{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "heycubit-effortless--benchmark-the-judge-on-your-own-setup",
 "repo": "HeyCubit/effortless",
 "repo_url": "https://github.com/HeyCubit/effortless",
 "repo_slug": "heycubit-effortless",
 "title": "Test how often the effort judge picks the right level",
 "page_title": "How to test how often the effort judge picks the right level with Effortless",
 "summary": "Run the bundled judge benchmark on your own Claude Code setup before trusting Auto.",
 "who": "A team lead or careful developer who wants evidence that the automatic effort judge picks sensible levels for their kind of work.",
 "problem": "The automatic judge's accuracy is only shown in the README on a fixed set of 73 cases, which may not match your work.",
 "outcome": "The user gets scores for each judge they have set up, measured against labelled prompts, and can compare them with fixed effort levels.",
 "steps": [
  "Install Effortless as described in the first use case.",
  "In Claude Code, run `/effortless bench` to score each judge you have set up on the labelled cases.",
  "Read the table of right answers, too low and too high counts, and median time.",
  "To rerun the cost benchmark, run `bash bench/agentic/run.sh` from a clone of the repo, knowing it makes real API calls and costs money."
 ],
 "agent_prompt": "Clone HeyCubit/effortless, run `bash bench/agentic/run.sh` and report the cost per task for each effort setting it prints. Confirm the output matches the table in bench/RESULTS.md within a reasonable margin before drawing conclusions.",
 "agents": [
  "claude-code"
 ],
 "difficulty": "Advanced",
 "time": "45 minutes",
 "basis": "readme",
 "caveat": "The README says the judge results come from 73 cases and that runs differ by a few points, and the cost benchmark makes paid API calls.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "html",
 "requirements": [
  "Claude Code installed",
  "A Claude login (the default judge runs on it, no key needed)",
  "git available if you want update checks, as the README mentions"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.7,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/heycubit-effortless/benchmark-the-judge-on-your-own-setup/",
 "md": "https://dedupedai.com/use-cases/heycubit-effortless/benchmark-the-judge-on-your-own-setup/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/heycubit-effortless--benchmark-the-judge-on-your-own-setup.json",
 "api_version": "v1"
}