Description
Measures a command: warmup and timed runs, median/p95/stddev and outliers, two commands compared or a saved baseline per project, and a pane with a block distribution plot. Bounded, one at a time, never during Claude's turn unless Claude asked.
What it can do
Reach level 2 — writes or runs What does this mean? →
other: $.state.getother: $.state.setother: $.tool.checkruns processeswrites filesdrives Claudereads env varspersists statedraws
Can see: classic hooks · mcp__bench__bench calls
Raw API calls (21)
- $.clock.after
- $.clock.now
- $.command.register
- $.env.get
- $.fs.write
- $.process.run
- $.session.cwd
- $.session.root
- $.state.get
- $.state.set
- $.store.get
- $.store.set
- $.tool.check
- $.tool.register
- $.ui.close
- $.ui.invalidate
- $.ui.log
- $.ui.open
- $.ui.resolve
- $.ui.status
- $.ui.toast
Static check passed on Claude Code 2.1.295.
Install
$/plugin marketplace add mako-code/gobworks $/plugin install bench Check the repo for the exact name.
Details
- Repository
- mako-code/gobworks
- Path in repo
- mods/abilities/bench
- License
- MIT
- Last updated
- Oct 4, 2026
- First seen
- Oct 10, 2026
- Last scanned
- Oct 10, 2026
Related mods — reach level 2
- ruview-live ★ 98,587
- ruflo-agntcy ★ 76,337
- ruflo-adr ★ 76,337
- ruflo-agent ★ 76,337
Capability data is machine-generated by static analysis and may be incomplete. A SAFE badge is not a guarantee — read the code before installing anything with broad access. Not affiliated with Anthropic.
Found a mistake in this listing or verdict? Report an issue →