Claude Code tip: before you ship a vibe-coded site, have Opus 5.5 send out ๐ฑ ๐๐๐ฏ๐ฎ๐ด๐ฒ๐ป๐๐ to check ๐๐ต๐ฒ๐๐ฒ ๐ฎ๐ฌ ๐๐ต๐ถ๐ป๐ด๐, then fix them all in one pass:
Consistent design
โ Write a DESIGN.md first, and make every color, font size, spacing and corner radius follow it
โ Keep the palette restrained and the type hierarchy clear
โ Make every button, card and input of the same kind look alike
โ Too flat? Add emphasis. Too crowded? Cut
โ Keep text readable on both dark and light backgrounds
On mobile
โ No sideways scrolling, and nothing spilling off the screen
โ Add a mobile menu
โ Make buttons big enough to tap
โ Keep the layout intact when the text is enlarged
Every state
โ Give loading, empty and error states a proper screen
โ Give every button feedback, with its own hover, pressed and disabled look
โ Show form errors right where they happen, plus submitting, success and failure messages
โ Add transitions to modals, dropdowns and tab switches
Use it like a real user
โ Click through the core flows, like sign-up and checkout, from start to finish
โ Find buttons that do nothing and links that are broken
โ Make sure the whole thing works with just a keyboard
Before launch
โ Say what you do in one line on the home page
โ Give each page one main button you want people to click
โ Give every page a title, a description and a favicon
โ Delete all placeholder text
For effort, follow Anthropic's cost guide from yesterday: medium is for well-scoped daily work. The default medium is enough for these 20 fixes; raise it for the harder ones. Thariq tested it: turning effort up mostly buys more verification and edge-case testing.
Send this whole post to Claude Code. If you need to, add this line at the end ๐
"Send one subagent per group to check it without editing anything. Then fix everything yourself from their lists, so no two agents edit the same file. If a group is more complex, raise that subagent's effort. Show me the list of issues first, don't change anything until I confirm, and when you're done, give me before-and-after screenshots."
Vox
@Voxyz_ai
Vox @Voxyz_ai
Anthropic just published its ๐ณ๐๐น๐น ๐ฐ๐ผ๐๐ ๐ด๐๐ถ๐ฑ๐ฒ for Opus 5.5. You can ask Opus 5.5 to use it to review your Claude Code setup.
At the same effort level, Opus 5.5 thinks more per turn than Opus 5, most of all at xhigh and max. Thinking is billed as output, and an output
At the same effort level, Opus 5.5 thinks more per turn than Opus 5, most of all at xhigh and max. Thinking is billed as output, and an output
10:38 PM UTC ยท Sep 26, 2026 ยท 485K Views
461972.8K6.7K