Building agents plugins

chunxiaoxx/nautilus-compass

Plugin Claude Code

Bundles 5 skills, 5 commands, 1 MCP server · 198 tokens together

Cross-agent memory layer with drift detection, Merkle integrity, semantic recall, and MCP A2A protocol. Surfaces user-facing slash commands for direct inspection of session memory.

jatinmayekar/openwiki-for-claude-code

Plugin Claude Code

Bundles 4 skills · 224 tokens together

Generate and maintain OpenWiki-format documentation (openwiki/quickstart.md + sections) for your repo using Claude Code's own inference. No separate API key, and fully interoperable with the OpenWiki CLI on disk.

smixs/disruptor-skills

Plugin Claude Code

Bundles 12 skills · 851 tokens together

12 agent skills for AI-driven software development, stitched into one gated idea-to-ship pipeline: 7w3 design, build-ready spec, executable architecture guardrails, tracer-bullet slicing, an honest review loop, a parallel MVP worker fleet, demo-stand QA and safe server deploy. Cross-agent skills format (Claude Code…

ariccb/sync-claude-skills-to-codex

Plugin Claude Code

Bundles 1 skill · 47 tokens together

Sync Claude Code skills to Codex CLI via symlinks. Share your skill library between both AI coding assistants.

tingyulu/MyR2D2

Plugin Claude Code

Bundles 12 skills · 2,090 tokens together

A plugin for managing coding-agent sessions and handoffs, with Traditional Chinese instructions and Chinese-English triggers. It includes tools for saving work, logging tasks, reviewing changes, searching with citations, and planning calendar events from flight details.

shinpr/rashomon

Plugin Claude Code

Bundles 5 skills, 7 agents · 472 tokens together

Evaluate prompts and skills through parallel execution comparison in git worktrees. Prompt optimization with BP-001009 patterns, skill creation/update with quality grading, and blind A/B evaluation.

aayushostwal/nexus

Plugin Claude Code

Bundles 10 skills, 2 commands, 14 agents · 2,068 tokens together

Plugin-first Claude Code workflows with planning, CI/CD debugging, reusable agents, TODOs, and MCP safety policies.

Neeeophytee/ai-cost-cutter-skills

Plugin Claude Code

Bundles 10 skills · 688 tokens together

10 skills that cut your AI bill with proof instead of vibes: cheap/premium routing, advisor call budgets, token receipts audits, tested fallbacks, free-tier batch sizing, guarded cheap swaps, reasoning-effort throttles, evidence-based model bake-offs, context diets, and free-model triage. Every skill carries a…

shinpr/galley

Plugin Claude Code

Bundles 1 skill · 45 tokens together

Create, validate, queue, set up, and troubleshoot Galley AFK task workflows.

heurema/signum

Plugin Claude Code

Bundles 8 skills, 8 commands, 5 agents · 743 tokens together

Evidence-driven development pipeline with multi-model code review.

michael-harris/devteam

Plugin Claude Code

Bundles 20 skills, 20 commands, 12 hooks, 2 MCP servers · 454 tokens together

127-agent automated development system with Agent Teams, quality gates, Bug Council diagnostics, and autonomous execution.

DanielBlomma/cortex

Plugin Claude Code

Bundles 5 skills, 1 hook · 192 tokens together

Cortex local context: five behavior skills, a session bootstrap, and an optional MCP bridge.

romiluz13/pi-agent-skills

Plugin Claude Code

Bundles 11 skills · 1,176 tokens together

Code-grounded Agent Skills for building with Pi (pi-mono). Covers all 7 packages: pi coding agent (workspace, extensions, packages, RPC/SDK, customization), pi-ai (multi-provider LLM API), pi-agent-core (agent runtime), pi-tui (terminal UI), pi-web-ui (web components), pi-mom (Slack bot), and pi-pods (vLLM GPU…

mhylle/claude-skills-collection

Plugin Claude Code

Bundles 38 skills, 13 agents, 5 hooks · 4,417 tokens together

A verification-first development pipeline for Claude Code: brainstorm to plan to phased implementation, with quality gates (verification-loop, code-review, security-review), adversarial review, and TaskTracker-native variants.

davisjam/model-based-agentic-software-engineering

Plugin Claude Code

Bundles 3 skills · 773 tokens together

The mage toolkit — the Davis AI-First Engineering Method plus the control catalogue, packaged as installable skills. Ships three partner skills: self-governance (harden — audit a repo for missing guardrails, or convert a recurring failure into a durable control), self-operations (operate — run the agent-fleet…

zapier/agent-skills

Plugin Claude Code

Bundles 6 skills · 339 tokens together

Zapier agent skills for Claude Code. Built and maintained by Zapier teams.

phj128/autoworker

Plugin Claude Code

Bundles 10 skills, 1 command · 558 tokens together

Auto-loop execution workflow with quality gates for Claude Code. Automatically decomposes tasks, implements code, runs tests, and iterates through quality gates until completion.

donnfelker/loop-skills

Plugin Claude Code

Bundles 1 skill · 146 tokens together

(beta/experimental) Host-agnostic, N-model variant of multi-llm-convergence. Drives any artifact (plan, PRD, design doc, spec, or implementation diff) to cross-model consensus from Claude, Codex, Gemini, or another capable host by rotating multiple built-in reviewer families through one uniform read-only reviewer…

epicsagas/epic-harness

Plugin Claude Code

Bundles 27 skills · 997 tokens together

3 commands + 25 auto-trigger skills + self-evolving agent harness. Less to remember, more automation.

understudylabs/understudy-agent-tools

Plugin Claude Code

Bundles 43 skills, 1 command · 3,272 tokens together

Improve LLM apps and agents from real traces — reduce cost/latency, raise quality/reliability, capture traces, build evals, run local optimization (GEPA), compare models/providers, and route through Understudy.

rylsherdamz-rgb/stellar-forge

Plugin Claude Code

Lists 1 plugin

Eval-driven multi-agent framework for building production Stellar dApps.

sandeepshekhar26/develop-anything

Plugin Claude Code

Bundles 1 skill, 2 commands · 115 tokens together

AI context engineering — analyze your codebase and let this agent deep-enhance every rule, then compile CLAUDE.md / AGENTS.md / .cursor-rules / copilot-instructions. Commands: /auk:run, /auk:enhance.

3xachris/3xa-harness

Plugin Claude Code

Bundles 5 skills, 2 plugins · 478 tokens together

The five-skill discipline loop for long-running agent work: freeze a task's scope into a workorder, gate sensory output behind human review, log decisions so they survive a context reset, hand off state when work changes hands, and close out with evidence instead of claims.

mikeprasad/aria-knowledge

Plugin Claude Code

Bundles 1 skill, 12 MCP servers · 87 tokens together

ARIA — Applied Reasoning and Insight Architecture. Persistent human-governed knowledge for Claude Code via a five-phase lifecycle: capture → govern → promote → apply → refresh. Stages session insights/decisions/feedback into review backlogs, promotes approved items to a tag-indexed markdown base, and applies them via…