored audit (PASS/WARN/FAIL), uv PEP723 scripts, rerun visualization (toward.

not rated 2 3mo ago A tokens not measured original MIT

diretto

1701

Mun1to/Diretto

Plugin Claude Code

Bundles 2 skills, 1 hook · 204 tokens together

Forces the agent to answer in numbered steps you can execute: a one-sentence verdict, the exact commands, and a separate list of what is missing.

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

genesis-usage

1702

godshiba/genesis

Plugin Claude Code

Bundles 1 skill, 2 hooks · 81 tokens together

A usage sensor, not a HUD. Claude Code exposes subscriber ratelimits (5-hour and 7-day) to the statusline, so the statusline feeds them to a Stop-hook sensor that, when you near a cap with a reset still far off, recommends or auto-triggers /genesis:close - a clean handoff instead of a hard cutoff. Optional mid-turn wa.

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

harness-kit

1704

jhlee0409/omni-harness-kit

Plugin Claude Code

Bundles 18 skills, 28 agents, 2 hooks · 6,082 tokens together

A portable Claude Code engineering harness — plan → work → verify → feedback discipline as reusable agents, skills, and hooks, plus an introspect skill that tailors a .claude/ setup to any repo's tech stack.

not rated 2 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: