Better Harness

See how your AI coding workflow works—and make it better, one step at a time.

Better Harness reviews how coding agents understand tasks, make changes, verify results, deliver safely, and learn—then shows what to improve next, with every finding tied to visible evidence.

Quick Start · Demo · Why · What's open · Installation · Host support · Roadmap · Contribute

See it in action

Ask /better-harness to review the current task and its surrounding project
Harness, then generate a durable report:

/better-harness review this project's AI coding workflow and generate a report

The report keeps missing evidence explicit and turns supported gaps into
prioritized findings with an impact, expected output, scoped repair, and
acceptance checks.

_{Open the complete self-contained English HTML report.}

After you have comparable reports over time, the history view shows how the five
Agent Work Loop dimensions move:

The animation replays historical Harness reports. It shows recorded trends, not
causal proof of improvement. See how the demo was recorded.

Why Better Harness?

AI coding agents change code fast, but the workflow around them is often the
weak point:

• 🎯 Fuzzy goals — the agent confidently solves the wrong problem.
• 🧭 Improvised steps — work happens on paths nobody can reproduce.
• ✅ "It works" without proof — validation is incomplete or missing.
• 🚢 Speed over safeguards — review and delivery checks get bypassed.
• 🧠 Lessons lost — the same friction comes back on the next task.

Reviewing only the final diff misses these system-level problems. Better Harness
reviews the workflow itself: it gathers project evidence (and session evidence
where supported), evaluates five connected dimensions, and turns concrete gaps
into prioritized findings — each tied to its evidence, expected outcome, repair
boundary, and validation route, so a team can improve one issue at a time.

How Better Harness works

Better Harness uses a
feedforward-and-feedback
loop that combines guidance available before work starts with signals available
after the agent acts:

• Feedforward guides — AGENTS.md, specs, Skills, and acceptance criteria
  steer the agent before it acts.
• Feedback sensors — linters, tests, Hooks, and review agents observe results
  and help the agent self-correct.

Across that loop, it evaluates five parts of delivery — the Agent Work Loop:

Running /better-harness establishes a task-bounded baseline and, depending on
the host, produces a visual report, a Markdown report, or both. The report
combines the five-part overview, prioritized findings, detected agent assets,
and an evidence brief. Each finding includes a repair action that drafts a
scoped fix plan for review.

Better Harness is deliberately honest: unobserved behavior stays explicit instead
of becoming an unsupported score or claim. Passing a current check proves that
the intervention was exercised; only a comparable later result can prove that
the loop improved.

What is open

Better Harness opens three connected layers, not only a slash-command prompt:

• Engineering practices — evidence and judgment guidance across
  Session Evidence, Project Harness, Agent Customize, and Loop Engineering.
• Evaluation model — the task-centered
  Agent Work Loop, including evidence states,
  findings, scoring boundaries, and longitudinal validation.
• Runnable implementation — the canonical
  /better-harness workflow, evidence
  collectors, analyzers, renderers, and thin
  host adapters.

The three layers share the same boundary: configured assets can establish that
a mechanism exists, but only linked task evidence can establish that it was used
or improved an outcome.

Architecture

The architecture keeps the three evidence domains independent until unified
analysis by the lead agent. Every result retains a visible evidence source,
owner, and validation route.

Quick start

Pick your coding agent — you can be looking at your first report in minutes:

Once installed, ask Better Harness to generate the host's durable report:

/better-harness review this project's AI coding workflow and generate a report

Better Harness scopes behavior claims to relevant Task Episodes and the
surrounding project mechanisms. Qoder produces a Canvas report; Claude Code,
Codex, and Cursor produce self-contained HTML with paired Markdown. Missing or
partial evidence remains explicit. See the
Host Adapter Matrix for current coverage and output
differences.

Installation

Installation differs by coding agent. Install Better Harness separately for
each host, except that Qoder CLI can use the version bundled with Qoder Desktop.
After installing or updating a plugin, start a new session or task so the host
reloads its plugin inventory.

Claude Code

Register this repository as a Claude Code marketplace:

/plugin marketplace add QoderAI/better-harness

Then install Better Harness:

/plugin install better-harness@better-harness

Verify discovery from the shell:

claude plugin details better-harness@better-harness

The details should include Skills (1) better-harness. Then start a new Claude
session in the repository you want to review and run the report prompt:

/better-harness review this project's AI coding workflow and generate a report

Claude Code defaults to a self-contained report.html with paired report.md
and findings.json under the repository's .claude/better-harness report root.
Ask for inline or no-files output to keep the result in chat only. Workspace-
matching local Claude sessions are included when available; missing evidence
stays explicit rather than being inferred.

Codex

Codex Desktop

1. Open Settings > Plugins.
2. Select + Add > From Marketplace.
3. Enter the Git repository URL, set its Git ref, and leave Sparse paths
   empty for this single-plugin repository.
4. Select Add marketplace, then install Better Harness from the new
   marketplace.
5. Start a new task in the repository you want to review and use the report
   prompt from Quick start.

Use https://github.com/QoderAI/better-harness.git with Git ref main.

Codex CLI

Add the repository source:

codex plugin marketplace add \
  'https://github.com/QoderAI/better-harness.git' \
  --ref main

Then inspect and install Better Harness:

codex plugin list --marketplace better-harness
codex plugin add better-harness@better-harness

Start a new Codex task in the repository you want to review and run the report
prompt:

/better-harness review this project's AI coding workflow and generate a report

Use the repository URL with marketplace add, not a raw marketplace.json
URL. Current Codex builds use plugin add and --marketplace; examples that
use plugin install or --source target a different CLI contract.

Qoder

Better Harness is built into the Qoder desktop app, so no
Marketplace or local plugin installation is required there. Choose either
entry point:

1. From a session: Open the repository you want to review, start a new
   session, and run the report prompt:

   /better-harness review this project's AI coding workflow and generate a report
   

2. From Quest (Qoder 1.18.0+): Open Quest, then select
   Better Harness (Beta) from the left sidebar.

Qoder CLI

If Qoder Desktop is installed, Better Harness is already available in Qoder
CLI. No marketplace or plugin installation is required. Start a new Qoder CLI
session in the repository you want to review and run the report prompt:

/better-harness review this project's AI coding workflow and generate a report

Only when using Qoder CLI without Qoder Desktop, add this repository as a
marketplace and install Better Harness manually:

qodercli plugin marketplace add \
  'https://github.com/QoderAI/better-harness.git'
qodercli plugin install better-harness@better-harness

Verify the manual installation:

qodercli plugin list

Then start a new Qoder CLI session before using /better-harness.

Cursor

The Cursor plugin is not published to the marketplace yet. Load the
source-local plugin for one Cursor Agent session:

git clone https://github.com/QoderAI/better-harness.git
cursor-agent --plugin-dir /path/to/better-harness

Cursor session evidence is supported through workspace-matched transcripts,
metadata, and audit logs. Partial or unavailable coverage remains explicit.

Develop and package from source

Development requires Node.js >=22.20.0 <25.0.0 and npm
>=10.9.3 <12.0.0 on Windows, macOS, or Linux.

npm ci
npm test
npm run pack:verify

Build the source-local Codex plugin artifact with:

node scripts/packaging/build-host-plugin.mjs

The validated artifact is written to dist/plugins/better-harness.

From the same source checkout, inspect repository evidence without reading local
sessions:

node scripts/better-harness.mjs report --no-sessions

From a source checkout, npm run preview -- --open serves a bundled fixture.
Canvas preview requires an installed Qoder runtime, or an explicit
--sdk-media/--sdk-root path. It listens on 127.0.0.1 by default and is a
local inspection tool, not an authenticated sharing service.

Contribute

You do not need to understand the whole runtime to contribute. Start with the
smallest surface that matches the improvement you want to make:

To get started:

1. Read the community extension map to choose the canonical
   owner and understand its contract.
2. Follow the contribution guide to set up the project and
   scope the change.
3. Add tests, fixtures, or preview evidence when the contribution changes
   runtime behavior or rendered output.
4. Open a focused pull request that explains what changed, why, and how it was
   validated.

Not sure where an idea belongs? Open an issue
before building a new top-level surface or changing a public report, schema,
packaging, or compatibility contract.

License

Better Harness is licensed under the MIT License.

If Better Harness helps you improve your agent workflow, consider giving it a ⭐ — it helps others find the project.