meta-harness-ygn
Meta-Harness-YGN is a Claude Code plugin (namespace /mh) that brings scientific rigor to harness engineering: every proposed change produces a falsifiable hypothesis, a…
Pacote de plugins · de yannabadie
Resumo
meta-harness-ygn é um pacote de plugins para ferramentas de programação com IA publicado por yannabadie. Marketplaces que lemos e que o listam: 1 (Claude Code: claude-plugins-community). Vimos pela primeira vez em 2026-10-11 e não registramos mudanças desde então. Conforme nossa passagem pelos marketplaces em 2026-10-14.
Meta-Harness-YGN is a Claude Code plugin (namespace /mh) that brings scientific rigor to harness engineering: every proposed change produces a falsifiable hypothesis, a reproducible evaluation against a 9-check suite, and a recorded entry on a multi-objective Pareto frontier — so you always know whether your harness actually improved, regressed, or just changed.
O que pede
- Instala-se como pacote de plugins
- Configurações: 2
- Hooks declarados: 7
O que declara, pede e executa, por completo
Instale apenas plugins de desenvolvedores em quem você confia. Mostramos o que os marketplaces publicam e não testamos plugins.
Funciona com
- Claude Code
Pelos marketplaces que o listam e pelo transporte MCP que declara, conforme cada cliente documenta. Não testamos plugins.
Conectar
Comandos e configurações gerados apenas a partir do que os marketplaces declaram. Não os executamos por você e não testamos plugins.
Como plugin do Claude Code
Gerado a partir do que Claude Code: claude-plugins-community declara.
/plugin marketplace add anthropics/claude-plugins-community
/plugin install meta-harness-ygn@claude-communityOnde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Abrir o código no GitHub) | Listado | 1.3.0 | Forks (GitHub): 0 Estrelas (GitHub): 0 |
Sem marcação |
Cada número é do próprio marketplace e nunca é somado entre marketplaces. Um marketplace que não publica números não mostra nenhum: sem número não é zero.
O que o pacote contém
Conforme publicado em Claude Code: claude-plugins-community.
Servidores MCP: 1
mh-server
Skills: 6
bootstrapdashboardevalevolvefrontierharness-regressions
Agentes: 4
context-harvesterharness-evaluatorharness-proposerregression-auditor
Hooks: 6
InstructionsLoadedPostCompactPostToolUseSessionStartStopSubagentStop
O que mudou
Nada mudou neste plugin desde que começamos a acompanhá-lo.
Plugins semelhantes
Produtos cujos próprios nomes, descrições, ferramentas e skills são os mais próximos deste pelo significado, em todos os marketplaces que lemos. A proximidade é ordenada apenas dentro desta lista.
-
harness-architect is a meta-tool that scans any target project and builds an end-to-end Claude Code harness — CLAUDE.md, settings, rules, agents, playbooks, hooks, and MCP…
-
HarnessKit is a professional-grade engineering framework that empowers AI agents with a robust 'harness' of structured controls and specialized personas. Built on the principles…
-
Harness leverages Claude Code's agent team system to decompose complex tasks into coordinated teams of specialized agents. Say "build a harness for this project" and it…
-
Diagnose your Claude Code harness (CLAUDE.md, settings.json, .mcp.json, hooks, skills, memory, MCP servers, and workflow) against 25 anti-pattern indicators. Outputs an S–E…
-
Autonomous LLM agent optimization using LangSmith. Spawns 5 parallel proposers in git worktrees, evaluates candidates via LangSmith experiments, and merges winners automatically…
-
karimo-harness-engineering-agent-orchestration
Harness engineering framework for Claude Code — plan mode on steroids. Product design-driven agent orchestration with sub-agents and agent teams, tuned for developers and…
-
Autonomous prompt optimization using Karpathy's autoresearch pattern. Editable file + fixed eval metric + autonomous improvement loop.
-
A Claude Code plugin that replaces 30+ commands with 6, auto-triggers skills based on what you're doing, and evolves new skills from your own failure patterns. Less surface area…
-
claude-meta-skills is a technical-preview reliability hook suite for Claude Code. It adds five local hook checks that help Claude catch common agent failure modes while working in…
-
A Claude Code subagent that explores unconventional, first-principles solutions to hard technical problems, pushing Claude out of its normal tendency to play it safe and stick to…
Plugins semelhantes por marketplace
A mesma pergunta feita a cada marketplace separadamente: existe lá um equivalente deste plugin?
Listado em Claude Code: claude-plugins-community (5)
-
harness-architect is a meta-tool that scans any target project and builds an end-to-end Claude Code harness — CLAUDE.md, settings, rules, agents, playbooks, hooks, and MCP…
-
HarnessKit is a professional-grade engineering framework that empowers AI agents with a robust 'harness' of structured controls and specialized personas. Built on the principles…
-
Harness leverages Claude Code's agent team system to decompose complex tasks into coordinated teams of specialized agents. Say "build a harness for this project" and it…
-
Diagnose your Claude Code harness (CLAUDE.md, settings.json, .mcp.json, hooks, skills, memory, MCP servers, and workflow) against 25 anti-pattern indicators. Outputs an S–E…
-
Autonomous LLM agent optimization using LangSmith. Spawns 5 parallel proposers in git worktrees, evaluates candidates via LangSmith experiments, and merges winners automatically…
Listado em Claude Code: claude-plugins-official (5)
-
Full Domino Data Lab platform support — workspaces, jobs, model deployment, experiment tracking, GenAI tracing, Spark/Ray/Dask, and app deployment for data science teams
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
Langfuse observability plugin for Claude Code — captures and exports traces, spans, and session telemetry from Claude Code to Langfuse for LLM monitoring, debugging, and evaluation
-
Skills, agents, and workflows for Honeycomb observability — query patterns, production investigations, SLOs, OpenTelemetry instrumentation, and Beeline migration. Designed to…
-
CodSpeed is the all-in-one performance testing toolkit. Dive into benchmarking results, flamegraphs, and performance comparisons — give Claude granular profiling context to…
Listado em Claude: knowledge-work-plugins (5)
-
Skills, agents, and workflows for Honeycomb observability — query patterns, production investigations, SLOs, OpenTelemetry instrumentation, and Beeline migration. Designed to…
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
A suite of agent skills for the full GrowthBook feature flag and experimentation lifecycle.
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Listado em Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
Listado em Community GitHub marketplaces (5)
-
Automated AI research toolkit: hypothesis generation, experiments, and paper writing
-
Hunch — Engineering Memory + Change Gate
The hunch_* MCP tools (why, constraints, blast radius, merge verdict, capture) plus /hunch:capture, /hunch:heal, /hunch:why, /hunch:fix, /hunch:fragile. Requires Node 22.13+…
-
Heystack observability for your coding agent: the hosted MCP server (investigate incidents, traces, sessions, AI usage; manage apps, keys, alerts) plus the heystack-setup and…
-
Triage and fix Mushi bug reports without leaving Claude Code: hosted MCP (OAuth sign-in, no keys) + a mushi-debugger subagent that pulls reports, diagnosis, and fix context
-
Deprecated compatibility plugin; use superskill for the human-facing reviewed capability flow
Listado em Copilot CLI: github/awesome-copilot (5)
-
Goal-driven task orchestration with independent verification. Interviews the user to define a clear goal, then loops between a Builder subagent (does the work) and an Inspector…
-
Three-agent workflow for orchestrated software delivery with an orchestrator plus implementation and QA subagents.
-
Self-Learning Multi-agent orchestration framework for spec-driven development and automated verification. With smarter tool calling and leaner context.
-
Create, edit, run, save, and checkpoint Jupyter notebooks in an interactive Copilot canvas.
-
7 specialized agents covering the full software development lifecycle from UX design and architecture to security and DevOps.
Listado em Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
Advanced Security plugin for GitHub Copilot.
-
Complete bundle: all Microsoft Skills for Fabric for developers and consumers.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
Listado em Cursor: cursor/plugins (5)
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
-
Thermo-nuclear branch review: deep security/correctness audits, harsh code-quality rubrics, parallel subagents, thermos orchestration, and optional merge-ready PR flows.
-
Inspect and manage feature gates, experiments, dynamic configs, and metrics.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Scaffold and validate new agent plugins.
Listado em Docker MCP Catalog (5)
-
mcp-grafana io.github.grafana/mcp-grafana
An MCP server giving access to Grafana dashboards, data and more.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
Listado em Official MCP Registry (5)
-
Automated AI research toolkit: hypothesis generation, experiments, and paper writing
-
Local-first defensive scanner for vulnerable dependencies, leaked secrets, and risky agent configs
-
Community of Consciousness MCP Server — upload and explore collective wisdom via GitHub.
-
DebugBundle MCP: runtime error reporting, incident response, health checks, and product analytics.
-
evalview-mcp io.github.hidai25/evalview-mcp
Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.
Encontrados pelo significado, não por código ou repositório em comum: plugins semelhantes continuam sendo produtos distintos, e isto não é uma avaliação nem uma recomendação.
Este plugin é seu?
Adicione-o aos seus projetos e prove que o mantém com um arquivo no repositório, um arquivo no seu domínio ou um registro DNS. Você recebe alertas quando um marketplace o publica, o remove, muda a marca de verificado ou o que ele pede, e o endpoint remoto passa a ser monitorado como um serviço web.
Dados de Claude Code: claude-plugins-community. Os números vêm das nossas próprias passagens regulares pelos marketplaces, última leitura em . Não publicamos dados de contato dos editores de plugins.