Home / Skills / devtu-benchmark-harness
devtu-benchmark-harness
mims-harvard/ToolUniverseSkill
Continuous improvement system for ToolUniverse tools, skills, and plugin. Run benchmarks, diagnose failures, route fixes to devtu skills, retest. Use after skill optimization, tool additions, or as regression check.
Why this score
This repo hosts 10 skills, so its 1,747 stars are split between them (about 175 each) for scoring.
Popularity score: 72/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 21, 2026 at commit 265848d91a74, with Cisco's open-source skill-scanner.
What its code does:
- Runs shell commands Common for dev tools. Read the commands it runs.scripts/run_harness_loop.sh:47, scripts/solve_one.sh:37 and 3 more
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This onedevtu-benchmark-harness mims-harvard/ToolUniverse · Skill | 72 | ★ 1.7k | ≈60 always | 16d ago |
| benchmark garrytan/gstack · Skill Both about benchmark and regression | 93 | ★ 137k | ≈14 always | 16d ago |
| harness revfactory/harness · Skill Both about harness | 83 | ★ 9.2k | ≈80 always | 1mo ago |
| benchmark-workflow xberg-io/xberg · Skill Both about benchmark and harness | 79 | ★ 9.4k | ≈64 always | 16d ago |
| benchmark-analyst growthack88/growth-marketing-os · Skill Both about benchmark | 60 | ★ 122 | ≈22 always | 25d ago |
| add-benchmark allenai/vla-evaluation-harness · Skill Both about benchmark | 72 | ★ 650 | ≈37 always | 20d ago |