agentic-coding-harness
Run, watch, and meter coding agents — Claude Code, OpenCode, Kiro, Codex CLI, Gemini CLI, Prime Agent — with normalized events, cost accounting, A/B experiment/variant comparison…
MCP server · by sblattj
About
agentic-coding-harness is an MCP server published by sblattj. Marketplaces we read that list it: 1 (npm registry (MCP servers)). The last change we recorded was on 2026-11-02. As of our marketplace pass on 2026-11-03.
Run, watch, and meter coding agents — Claude Code, OpenCode, Kiro, Codex CLI, Gemini CLI, Prime Agent — with normalized events, cost accounting, A/B experiment/variant comparison, external run sources, and replayable run artifacts.
What it asks for
- Runs on your machine
None of the marketplaces we read publishes its tools or the settings it asks for.
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.
Package
npm agentic-coding-harness (agentic-coding-harness on npm)
- npm downloads/week: 528 (2026-10-31)
- npm downloads/month: 3 731 (2026-10-31)
- Latest version on npm: 0.26.0, published 2026-10-21
- Declared version 0.27.3 is not listed on npm
npm facts come from the public npm registry (registry.npmjs.org, api.npmjs.org). Each figure is the registry's own and is never added to another. A registry that publishes no figure shows none: no number is not zero.
Connect
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
Where it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| npm registry (MCP servers) (Open on npm) | Listed | 0.27.3 | Downloads/month (npm): 3 731 Downloads/week (npm): 528 Forks (GitHub): 0 Stars (GitHub): 1 |
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 changed
- npm registry (MCP servers): released version 0.27.3 (was 0.27.1)
- npm registry (MCP servers): released version 0.27.1 (was 0.26.0)
- npm registry (MCP servers): released version 0.26.0 (was 0.25.0)
- npm registry (MCP servers): released version 0.25.0 (was 0.24.0)
- npm registry (MCP servers): released version 0.24.0 (was 0.23.0)
- npm registry (MCP servers): released version 0.23.0 (was 0.20.3)
- npm registry (MCP servers): released version 0.20.3 (was 0.16.1)
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.
-
Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.
-
Cloud console for a fleet of AI coding agents running on your own machines. OAuth.
-
Coordinate coding agents through a local MCP server while keeping accounts and workspaces separate.
-
Cut AI agent token costs 5-15x — routes only relevant code symbols instead of full files.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
See which of your team's coding agents needs someone, across Claude Code, Codex and Cursor.
-
Multi-agent orchestration for coding agents: run external agent CLIs (Codex, Claude Code, OpenCode, Grok Build, Gemini, Devin CLI) as independent reviewers, stateful repository…
-
Search, resume and hand off coding-agent sessions: Claude Code, Codex, Gemini, Antigravity and more.
-
Intelligent orchestration platform for AI coding tools. Coordinates Claude, Codex, Gemini, and OpenCode through a single MCP server — routing each task to the best model using…
-
Tokmeter — AI Agent Usage & Cost
Tokens and cost for Claude Code, Codex and 22 more AI coding agents, from local session files.
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)
-
Intelligent orchestration platform for AI coding tools. Coordinates Claude, Codex, Gemini, and OpenCode through a single MCP server — routing each task to the best model using…
-
agent-discover io.github.keshrath/agent-discover
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
-
agent-comm io.github.keshrath/agent-comm
Agent intercommunication - messaging, channels, shared state, and real-time events
-
Autonomous overnight coding agent. Queue tasks in YAML, run them via Claude CLI while you sleep, and use self-healing audit-fix loops to hit any quality target. Includes skills…
-
Multi-provider AI agent remote control for Claude Code. Manage Claude Code, Codex CLI, and Gemini CLI agents from Telegram or Matrix. Send commands, check status, monitor health…
Has a listing on Claude Code: claude-plugins-official (5)
-
Detect AI agents in your codebase and instrument them with Pendo Agent Analytics via the best-fit path: Python SDK, TypeScript SDK, client-side trackAgent, or the Conversations…
-
Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
-
New Relic observability intelligence for Claude Code. Investigate APM performance, analyze cloud costs, debug Kubernetes, write NRQL queries, and respond to alerts — all from your…
-
Comprehensive development workflow for building AI agents with the Atomic Agents framework. Includes specialized agents for schema design, architecture planning, code review, and…
-
Appwrite tools for Claude Code, including SDK skills, Appwrite MCP servers, and deployment commands.
Has a listing on Claude: knowledge-work-plugins (5)
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
-
MCP server for terminal commands, file operations, and process management
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
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.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
AI-powered code review in Codex, powered by CodeRabbit.
-
Qodo setup, code intelligence, and review workflows.
Has a listing on Community GitHub marketplaces (5)
-
Multi-agent orchestration for coding agents: run external agent CLIs (Codex, Claude Code, OpenCode, Grok Build, Gemini, Devin CLI) as independent reviewers, stateful repository…
-
Orchestrate OpenAI Codex agents from Claude Code. Spawn parallel agents, monitor progress, send follow-up messages, and capture results - all through tmux sessions.
-
Complete guide for managing AI coding agent sessions via agent-deck CLI - session lifecycle, MCP management, groups, profiles, and automation
-
Drive the ccmux cross-harness CLI to dispatch work to other AI coding agents (Claude Code, Codex, Cursor, OpenCode, Pi, Gemini) through programmatic ccmux invoke calls. Requires…
-
Delegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.
Has a listing on Copilot CLI: github/awesome-copilot (5)
-
Meta prompts that help you discover and generate curated GitHub Copilot agents, instructions, prompts, and skills.
-
Model, visualize, and deploy applications with Radius from the GitHub Copilot app and CLI.
-
foundry-hosted-agent-copilotkit
Build CopilotKit + AG-UI web apps on Microsoft Foundry hosted agents (Microsoft Agent Framework): wiring, native Foundry primitives, human-in-the-loop approvals, azd deploy, and…
-
Build applications with the Microsoft Copilot SDK, transitioning from GitHub Copilot SDK, across multiple programming languages. Includes instructions for C#, Go…
-
Analyze any repository and generate AI-ready configuration — AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more. Mines your PR review patterns and creates…
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.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Advanced Security plugin for GitHub Copilot.
-
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…
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
Has a listing on Cursor: cursor/plugins (5)
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
-
Skills for building on the Cursor Origin API. Fetch the live spec first, then follow the Origin rules for credentials, scopes, webhooks, paging, and errors. Includes a skill that…
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
Has a listing on Docker MCP Catalog (5)
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Give your AI agents trusted access to the full Postman platform.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
-
MCP server for terminal commands, file operations, and process management
Has a listing on Official MCP Registry (5)
-
Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.
-
Cloud console for a fleet of AI coding agents running on your own machines. OAuth.
-
Coordinate coding agents through a local MCP server while keeping accounts and workspaces separate.
-
Cut AI agent token costs 5-15x — routes only relevant code symbols instead of full files.
-
See which of your team's coding agents needs someone, across Claude Code, Codex and Cursor.
Has a listing on PyPI (MCP servers) (5)
-
Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.
-
marm-mcp-server io.github.Lyellr88/marm-mcp-server
Universal MCP Server with advanced AI memory capabilities and semantic search.
-
lineai-mcp-server io.github.lineai-intelligence/lineai-mcp-server
An MCP Server to utilize Lineai's rich software dependency data in your AI programming assistant.
-
A code intelligence graph that gives AI coding agents deep, token-efficient understanding of your codebase.
-
Every tool your AI needs in one self-hosted install: memory, reasoning, git, Docker and more.
Has a listing on npm registry (MCP servers) (5)
-
mcp-server io.github.cachly-dev/mcp-server
Solve it once. From then on, your AI knows. Experience for coding agents, hosted in the EU.
-
agent-discover io.github.keshrath/agent-discover
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
-
Reports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
-
Agent-Nuvira: Multi-agent AI coding CLI — plan, write, review, test, and publish code with local models (Ollama) or cloud APIs (Groq, NVIDIA NIM, Google Gemini, OpenRouter)
-
Deploy Claude Code, Codex & Antigravity (agy) CLI agents to demolish your work before users do. Real file analysis. Brutal honesty. Per-call model pinning, conversation…
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.
Want this mark on your plugin in our catalog?
Prove you maintain it with a file in its repository, a file on your domain or a DNS record, and you can show this mark on the card, with live banners for your site and README. How verification works
You also 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.
Package data comes from the public npm registry (registry.npmjs.org). Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.