OPEN-SOURCE CLI · MIT · 100% LOCAL

Audit your repository’s AI harness in 2 seconds.

Run one command inside any repository to inspect your real agentic setup — context files, hooks, sandboxing, worktree hygiene, test oracles and CI gates. Zero API keys, zero code uploaded, deterministic Level 0–5 score.

  • 100% local by default
  • 6 Factory Stations
  • Level 0–5 Autonomy Ladder
  • Replaces scorecards & Setup Pack

Works with every coding agent and CI pipeline.

Start with the zero-config deterministic scan, then add qualitative review (--deep), a 7-question team interview (--interview), or a tailored fix prompt (--prompt).

Deterministic local audit (<2s, zero API keys, zero network calls)

npx @wondelai/harness-audit
  • Add --format html --out report.html for a shareable standalone report.
  • Add --prompt to emit HARNESS-FIX-PROMPT.md tailored to your exact missing checks.
  • Run npx @wondelai/harness-audit init for a minimal, non-destructive starter scaffold.

Four modes — from 2-second scan to minimal scaffold.

Everything the old web scorecards and static Setup Pack tried to do, rebuilt directly against your real repository.

default

Deterministic Scanner (<2s)

Inspects files, scripts, hooks, CI workflows, PR templates and git history locally. No LLM hallucination, repeatable in CI.

--deep

Qualitative LLM Review

Optionally invokes your own local claude/codex CLI or API key to critique rule bloat, vague acceptance criteria and brittle tests.

--interview --role dev|lead|cto

7-Question Org Interview

Adds the human and organizational dimensions files cannot show: review queues, risk-class merge policies and outcome metrics.

--prompt / init

Fix Prompt & Safe Scaffold

Generates HARNESS-FIX-PROMPT.md for your coding agent, or runs init to scaffold minimal AGENTS.md, CLAUDE.md and PR template without overwriting.

Sample output & local JSON report viewer.

Explore a realistic 6-station audit below — or paste/drop your own report.json from npx @wondelai/harness-audit --format json. Parsing runs 100% inside your browser.

acme/billing-api (sample)

Sample repository audit

Harness Score

64/100

Claude Code · Cursor

Autonomy Level

L3

Review Manager

Capping Station

Verification

Active Contributors

8

6 Factory Stations

  • 1. Intent 14/18

    PR template and architecture notes exist; missing explicit risk-class labels.

  • 2. Harness 14/20

    AGENTS.md & CLAUDE.md present, but Stop/PreToolUse hooks are not configured.

  • 3. Loop 13/16

    Single-command test and typecheck scripts verified in package.json.

  • 4. Graph 8/12

    CI runs tests, but worktree isolation and port hygiene are undocumented.

  • 5. Verification 7/20

    No oracle protection rule in CI and no architectural fitness functions.

  • 6. Release 8/14

    CI pipeline runs on PRs, but no automated AI PR review or evidence bundle.

Top Prioritized Findings

Inspect your own report.json locally

100% client-side JSON.parse — nothing leaves your browser.

Run npx @wondelai/harness-audit --format json > report.json and paste or load the file here. Zero data is sent to any server.

FOR CTOS, VPS OF ENGINEERING & CEOS

No terminal open? Delegate the 2-minute audit or book an external diagnostic.

You do not need to clone a repo yourself to see where your engineering organization actually sits on the Autonomy Ladder.

Send to your Tech Lead on Slack / Teams

Ready-to-paste message (100% local, zero source code leaves the company):

Hey — could you run `npx @wondelai/harness-audit --format html --out harness-report.html` on our main repo and send me the HTML summary? It runs 100% locally (MIT, zero code upload) and gives us a clean baseline of our AI harness & Level 0–5 bottlenecks.

Prefer an independent repo diagnostic?

Michał Jaskólski audits your main repository directly (written findings + prioritized 30-day roadmap from $499) or spends a full Working Day implementing hooks, CI gates and review standards with your team ($2,499).

See fixed-price team services

Fixed scope · Delivered personally · Written proposal first

Questions about @wondelai/harness-audit.

Does it upload my source code or send telemetry?

No. The default scan is 100% local, deterministic, offline-capable and sends zero telemetry or source code anywhere. The web JSON viewer on this page also parses everything locally in your browser with JSON.parse.

How does --deep mode work without vendor lock-in?

--deep automatically detects a locally installed claude or codex CLI (using your existing session) or accepts your own ANTHROPIC_API_KEY / OPENAI_API_KEY. It only runs when you explicitly pass --deep.

What happened to the old AI Dev Score quiz and Setup Pack?

A 25-question web survey measures self-perception; harness-audit inspects your actual repository and adds an optional 7-question --interview for org dimensions. And --prompt + init replace the old static Setup Pack ZIP with a tailored fix prompt based on what your repo actually lacks.

Is it really MIT open-source and free for commercial teams?

Yes — MIT licensed, free for solo developers and enterprises alike. If you want offline books for your team or hands-on implementation help, those are available on /en/books/ and /en/services/.

Does this page answer your questions?

One tap, no sign-in.

not at all fully

Measure your real harness — then climb one rung.

Run npx @wondelai/harness-audit in two seconds, read the free docs chapters for your top gaps, or bring us in for a fixed-price Repo Diagnostic.