{ "schema_version": 1, "generated": "2026-10-26", "id": "rsi-gear-gear--optimize-agent-on-own-task-set", "repo": "rsi-gear/gear", "repo_url": "https://github.com/rsi-gear/gear", "repo_slug": "rsi-gear-gear", "title": "Optimize an agent against your own task set", "page_title": "How to optimize an agent against your own task set with Gear", "summary": "Package your own tasks in Harbor format and run Gear's Refine Skill to improve the agent on them.", "who": "A developer who has a repeatable set of agent tasks with clear pass or fail criteria and wants the agent to get better at that specific work.", "problem": "No public benchmark matches your workflow, so the agent's failures on your real tasks go unmeasured and unfixed.", "outcome": "A harness tuned to your task set, with each version and its results recorded so you can compare changes and reuse the best harness.", "steps": [ "Build your task set in Harbor format by following the dataset guide, with a clear success criterion for each task.", "Run `npm install --global rsi-gear@latest agent-hitch@latest @deepseek-ai/dsh@latest` to install Gear and its runners.", "Run `hitch eval setup harbor` to set up the Harbor evaluation runner.", "Install the Refine Skill in your agent environment and point its configuration at your task paths, target harness, and model settings.", "Invoke `/refine` where supported and run one optimization round, then review the recorded harness versions and their results." ], "agent_prompt": "Use the Gear repo at rsi-gear/gear to optimize the harness of on my task set at . Report the pass rate for the starting harness and for the best retained harness. Verify that the task paths resolve and that the Refine Skill connects to Gear before the first run.", "agents": [ "codex", "claude-code" ], "difficulty": "Advanced", "time": "3 hours", "basis": "readme", "caveat": "Results are only as good as the tasks, so the success criteria in your Harbor tasks must be clear enough for Gear to score them.", "category": "Software and DevOps", "tags": [ "Software and DevOps" ], "lang": "typescript", "requirements": [ "npm installed, to run the global install of rsi-gear, agent-hitch, and DSH", "An agent environment such as Codex, Claude Code, or DSH that can use the bundled Refine Skill", "A benchmark of representative tasks with clear success criteria, either an existing one or your own in Harbor format", "Access to the models you choose for the Meta agent and the task agent" ], "risk": "none", "seen_in_the_wild": false, "mentioned_publicly": false, "risks": [], "best": false, "score": 0.9, "evidence": [], "url": "https://dedupedai.com/use-cases/rsi-gear-gear/optimize-agent-on-own-task-set/", "md": "https://dedupedai.com/use-cases/rsi-gear-gear/optimize-agent-on-own-task-set/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/rsi-gear-gear--optimize-agent-on-own-task-set.json", "api_version": "v1" }