#143143rd of 259 in Skills, plugins and prompts
better-harness
Plugin that audits a coding-agent workflow and reports evidence-backed findings
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 2.4k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Aug 2026
- Language
- JavaScript
4 on 21 Jul 20262,398 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Better Harness is a plugin and skill, run as /better-harness inside a coding agent. It collects project and session evidence, evaluates five Agent Work Loop dimensions, and writes findings with scoped repair plans and acceptance checks. Output is a self-contained report.html with report.md and findings.json, or a host-native Canvas in Qoder and Cursor. Missing evidence is marked explicitly rather than scored.
Who it is for: Teams using coding agents who want to audit and improve their workflow
Strengths
- Supports Claude Code, Codex, Qoder, Cursor, Copilot CLI, Qwen Code, Pi, Kimi Code, WorkBuddy, Grok
- Each finding links to evidence, expected output, repair boundary and acceptance checks
- Unobserved behavior stays explicit instead of becoming an unsupported score
- Public sample report and Harness Inspector demo; MIT licensed
Weaknesses
- No single entrypoint: install and invocation steps differ per host
- Cursor plugin is not published; install plan is reported as unavailable
- Copilot records no per-response token usage; VS Code Copilot Chat has no durable transcript
- Plugin lifecycle CLI is marked Beta; history shows trends, not causal proof
What it needs
- no GPU
- Needs Node.js >=22.20.0 <25 (source builds), npm >=10.9.3 <12 (source builds), A supported coding agent host
- Models: Depends on the host coding agent
Also in Skills, plugins and prompts
See all 259| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |
| 3 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| #4 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| #5 | oh-my-claudecodeMulti-agent orchestration plugin and CLI for Claude Code | 94 out of 100 |