paircoder

we spent 12 months teaching Python to babysit Claude Code 🐍
enforcement gates · 200+ commands · 7,500+ tests · 98% core coverage
stop hoping. start enforcing.

[paircoder @paircoder]

your CLAUDE dot md is a suggestion, not a rule. Claude can edit it. Claude can ignore it. Claude can agree with it and then do the opposite anyway.

200+ CLI commands. enforcement gates the AI can't bypass. 7,500+ tests.

Claude codes. Python enforces 🐍
https://t.co/BmFLrd5GLU

[paircoder @paircoder]

enforcement isn't about not trusting AI. it's about not trusting yourself to catch everything at 2am.

[paircoder @paircoder]

your AI just wrote 400 lines of clean code. now show me the 40 tests that prove it works.

[paircoder @paircoder]

the model writes the code. the tests decide if it ships. that's the whole system. 🐍

[paircoder @paircoder]

ownership should be queryable, not tribal knowledge. if "who owns this" requires asking a person instead of running a command, that's a gap. 🐍

[paircoder @paircoder]

your system should never report stale data as truth. if it says 12 things need attention and you already handled all of them, the system is lying.

[paircoder @paircoder]

cleaned up our git history today. if you've ever committed a secret and thought "i'll fix it later," later is now. scrub it.

[paircoder @paircoder]

just shipped a team model so any session can answer "who owns this project" without reading someone's notes. one table, one query.

[paircoder @paircoder]

the model changes every 3 months. your enforcement layer shouldn't. python gates don't care which model is running.

[paircoder @paircoder]

git diff main...HEAD before every review. don't let the model tell you what it changed. read the diff yourself.

[paircoder @paircoder]

claude code will auto-compact your context and lose your constraints mid-task. state files survive compaction. that's not a tip, that's architecture.

[paircoder @paircoder]

put your acceptance criteria in a markdown file, not in the prompt. the model can read it, reference it, and you can diff against it later.

[paircoder @paircoder]

tdd isn't slower with AI. it's faster. the model writes passing code in one shot when it has a failing test to aim at instead of vibes.

[paircoder @paircoder]

people ask why i run arch checks on every commit. because the third refactor is where the AI starts hiding complexity in god functions.

[paircoder @paircoder]

the AI is not your coworker. it's a contractor with amnesia. scope the task, write the AC, verify the output. every single time.

[paircoder @paircoder]

if your test suite passes when the AI writes the tests and the code in the same prompt, you don't have a test suite. you have a mirror.

[paircoder @paircoder]

the model layer is going to keep flipping every 3 months. the enforcement layer, structure, gates, quality control, that's the part that stays stable regardless of who's generating the code.

[paircoder @paircoder]

write your acceptance criteria before you prompt. not in the prompt, in a separate file the model can't edit. then make claude prove it met every line. that's the difference between "said it did it" and actually verifying.

[paircoder @paircoder]

spent the week building enforcement gates that won't let code ship without passing every acceptance criteria first. the AI writes fast. the gates decide if it wrote correctly.

[paircoder @paircoder]

your CLAUDE.md is editable by the thing it's supposed to govern. that's not enforcement. that's a sticky note on a door the AI has the keys to.

[paircoder @paircoder]

stop letting claude code auto-compact your context mid-task. if you're hitting the limit, you scoped wrong. one task per conversation. your rate limits will thank you.