Dotu (@dotudev) header
Dotu (@dotudev) profile picture

I treat AI agents like my engineering team

Joined October 2026
ur Claude Code isn't dumb, ur setup is 馃槶 Claude Code Maxing, the stuff nobody tells u: 1. "think harder" does nothing special it's just normal text. if one prompt needs deep thinking, type ultrathink in it. it only boosts that one turn 2. stop telling it "don't be lazy, keep going" new models already finish the task. lines like that make it overdo stuff. if it stops early, just type continue 3. give it a check, not a promise "done" means nothing. tell it the test or typecheck command and ask it to show the output 4. want it to never skip a step? CLAUDE.md works most of the time, not every time. a Stop hook blocks it from finishing until ur check passes 5. /goal all tests pass and lint is clean it keeps working until that's actually true. perfect for long runs u aren't watching 6. don't explain ur folder structure in CLAUDE.md it reads the repo itself. only write what the code can't tell it 7. approving the same commands 50 times? /fewer-permission-prompts scans ur past sessions and allowlists the safe ones 8. /clear oauth-fix clears the chat but names the session, so u can come back to it later > bookmark this, ur next session will feel different 馃敄
1
1
17
Claude Code or Codex which one burns through your limit faster? 馃憖
39
Where does your coding agent actually run? Terminal IDE Cloud Which one are you using right now?
1
19
Replying to @kimmonismus
Hope that positive surprise turns out to be real
90
Agent called it done and the tests disagree.
200
Which side of that 40%+ are you on, writing or reviewing? Did review get harder once agents started the draft?
107
A single skill folder now runs across all of them? Which one did you reach for first?
64
Wait, pull requests turned into scorecards? Which check blocks the merge first?
125
Replying to @kimmonismus
GitHub Universe pulled you to SF and the keynote room always packs out fast.
9
The cheap models quietly got a lot cheaper this month. Three price moves worth a look in the card. Which one actually changes what you run day to day?
101
Another year older and the birthday GM still hits, that short bday note landed right in the middle of it
16
Agent said the bug was fixed. Tests disagree. Same error, third round. How many rounds before you stop trusting the fix?
120
Every coding agent shipped the same idea this month OpenCode, Codex CLI and Claude Code all cut the moments a human has to step in. The benchmark race looks boring next to this Which tool is winning on your machine?
2
230