ai-agents plugins

OAI-Labs/vibe-flow

Plugin Claude Code

Bundles 14 skills, 2 agents · 878 tokens together

Orchestration skills for Vibe Kanban: plan → ship → link → review → merge with wave-based dispatch, executor routing (T0-T4), and autonomous fix loops.

miguelmperezh/skillcat-sync

Plugin Claude Code

Bundles 1 skill · 95 tokens together

Link Claude Code to your SkillCat account and install/uninstall your catalog picks for real.

astropham1808/astro-agent-skills

Plugin Claude Code

Bundles 2 hooks

Cross-platform desktop notification (Windows/macOS/Linux) when Claude Code finishes a turn. Windows path is ThreatLocker-safe (inline PowerShell). Configurable agent name, session label, icon, and optional sound.

sentasity/cadence

Plugin Claude Code

Bundles 11 skills, 5 agents, 1 hook · 1,714 tokens together

Phase-aware, sub-agent-driven design/plan/execute system with explicit OOS discipline and post-deploy validation.

Bulugulu/game-qa

Plugin Claude Code

Bundles 6 skills · 453 tokens together

Verify browser-based game features through a PM-driven QA loop. Ships a project-agnostic runner + adapter skeleton + journey schema so projects onboard by copy-and-adapt, not natural-language reconstruction. Six skills covering request → plan → execute → review → rollup, plus the bootstrap that drops the framework…

tunahanaliozturk/atelier

Plugin Claude Code

Bundles 7 skills, 9 commands, 13 agents, 1 hook · 715 tokens together

Agent-orchestration plugin: a lead reviews a plan, gates on user approval, and routes tasks to specialist agents by capability.

t1djani/servo

Plugin Claude Code

Bundles 9 skills, 1 command · 481 tokens together

Process AI-first: ground-truth oracles, non-colluding gates, deterministic plans.

CassetteTapeCrackle/claude-starters

Plugin Claude Code

Bundles 9 skills, 1 command, 8 agents, 2 hooks · 754 tokens together

Token-lean project starters, on-demand clean-code skills, a scoped 76-agent library, and a cost-aware auto-launch orchestrator for Claude Code.

waveriderai/ce-design-flow

Plugin Claude Code

Bundles 2 skills · 336 tokens together

Design-first Compound Engineering. Adds a design leg to the CE loop: brainstorm -> wireframe -> pick -> hi-fi -> plan, driven by Open Design, with a live browser portal you can chat and mark up in and a clean handoff back to your terminal.

odysseus0/claude-orchestrate

Plugin Claude Code

Bundles 1 skill, 1 command · 104 tokens together

Decompose a large goal into a tree of parallel workers running in isolated git worktrees, collect typed handoffs, replan, repeat until terminal. Idiomatic Claude Code realization of Cursor /orchestrate.

meganemura/headsign

Plugin Claude Code

Bundles 3 skills, 3 hooks · 276 tokens together

A tiny phase gate for coding agents: your shell checks decide pass/fail (never the LLM), your workflow routes the agent (advance / retry / escalate / done). The agent drives, headsign holds the state.

alexsds/ade-workflow

Plugin Claude Code

Bundles 3 skills, 4 commands, 2 agents, 1 hook, 1 MCP server · 762 tokens together

Agent-Driven Engineering: Anthropic's 3-agent harness with pluggable rubrics and testing tools for long-running app development.

didvc/claude-chrome-multi-instance-warn

Plugin Claude Code

Bundles 1 hook

An agent driving a browser tends to start a new one rather than use the one already open, and to size its work off the core count. This warns once per session when a tool payload is about to do either. Never blocks.

FaisalNoman/playwright-skills

Plugin Claude Code

Bundles 1 skill · 52 tokens together

Test your web app on real iOS Simulator / Android emulator sessions via tapflow, alongside your existing Playwright suite.

NmadeleiDev/landingforge

Plugin Claude Code

Bundles 8 skills, 9 agents · 2,320 tokens together

A Claude Code engine that manufactures SaaS landing pages to a spec across four axes (conversion, organic SEO, AI-search/GEO, visual craft). Gated specialist phases (strategy -> copy -> design -> build -> discoverability -> conversion QA -> performance) plus a 10-star scoring loop that refuses to ship below a quality…

Natt-code216/promo-plan

Plugin Claude Code

Bundles 1 skill, 1 command · 183 tokens together

A plugin that generates an unattended promotional-video production plan through several structured interviews. A plugin is an add-on that extends what a coding agent can do.

felipeJJ/fullStack-pipeline

Plugin Claude Code

Bundles 3 skills, 3 agents, 2 hooks · 283 tokens together

Multi-agent TDD development pipeline: discovery, planning, red tests, implementation, review with complexity ratchet, and a local task registry. Portable across projects via a per-project profile.

10CG/aria-plugin

Plugin Claude Code

Lists 1 plugin

A plugin marketplace package built around AI-driven domain-driven design, a way to organise software around the business concepts it models. Its description lists 42 skills, 11 agents, and hooks, including a default secret-protection hook.

derio-net/super-fr

Plugin Claude Code

Bundles 2 skills · 137 tokens together

super-fr dispatch: queue phases to autonomous runners (VibeKanban adapter included) with per-PR quality gates.

git-aditya-star/project-notes

Plugin Claude Code

Bundles 1 skill, 5 hooks · 50 tokens together

Gives Claude a persistent, self-maintained notebook per project: distilled topic notes, a generated index injected into context each turn, and hooks that keep the notes current.

adamjali/claude-skills

Plugin Claude Code

Bundles 1 skill · 168 tokens together

Free up disk space on macOS safely — reason about regenerable caches, old runtime versions, and bulky artifacts; green/yellow/red buckets with a preview gate; never touches credentials or active code.

orenluxy/fable-method

Plugin Claude Code

Bundles 8 skills, 2 agents, 3 hooks · 741 tokens together

The Fable Method: systematic unknowns-discovery workflow based on Thariq's 'A Field Guide to Fable'. Blindspot scanning, structured interviews, prototype-first, implementation notes with deviation tracking, and merge quiz gates.

inferencegod/autonomy-loop

Plugin Claude Code

Bundles 1 skill, 9 commands, 2 agents, 2 hooks · 504 tokens together

Claude Code terminals on one repo pass a git baton: composable builder / reviewer / planner / researcher roles with a deterministic floor under every LLM judgment. v0.8.0 adds a rings + provision-or-refuse security posture: a SessionStart preflight prober classifies an assurance tier (ATTESTED -> LIVENESS -> SEPARATED.

ne11nn/cantos-plugin

Plugin Claude Code

Bundles 25 skills, 2 commands, 11 agents, 2 hooks · 1,808 tokens together

The full Cantos system as a one-command install: a self-improving, multi-agent assistant orchestrator for Claude Code. /cantos:init scaffolds the whole writable system into a project; /cantos:start runs it for one session. Bundles the orchestrator, specialist assistants, sub-agents, workflows, references, and a…