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

I treat AI agents like my engineering team

Joined October 2026
Photo by Dotu (@dotudev)Photo by Dotu (@dotudev)Photo by Dotu (@dotudev)Photo by Dotu (@dotudev)Photo by Dotu (@dotudev)Photo by Dotu (@dotudev)Photo by Dotu (@dotudev)Photo by Dotu (@dotudev)Photo by Dotu (@dotudev)Photo by Dotu (@dotudev)
Claude Code made me 10x faster at building It did not make me 10x faster at launching I have more finished side projects than ever and almost none of them are live Turns out the bottleneck was never the code
1
2
7
Hey @grok, center a div. One of the HARDEST problems in tech. Don't be DUMB
1
1
9
Underrated Claude Code advice: When it finishes a feature, open a fresh session and ask it to review the code like it's someone else's PR. The same chat defends its own code. A fresh one actually finds the bugs.
2
1
16
ur Claude Code isn't dumb, ur setup is 😭 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 🔖
1
1
17
claude is halfway through a refactor then the session limit hits reset is in 40 min what's your move?
1
14
you asked for a one line fix the agent rewrote 14 files and "cleaned up" three folders you didn't mention what's your move?
30
Claude Code or Codex which one burns through your limit faster? 👀
39
Claude had two incidents yesterday. Logins broke for about 2 hours, then the API and Claude Code threw elevated errors for a couple more. The fallback flag only covers overload. Not login, not rate limits. I keep the plan in a file in the repo so switching agents mid-task isn't a restart.
1
34
What's the first thing you'd hand off to an AI agent if you could trust it 100%? Emails Coding Marketing Customer support Marketing for me. I'd build all day if someone else posted.
1
37
Developers, which one would you pay for if you could only keep one: Claude Code, Codex, or Cursor?
24
Quick bet for the Claude users here. One year after the IPO, what changes first? Pricing Rate limits Release speed Nothing I'm saying rate limits.
Our initial public offering: ipo.anthropic.com Legal disclaimer: Anthropic has filed a registration statement (including a prospectus) with the SEC for the offering to which this communication relates. Before you invest, you should read the prospectus in that registration statement (available at: sec.gov/Archives/edgar/data/…) and other documents Anthropic has filed with the SEC for more complete information about Anthropic and this offering. You may get these documents for free by visiting EDGAR on the SEC Web site at sec.gov. Alternatively, copies of the preliminary prospectus may be obtained from: Goldman Sachs & Co. LLC, Attention: Prospectus Department, 200 West Street, New York, NY 10282, by telephone at (866) 471-2526, or by email at [email protected]; or Morgan Stanley & Co. LLC, Attention: Prospectus Department, 180 Varick Street, 2nd Floor, New York, NY 10014. The securities may not be sold, nor may offers to buy be accepted, prior to the time the registration statement becomes effective. This post is not an offer to sell, or a solicitation of an offer to buy, the securities in any jurisdiction where the offer or sale is not permitted.
1
1
34
Where does your coding agent actually run? Terminal IDE Cloud Which one are you using right now?
1
19
A CLAUDE.md file asks Claude to behave. A hook enforces it. It runs a shell command at a fixed point in the run, whether the model remembers the rule or not.
2
1
199
The hook gets JSON on stdin with what Claude is about to do. It answers with an exit code. Exit 2 on a PreToolUse hook blocks the call and hands the reason back to Claude.
1
109
Start with these two. A PostToolUse hook that formats every file Claude edits. A PreToolUse hook on Bash that blocks rm -rf before it runs. What would you block first?
104
If the same instructions keep going into Claude Code, stop pasting them. Write the block down once as a skill and let Claude load it when the job matches.
1
1
211
Personal skills live in ~/.claude/skills/ and follow you across projects. Project skills live in .claude/skills/ and travel with the repo. Run it with /skill-name or let Claude pick it up from the description.
1
87
Skills that touch real things get one extra line. disable-model-invocation: true stops Claude loading it on its own. A deploy skill only runs when you type its name. What is the first instruction you would never paste again?
77