---
title: "Deleting 1,410 safety checks on purpose to see which ones the tests miss"
date: 2026-11-09
url: "https://morningtokens.com/workflows/deleting-1-410-safety-checks-on-purpose/"
source: "https://x.com/tom_thomasson/status/2118745575113851100"
issue: "https://morningtokens.com/issues/2026-11-09/"
---

# Deleting 1,410 safety checks on purpose to see which ones the tests miss

## How does this AI workflow work?

- **Replaces:** trusting a growing agent-written test suite on faith, and being the copy-paste layer between two coding agents.
  - Agents removed 1,410 safety checks from the code one at a time and re-ran the tests: 1,297 were caught, 113 slipped through, 91 of those were real gaps and each now has a test pinning it.
  - A supervisor passes work between Claude Code and Codex, which landed 12 packages in 4 days (suite at 6,329 tests).
  - The same idea was used on AI-written market reports: 28 planted errors (wrong prices, bad maths, invented figures), all 28 caught by an AI reviewer.
  - Honest scoreboard included: consulting calls booked 0 of a goal of 3.
- **What to connect:** Claude Code and Codex with a supervisor that routes work between them, a test runner the agents can call, and a reviewer agent for generated reports.
  - A separate model (ChatGPT here) audits live pipeline runs against the governance rules.
  - No cost stated.
- **Who it's for:** solo developers and small teams shipping agent-written code or reports who want proof that their checks actually catch failures.

Source: https://x.com/tom_thomasson/status/2118745575113851100

From the Morning Tokens issue of 2026-11-09: https://morningtokens.com/issues/2026-11-09/
