madbench

Authors, validates, runs, and debugs agentic coding benchmarks through a dedicated agent and terminal pane.

Parent repository GitHub

Type: Claude Code benchmarking plugin
Repository: MadAppGang/magus
Readiness: Mixed: core plugin packaging and documentation appear usable, while readiness varies substantially by plugin and external dependency.
Keywords: 7

Location

Repository path

plugins/madbench/README.md

Invocation

/madbench:bench; /madbench:doctor; madbench:bench agent

Setup

Installation / activation

Enable madbench@magus; requires madbench on PATH and terminal@magus.

Keywords

benchmarkingagent evaluationbench YAMLchecksmetricsterminalhook

Repository context

MadAppGang/magus

MIT-licensed Claude Code plugin marketplace and companion plugin suite for software development, combining commands, agents, skills, hooks, MCP runtimes, terminal control, semantic code navigation, multi-model orchestration, project provisioning, UI review, and stack-specific guidance; several features require external binaries, provider credentials, or dependent plugins.

software developmentcodebase navigationdebugging and testingarchitecture and researchmulti-model AIterminal automationUI design and reviewproject provisioningagent benchmarkingGo developmentBun and TypeScriptdocumentation

Open full repository research