HarnessFit · Bespoke Harness Environment Benchmark (BHEB)
AI Coding Cost, Drift & Readiness Diagnostics
Home
Zero Install · 0 LLM Tokens · Zero Source Code Uploaded

See what your AI coding setup costs to run — and what is quietly drifting.

HarnessFit (powered by BHEB) audits any repository in under 2 seconds. Measure your hidden startup token tax, catch stale rules and broken Cloud VM links, and compare against peer setups — right from your browser.

1. Scan Any Public GitHub Repository
Try instant scan:
Fetches public repo structure & startup rules directly from GitHub in your browser.
2. Scan a Local Repo or Projects Folder (1 Click)
Runs 100% in browser RAM (single repo or entire projects/ folder). Nothing leaves your laptop.
Real Operating CostHarness Tax

See exact eager startup tokens loaded on every turn and projected spend per 1,000 turns across DS4, MiniMax M3, Kimi, GLM, Flash, Haiku, and 470+ OpenRouter models.

High-Leverage FixesActionable

Catch real production harness drift: stale .claude/SYNC_STAMP mirrors, OS-hardcoded paths breaking Linux Cloud VMs, missing test nets, and divergent AGENTS.md rules.

Zero-Trust Privacy100% Local

Default scans use 0 LLM tokens and upload nothing. Unlock deeper fixes & saved history via passwordless Email Magic Link only when you choose.

Returning user?