Benchmark
Snapshot codebase metrics (file count, total lines, /critique scores) for trend tracking. Subcommands capture/list/compare/show. Snapshots stored as JSON in .dragoon/benchmarks/. Use to track design quality and codebase growth over time. Run as `node ~/.claude/skills/dragoon/skills/benchmark/scripts/benchmark.js <subcommand>`.From its SKILL.md
npx -y skills add Dragoon0x/dragoon-skills --skill benchmarkAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 4 commands, including `dragoon benchmark capture` and 3 more.
SKILL.md
0.8 KB, 96 tokens by cl100k_base, as published. Nobody here has run it
/benchmark
Track codebase metrics over time.
When to use
- Weekly snapshot to watch trends
- Before/after a refactor
- The user says "track quality", "are we improving"
Commands
dragoon benchmark capture # take a snapshot
dragoon benchmark list # list snapshots
dragoon benchmark compare # compare latest two
dragoon benchmark show 2026-04 # show one matching prefix
What ships with it: 1 file
5.4 KB alongside SKILL.md, 1 of them executable
scripts/
- benchmark.jsruns5.4 KB