Verification pipeline · Sheet 01

HYPERFIXER

Make AI agents prove their code works. hyperfixer runs your project's quality gates in cost order, cheapest first, fail-fast, and produces a machine-readable verdict that any coding agent consumes to fix its own mistakes.

✓ lint (67ms)
✓ typecheck (552ms)
✓ typetest (17ms)
✓ unit (120ms)
✓ pbt (38ms)
✓ e2e (814ms)

OK, all gates passed in 1612ms

OK · ALL GATES PASSED

Why layers

Agent-written code fails in layers, and each layer needs a different detector. Running everything on every change is wasteful; running only unit tests misses whole failure classes.

Layer	Catches	Tool
Lint	Style drift, suspicious patterns	Biome
Typecheck	Type errors	tsc, strict
Type tests	Wrong public API types	expect-type
Unit tests	Broken behavior	bun test
Property-based	Edge cases nobody thought to write	fast-check
Mutation	Tests that pass but assert nothing	Stryker, opt-in

Quick start

npm i -D hyperfixer            # or bun add -d hyperfixer, deno add npm:hyperfixer
bunx hyperfixer init           # detects your stack, writes hyperfixer.config.json
bunx hyperfixer doctor         # verify toolchain
bunx hyperfixer run            # run the pipeline
bunx hyperfixer install-hooks  # enforce on git commit and push

The agent loop

Note, agent loop run → verdict.json → hint → fix → repeat, until exit 0

hyperfixer fix --quiet || hyperfixer hint
=> [typecheck] src/service.ts:42, Type 'string' is not assignable to type 'number'. (+3 more)

Exit codes are a strict contract: 0 verified, 1 the code is wrong, 2 the setup is wrong, 3 gate infrastructure failed (do not edit code). Agents branch on the exit code alone, fix clears the autofixable noise, and hint gives the exact file and line to fix first.

Fast in practice

Gates with equal cost run in parallel. Gates that declare inputs are cached by input hash: an unchanged project re-verifies in milliseconds.

✓ lint (0ms), cache hit
✓ typecheck (0ms), cache hit
✓ e2e (0ms), cache hit

OK, all gates passed in 2ms