{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "yuyaoge-doc2harness--score-existing-agent-harness",
 "repo": "YuyaoGe/doc2harness",
 "repo_url": "https://github.com/YuyaoGe/doc2harness",
 "repo_slug": "yuyaoge-doc2harness",
 "title": "Score an existing coding agent harness",
 "page_title": "How to score an existing coding agent harness with Doc2 Harness",
 "summary": "Run all 94 released scenarios against your product directory and get a pass rate.",
 "who": "A developer who has a coding agent product in a directory and wants an objective pass rate before a release or comparison.",
 "problem": "Checking whether a coding agent harness really enforces its rules and behaves correctly across file, permission, state, and startup cases is slow to do by hand.",
 "outcome": "A JSON receipt for each scenario plus catalog_receipt.json, with a score of pass divided by pass plus fail over applicable scenarios.",
 "steps": [
  "Run `docker build --target evaluation -t doc2harness/evaluation:candidate -f containers/Dockerfile .` from the repo root (see containers/README.md for mirror options).",
  "Confirm your product directory contains src/yuyao/, then run `PYTHONPATH=src:tools:run python3 tools/run_production_catalog.py --artifact /path/to/product --artifact-id my-product --output /tmp/scores --concurrency 12 --timeout 300`. (inferred, check the README)",
  "Wait about 25 to 90 seconds at concurrency 12 for the full catalog to finish.",
  "Open /tmp/scores/catalog_receipt.json and read the score, remembering that INCONCLUSIVE is not counted as a failure."
 ],
 "agent_prompt": "Use the repo YuyaoGe/doc2harness to score the product at <path-to-product-directory>. Run tools/run_production_catalog.py with --artifact <path-to-product-directory> and --output <output-dir>, then report the pass and fail counts from catalog_receipt.json. Verify that the product directory contains src/yuyao/ before running.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "30 minutes",
 "basis": "readme",
 "caveat": "The README says the leaderboard numbers come from the full 328-case suite and cannot be reproduced from this 94-scenario subset alone.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "Python 3.11 or newer",
  "Docker installed and running",
  "The repo cloned locally",
  "For building a new harness only: the builder image, a local LiteLLM gateway, and your own API key"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/yuyaoge-doc2harness/score-existing-agent-harness/",
 "md": "https://dedupedai.com/use-cases/yuyaoge-doc2harness/score-existing-agent-harness/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/yuyaoge-doc2harness--score-existing-agent-harness.json",
 "api_version": "v1"
}