ai-agents plugins

zapier/wade-skills

Plugin Claude Code

Bundles 3 skills · 185 tokens together

Agent skills Wade Foster (Co-Founder & CEO, Zapier) uses day-to-day — War Council, Meeting Follow-Up Pipeline, and Exec Weekly Agenda Generator.

MRCalderon3D/everything-game-dev-code

Plugin Claude Code

Lists 1 plugin

A universal game development scaffold for Claude Code with layered rules, agents, skills, commands, hooks, contexts, and isolated engine packs for Unity, Unreal, and Godot.

kurikomi-labs/komi-learn

Plugin Claude Code

Bundles 4 hooks

A continuous, zero-friction learning layer: the agent learns about you and improves its own skills across every session, and can share anonymized, provenance-verified learnings to a global pool. Inspired by Hermes Agent.

existential-birds/beagle

Plugin Claude Code

Bundles 14 skills · 1,918 tokens together

Architecture analysis, brainstorming, ADR generation, LLM-as-judge comparison, and spec gap resolution.

existential-birds/beagle

Plugin Claude Code

Bundles 19 skills · 766 tokens together

Shared code review workflows, verification protocol, git commands, and feedback handling. Recommended as a base for all beagle plugins.

existential-birds/beagle

Plugin Claude Code

Bundles 4 skills · 119 tokens together

Documentation quality, generation, and improvement using Diataxis principles. Pairs with beagle-core for full workflow.

apoorvjain25/frontier

Plugin Claude Code

Bundles 1 skill, 2 agents · 409 tokens together

Standards written and audited by Claude Fable 5: make Opus, Sonnet, GPT, or Gemini produce work close to its bar. 21 craft rubrics, best-of-N candidates, convergence sweeps, a taste gate with permanent distillation.

postmelee/hyper-waterfall

Plugin Claude Code

Bundles 1 skill · 47 tokens together

Claude Code discovery layer for the Hyper-Waterfall framework.

ThierryN/fire-flow

Plugin Claude Code

Bundles 44 commands, 15 agents · 879 tokens together

Research-backed orchestration for Claude Code. Structured workflow from idea to production with parallel execution, session memory, 70-point validation, autonomous mode, and adversarial review. 51 commands, 15 agents across 7 departments.

KilledByAPixel/LittleJS-AI

Plugin Claude Code

Bundles 4 skills · 572 tokens together

Make games and graphics-heavy apps with LittleJS, a fast open-source HTML5 engine. Ask for a game and get a complete playable project in seconds - 2D, Box2D physics, or three.js 3D - ready to run and share.

synadia-ai/synadia-agents

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 41 tokens together

NATS channel plugin for Claude Code — bridges NATS messaging to Claude Code sessions.

sneg55/agent-starter

Plugin Claude Code

Bundles 8 skills, 4 hooks · 303 tokens together

Skills, hooks, templates, and engineering guides for bootstrapping AI-agent-friendly projects, with a per-project self-improvement loop.

spacedock-dev/spacedock

Plugin Claude Code

Lists 1 plugin

Plugin marketplace listing 1 plugin: spacedock.

genai-io/san

Plugin Claude Code

Bundles 1 skill, 1 command, 1 agent, 1 hook · 27 tokens together

A test plugin for UI/UX comparison testing between Claude Code and San.

tomascupr/sous-chef

Plugin Claude Code

Bundles 7 skills · 536 tokens together

Claude plans, delegates, and tastes every plate. Sonnet, Codex, GLM, or Grok does the knife work. A Claude Code plugin for the orchestrator/implementer split: /serve runs the whole line autonomously (implement, cross-review, fix, verify), /fire hands specced implementation to the worker, /taste runs cross-model review.

baldaworks/callee

Plugin Claude Code

Bundles 2 skills · 89 tokens together

Run Markdown-defined agents and deterministic workflows.

netresearch/agent-rules-skill

Plugin Claude Code

Bundles 1 skill · 63 tokens together

Generate and maintain AGENTS.md, copilot-instructions.md, and other agent rule files.

Jovancoding/Network-AI

Plugin Claude Code

Bundles 1 skill, 4 commands, 1 MCP server · 116 tokens together

Gives Claude Code a multi-agent coordination layer over MCP — an atomic shared blackboard (locked propose/validate/commit), permission gating with HMAC/Ed25519-signed tokens, federated token-budget tracking, and append-only audit-log queries. Backed by an orchestrator with 32 framework adapters (LangChain, AutoGen…

doodledood/manifest-dev

Plugin Claude Code

Bundles 1 skill · 40 tokens together

A template for creating new Claude Code plugins.

doodledood/manifest-dev

Plugin Claude Code

Bundles 8 skills · 564 tokens together

Tools for prompts and PRs alongside the manifest workflow. Includes collaborative PR walkthroughs, autonomous PR review with independent per-gate manifest verification, author-side PR babysitting that forwards /do verification policy, gap-calibrated prompt engineering, cross-boundary context handoff, incremental…

doodledood/manifest-dev

Plugin Claude Code

Bundles 20 skills · 1,473 tokens together

Manifest-driven development: /figure-out reaches shared understanding, /define writes Deliverables with Acceptance Criteria and Global Invariants, and /do implements them. Each gate is one text — a title, a body, and an optional why — carrying a required kind (judgment or deterministic, never inferred) as its only…

Junhanliu-dev/espalier-engineering

Plugin Claude Code

Lists 1 plugin

Marketplace publishing the Espalier Engineering plugin — auto-discovered, project-specific guardrails for AI coding agents.

yempik-ai/cowork-os

Plugin Claude Code

Bundles 4 skills, 7 commands · 895 tokens together

Turn a Claude Cowork project into a company brain your team owns: guided setup, a Memory Update protocol, a knowledge-transfer interview, a senior strategy skill, a decision lifecycle with daily signal sweeps and a weekly Decision Radar, a sales/pipeline follow-up layer, a LinkedIn editor, mission mode, and recurring…

heggria/taskflow

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 122 tokens together

Declarative, verifiable DAG orchestration for Claude Code subagents — fan-out, gates, loops, tournaments, approvals, resumable runs, and saveable commands, with intermediate transcripts kept out of your context.