Make Claude Code prove a fix's test fails without the fix
ehnruiz shared Claude Code skills and hooks that check a new test fails without the fix before the fix is accepted.
Source
ehnruiz on Hacker News · 2026-10-19 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-24.
What they did
ehnruiz shared Claude Code skills and hooks that check a new test fails without the fix before the fix is accepted.
Result (as claimed)
Tests that really guard the bug instead of passing anyway.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Claude Code. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Make Claude Code prove a fix's test fails without the fix What the original author did: ehnruiz shared Claude Code skills and hooks that check a new test fails without the fix before the fix is accepted. Reported result (as claimed by the author): Tests that really guard the bug instead of passing anyway. Source: https://news.ycombinator.com/item?id=50158230 Tools they used: Claude Code Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Make Claude Code prove a fix's test fails without the fix What the original author did: ehnruiz shared Claude Code skills and hooks that check a new test fails without the fix before the fix is accepted. Reported result (as claimed by the author): Tests that really guard the bug instead of passing anyway. Source: https://news.ycombinator.com/item?id=50158230 Tools they used: Claude Code Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Make Claude Code prove a fix's test fails without the fix What the original author did: ehnruiz shared Claude Code skills and hooks that check a new test fails without the fix before the fix is accepted. Reported result (as claimed by the author): Tests that really guard the bug instead of passing anyway. Source: https://news.ycombinator.com/item?id=50158230 Tools they used: Claude Code Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to use Claude Code skills and plugins · How to vibe code an app with Claude Code · How to automate work with n8n and AI
Related use cases
Have Claude Code review your Codex build from your phone
From his phone, ZazenCodes gets Codex on his computer to spin up Claude Code and pull its review of what Codex built.
Have CLAUDE.md import AGENTS.md so Claude and Codex share rules
Dainer_Jun's CLAUDE.md just imports AGENTS.md and routes the work, Codex reads AGENTS.md on its own, and work state lives in files too.
Wake Claude Code on GitHub comments only when they are worth it
fleyta88 described running Claude Code inside GitHub with a one-line filter that decides whether a comment should wake it, so emoji reactions don't burn usage, and nothing merges without approval.
Switch Claude Code skills on per project so they stop getting dropped
makosamunyaa found skill descriptions are capped at about 1% of context and the least-used get silently dropped, so he built Skillshed to enable vetted skills per project.