edonadei / caliper
Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Claude Code, Codex, Pi, and Hermes.
Why this job: topics: evaluation, evals
What it does
Your skill worked when you tried it. Will it work the next nine times? After the next model update? When another skill competes for the same prompt?
Get started
npx skills@latest add edonadei/caliper - Maintenance
- Active
- Last commit yesterday
- Stars
- 229
- +4 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.22.1
- Released yesterday
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 89% closed
- 12 still open
- Pull requests
- 202 merged
- 0 waiting
- Releases
- 30
- 30+ in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| GitHamza0206 / simba | 1,547 | 4 months ago | Apache-2.0 | No downloads |
| agentevals-dev / agentevals | 169 | 4 days ago | Apache-2.0 | No downloads |
| METR / hawk | 105 | today | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- ai-agents
- claude-code
- cli
- codex
- evals
- skills
- pi
- evaluation
- reliability
- hermes
- hermes-agent
- hermes-skill
Project record
- JobEvals and observability
- StatusListed
- Commits330
- Forks25
- Watching0
- Stars in 28 days+22
- CreatedMay 13, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026