Building agents plugins

microsoft/eval-guide

Plugin Claude Code ✓ vendor

Bundles 6 skills · 569 tokens together

AI agent evaluation toolkit for Copilot Studio. Plan evals, generate test cases, interpret results, and triage failures — grounded in Microsoft's Eval Scenario Library and Triage & Improvement Playbook.

pydantic/skills

Plugin Claude Code

Bundles 1 skill · 85 tokens together

Build production-grade AI agents with Pydantic AI — tools, capabilities, structured output, streaming, and testing patterns.

pydantic/skills

Plugin Claude Code

Bundles 1 skill · 142 tokens together

Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness, currently Code Mode for collapsing many tool calls into one sandboxed Python execution.

RayFernando1337/rayfernando-skills

Plugin Claude Code

Bundles 1 skill · 127 tokens together

WAVES (Workers, Aggregate, Verify, Extend): wave-based orchestration for Codex. Decompose into independent slices, spawn parallel Codex subagents (or spawnagentsoncsv) as a bounded wave, verify evidence-backed handoffs, then synthesize. The manifest is the stop function: stop only on completion, stagnation, or budge.

povvo/claudikins-kernel

Plugin Claude Code

Bundles 4 skills, 4 commands, 8 agents, 8 hooks · 2,436 tokens together

Core planning and workflow infrastructure for the Claudikins ecosystem.

AlexZio00/sovereign-skills

Plugin Claude Code

Bundles 1 skill · 0 tokens together

Carves safety-adjacent requests into a safe scope, executed by a genuinely isolated fresh-context subagent, with an adversarial verify pass and a descope ledger.

AlexZio00/sovereign-skills

Plugin Claude Code

Bundles 1 skill · 179 tokens together

13-section AI collaboration audit — analyzes actual work patterns (not surveys) to generate behavioral profile, blind spots, and growth direction.

vinta/hal-9000

Plugin Claude Code

Bundles 1 hook

Automatically name each session and rename it as the conversation evolves.

vinta/hal-9000

Plugin Claude Code

Bundles 10 skills · 529 tokens together

Opinionated agentic skills that do the boring parts for you.

openprose/mycelium

Plugin Claude Code

Bundles 3 hooks

Git-native note graph for AI agent collaboration. Injects mycelium notes into context when files are read, teaches agents the protocol via SKILL.md, and nudges agents to leave notes after edits.

ZSeven-W/dsh-crew

Plugin Claude Code

Bundles 3 skills, 8 commands, 2 agents, 1 MCP server · 282 tokens together

Dispatch subtasks to DeepSeek Harness (DSH) agents as native subagents with live progress.

no-human-ai/no_human

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 37 tokens together

File a task with nohuman and check on it without leaving Claude Code: taskadd and taskstatus over your local nohuman server (127.0.0.1:8420). nohuman plans, codes, tests and has the work reviewed by a second model, then opens the pull request and stops.

UiPath/coder_eval

Plugin Claude Code

Bundles 6 skills · 284 tokens together

Test whether your Claude Code skills actually trigger, and benchmark any coding agent — author, run, and analyze the eval suite that proves it, locally or as a CI gate.

686f6c61/alfred-dev

Plugin Claude Code

Bundles 11 skills, 22 commands, 10 agents, 5 hooks, 1 MCP server · 3,310 tokens together

Plugin de ingeniería de software: 8 agentes de núcleo, Selina si hay frontend y Lucius bajo demanda. Memoria persistente por proyecto, quality gates y flujos desde la idea hasta la entrega.

tma1-ai/tma1

Plugin Claude Code

Bundles 4 skills, 2 commands · 401 tokens together

Local-first LLM agent observability powered by GreptimeDB.

rhuss/cc-spex

Plugin Claude Code

Bundles 1 skill, 7 commands · 154 tokens together

Specification-Driven Development with Process Discipline for AI Agents.

VKirill/claude-lane-stack

Plugin Claude Code

Bundles 17 skills, 4 commands, 14 agents · 1,726 tokens together

Solo PM conveyor for Claude Code: orchestrator agents, lane playbooks, onboard and resume commands.

sonilo-ai/skills

Plugin Claude Code

Bundles 12 skills · 961 tokens together

Agent Skills for Sonilo's licensed music, sound-effects, dubbing, and audio-ducking API — with structured-brief prompting guidance (pre-flight, music briefs, SFX action maps) folded into each skill.

harnessworks/harness-starter-kit

Plugin Claude Code

Bundles 6 skills · 243 tokens together

Portable Harness Starter Kit workflows for Claude Code.

Toskysun/sub-agents

Plugin Claude Code

Bundles 2 commands, 28 agents · 1,131 tokens together

Universal AI agents collection for Claude Code - 28+ specialized agents with strict boundary enforcement, project-specific agent creation, and intelligent task routing.

cap-js/mcp-server

Plugin Claude Code

Bundles 2 MCP servers

Model Context Protocol (MCP) server for AI-assisted development of CAP applications.

share-skills/pi

Plugin Claude Code

Bundles 4 skills, 3 commands, 4 agents, 7 hooks · 842 tokens together

PI (Wisdom-in-Action) Engine v10 — Name-Reality Alignment & Zero-Question Imperatives. ⚡PI-0105 pinned mandates, all-imperative directives, scene router, delivery quality gates, token economy. 16 wisdom traditions, MBTI cognitive strategies, anti-pattern decalogue, scene chaining, four dojos. 16+ platforms.

beefiker/superloopy

Plugin Claude Code

Bundles 9 skills, 6 agents, 4 hooks · 1,144 tokens together

Lightweight loop harness with strict evidence gates — Claude Code edition.

assafkip/kipi-system

Plugin Claude Code

Bundles 2 skills, 9 commands · 334 tokens together

PRD operating system: capture rough ideas, draft reviewable PRDs, run standard and adversarial review (Codex or a Claude senior-staff-engineer subagent, recorded truthfully), triage findings, decompose approved PRDs into atomic issue specs, and execute those issues with scope enforcement, stop-gate receipts, and…