{
 "schema_version": 1,
 "generated": "2026-10-26",
 "id": "microsoft-argusagent--evaluate-argus-as-a-harbor-agent",
 "repo": "microsoft/ArgusAgent",
 "repo_url": "https://github.com/microsoft/ArgusAgent",
 "repo_slug": "microsoft-argusagent",
 "title": "Benchmark the Argus runtime as a custom agent in Harbor",
 "page_title": "How to benchmark the Argus runtime as a custom agent in Harbor with Argus Agent",
 "summary": "Run the full Argus Manager, Planner, Engineer and Reviewer runtime inside Harbor Framework for evaluation.",
 "who": "An evaluation engineer who needs to compare Argus against other agents on the same Harbor tasks.",
 "problem": "Comparing agent systems fairly requires running each one through the same harness, and Argus is not wired into Harbor by default.",
 "outcome": "Harbor results that record how the bounded Argus runtime performed on the chosen tasks.",
 "steps": [
  "Install Docker, which the README lists as required only for the Harbor integration.",
  "Complete the basic Argus install with Node.js 22.12 or later and one authenticated Agent CLI.",
  "Open the Harbor integration guide at docs/harbor.md.",
  "Register Argus as a custom agent in Harbor by following that guide.",
  "Run your Harbor task set and read the results alongside the Argus status output."
 ],
 "agent_prompt": "Using the microsoft/ArgusAgent repo, follow docs/harbor.md to run the Argus runtime as a custom agent in Harbor Framework on the task set <task set name>. Expect Harbor's result report for each task. Verify that the runtime ran in its bounded form and that each task result links back to its Argus run.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "2 hours",
 "basis": "readme",
 "caveat": "The README describes Harbor as a separate integration, so it is not part of a normal Argus install and needs its own guide.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "Node.js 22.12 or later",
  "One authenticated Agent CLI, such as GitHub Copilot CLI, OpenAI Codex CLI, or Claude Code",
  "A project folder you are willing to let the agents modify"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/microsoft-argusagent/evaluate-argus-as-a-harbor-agent/",
 "md": "https://dedupedai.com/use-cases/microsoft-argusagent/evaluate-argus-as-a-harbor-agent/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/microsoft-argusagent--evaluate-argus-as-a-harbor-agent.json",
 "api_version": "v1"
}