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…
Plugin bundle · by yannabadie
About
meta-harness-ygn is a plugin bundle for AI coding tools published by yannabadie. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). We first saw it on 2026-10-11 and have recorded no change since. As of our marketplace pass on 2026-10-13.
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.
What it asks for
- Installs as a plugin bundle
- Settings: 2
- Hooks: 7
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Works with
- Claude Code
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a Claude Code plugin
Built from what Claude Code: claude-plugins-community declares.
/plugin marketplace add anthropics/claude-plugins-community
/plugin install meta-harness-ygn@claude-communityWhere it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Open the source on GitHub) | Listed | 1.3.0 | Forks (GitHub): 0 Stars (GitHub): 0 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
What the bundle contains
As published on Claude Code: claude-plugins-community.
MCP servers: 1
mh-server
Skills: 6
bootstrapdashboardevalevolvefrontierharness-regressions
Agents: 4
context-harvesterharness-evaluatorharness-proposerregression-auditor
Hooks: 6
InstructionsLoadedPostCompactPostToolUseSessionStartStopSubagentStop
What changed
Nothing has moved on this plugin since we started watching it.
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
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…
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on 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…
Has a listing on 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…
Has a listing on 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.
Has a listing on 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.
Has a listing on 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
Has a listing on 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.
Has a listing on 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…
Has a listing on 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.
Has a listing on 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.
Has a listing on 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.
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Is this your plugin?
Add it to your projects and prove you maintain it with a file in its repository, a file on your domain or a DNS record. You get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.