Clément Rog

you now can use google analytics mcp in claude setup in claude: 1 min setup Google Auth: 12 steps (good luck) feels good not to have to fight GA4 UI anymore MCP repo github.com/googleanalytic…

It works like a charm paired with @raycast snippets! Even faster double-model workflow unlocked. Star the repo if it saves you time ✌️

claude-copy just dropped 🔥 Instant keyboard shortcuts to copy ANY Claude Code output to clipboard. No selecting text, no scrolling. Just Cmd+Shift+C/P/A in Kitty or iTerm2. Works for questions/plans/normal output. Perfect for pasting into ChatGPT, Gemini, Grok or whoever you trust for a second opinion. Try it: github.com/clementrog/cla…

Everyone thinks Claude Opus is a cheat. It’s good, for sure. But the actual cheat is: your favorite model’s output + sharp feedback from a second model. Double-pass feels tedious at first…but delivers ~5× quality and slashes revisions dramatically

8/ "Separate reasoning from execution, get same results" is close to reality, especially with Cursor new Composer 1.5! If you're one of ~2K Pilot users (my previous workflow) i'm sure you'll like this 3x more. Repo: github.com/clementrog/cla…

7/ And to me it feels promising because it reduces Opus 4.6 context (needs less compacting, more token efficient ofc), Composer 1.5 from Cursor is fast (and Cursor indexing works through CLI). I almost code unlimited for 40€/month without noticeable quality drifts.

1/ I was burning through €100+/month on AI-assisted coding. Most of it on tasks that didn't need frontier-level reasoning. So I built a system that uses Claude for thinking and Cursor for typing. Costs ~€40/month now. Here's how!

Still prototyping layouts in plain HTML + CSS. No server, no build. Just refresh. Debug borders + tinted backgrounds until alignment is locked. Then port to real code. Feels old school but nothing's faster for iteration. Anyone else work this way?

@danvibecode Working on it to make Claude great again. May have a fix

@clementrog It was a good run while it lasted. Given Anthropic's poor PR, I wouldn't expect an announcement. Codex allows using ChatGPT pro / plus plans with Opencode, worth a shot.

Did Anthropic just quietly break OpenCode for Claude Pro/Max? Getting “Claude Code only” on every request (worked yesterday). Anyone managed to make it work again?

Still not found a solution besides using Claude code

Pilot v3.1.0 — stricter by design. Git diff required on ALL verifies. Evidence mandatory. Secret reads = hard violation. Less trust, more proof. Also in v3: batch mode, design contracts, skills system. github.com/clementrog/pil…

I built my own workflow for this. Open-source, optimized for .JSON machine/machine coordination. One model thinks, breaks downs into tasks, ask for reviews when relevant. Another builds. Model agnostic. Copy paste in your repo to initialize. No magic, just encoded discipline. github.com/clementrog/pil…

I've been running this way for six months. ~$60/month total. Zero "usage limit reached" messages. The real constraint isn't tooling—it's having a system that forces the split automatically, without thinking about it.

I've seen devs stack $200-300/month in AI subscriptions and still hit limits every other day. The instinct is always "I need more quota." Wrong diagnosis. The problem isn't token supply. It's how you're spending them.