better-harness
Use when /better-harness reviews the outer coding-agent Harness for lifecycle controls, repeated work, project feedback, agent assets, session outcomes, repair planning, durable reports, finding-bound fixes, or manual direct fixes. Invoke only via slash command.
npx skills add QoderAI/better-harness --skill better-harness --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Better Harness Review the coding-agent system: context, execution, control, feedback, and learning; keep Sessions, project, and Agent assets independent. ## Step 1: Resolve Scope and Collect the Evidence Bundle Route: - `<better-harness-fix-output>`: [Finding-bound Fix](references/finding-bound-fix.md). - No callback plus leading `fix`, `repair`, or `\u4fee\u590d`: [Manual Direct Fix](references/manual-direct-fix.md). - Review/evaluation/reporting or mixed review-and-fix: Step 1. Resolve the Skill path, `<better-harness-root>` as `../..`, a supported `<node>`, and `<cli>` as `<node> <better-harness-root>/scripts/better-harness.mjs`. Stop if any owner is missing; never select another cache or runtime by search order. Resolve the absolute target, decision, acceptance boundary, risks, locale (the user's request language unless explicitly changed), output mode, provider scope, and evidence depth. Quick uses three assets or Episodes and the previous 7 days; normal uses five and the previous 30 days. Default Qoder/Cursor to durable Canvas; default others to durable HTML. Only an explicit inline or no-files request writes nothing. Keep providers separate. Use the current one unless proj
- Step 1: Resolve Scope and Collect the Evidence Bundle
- Step 2: Run Three Independent Evidence Passes
- 2.1 Session Evidence
- 2.2 Project Harness Evidence
- 2.3 Agent Customize Evidence
- Step 3: Lead Reconciliation and Regrading
- Report Output — Step 4: Render an Authorized Report
- Step 5: Follow Up
What does the better-harness skill do?
Use when /better-harness reviews the outer coding-agent Harness for lifecycle controls, repeated work, project feedback, agent assets, session outcomes, repair planning, durable reports, finding-bound fixes, or manual direct fixes. Invoke only via slash command.
How do I install it?
Run `npx skills add QoderAI/better-harness --skill better-harness --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From QoderAI/better-harness, a repository with 1,619 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.