madbench

Toolkit for madbench, MadAppGang's Go harness for benchmarking agentic coding tools. Carries madbench's own skills with /madbench:madbench as the entry point, checks them against the installed madbench, and runs benches in a visible pane through the madbench:bench agent.

Version	0.9.1
Marketplace	magus
Commands	1
Subagents	1
Skills	3
MCP server	no
Hooks	yes

Install

magus

Find madbench on the Plugins tab and turn it on. magus registers the magus marketplace if you do not have it, and installs what the plugin needs to actually run — binaries, MCP servers, CLI tools.

For a team, press s to save your plugins as a profile and commit it. Everyone else runs magus install — see Teams and profiles.

Prefer to do it by hand? Installing Magus has the manual path.

Commands

Command	What it does
/madbench:doctor	Run the three madbench plugin checks — skills against the installed madbench, bench layout, and the generated bench index — and print their output verbatim

Subagents

Dispatched with the Agent tool, each in its own context window.

Agent	What it does
madbench:bench	|

Skills

	How you get it
○	You invoke it by name
▸	A command loads it for you — you never name it

Why a skill lands in one row or another

	Skill	What it covers
○	madbench:madbench	Creates, runs, debugs and migrates madbench benches. Checks the installed madbench against these skills first, then routes the request.
○	madbench:migrate	Brings a madbench Bench or Experiment written for madbench v0.41.0 or later to the installed madbench, applying the changes changes.md records between the two versions.
▸	madbench:madbench-evals — 5 more docs	Authors, runs and debugs madbench benches natively — bench YAML, checks, metrics with module/, red-state testdata, the two controls, exit codes;

Hooks

This plugin installs hooks. They run automatically and are the usual first place to look if its behaviour stops firing.

Source

plugins/madbench/ on GitHub, including its full README.