I was using Claude Code wrong... Here’s what I learnt and how I maximise Claude Code performance + Best tips that ACTUALLY useful 👇 Thread below

I keep hitting API error on Claude Code past 2 days Anyone has an affordable workaround? I can't easily switch to @cursor_ai /@cline because I want to keep continue a conversation lol

After testing @Kimi_Moonshot K2 for a few hours, My overall take: - Performance between Claude 3.5 & Claude 4 (Just my vibe eval!) - The UI generation seems great - But the cost is only 20% of Claude 3.5 - So good enough for most coding agent with a lot more manageable cost Easiest way to use Kimi K2 in Claude Code: - export ANTHROPIC_AUTH_TOKEN=YOUR_MOONSHOT_API - export ANTHROPIC_BASE_URL= - claude ------ Here are my tests & how to integrate to Claude Code: 1. Whole UI component library 2. Make online IDE UI 3. Build Functional mario game ...

Kimi K2 - On-par with Claude 4, but 80% cheaper!! I connected Kimi K2 to Claude Code to get a sense of real performance (Kimi Code!) Overall findings: 1. Exceptional coding capability 2. Cost only 20% of Claude 4 (Huge!) 2. Only downside is API is a bit slow 🧵 Below is some experiments I did + how can you test yourself 👇

AI generated UI always look similar Anyone has good tricks to get LLM design more custom slick UI?

After a few hours of research, Here are some best open source reference of how to build a 'Claude Code': - Open Code: - Gemini CLI: - Claude Code system prompt: ——— A basic coding agent compose of below: Agent: Can be basic tool call agent with system prompt + Tools: - Bash: Run command - Grep: Search for text within a file - Glob: Find finds - Read: Read code/pdf/img, etc. - Write: Create new files - Edit: Edit existing file, file_path, old_string, new_string -> Basically agent output exact old string to replace (surprised this was the approach, but make sense!) - MultiEdit: file_path + []array of old_string & new_string, when there are multiple places need to edit within a file ———— With the above you already get a semi-working Claude code agent, Some unique features to make it better: - Sub agent: Claude code has this dispatch_agent feature, to do deeper code base searching task (so it doesn’t mess up with the main conversation thread too much) - Thinking tool: A thinking tool to get agent do deeper analysis - Todo: Claude Code has create/update ToDo tool as their planning stage - Context management: Compress past conversation history for long running tasks, both gemini, claude code, open code has it, but an opt-in process - Codebase indexing: Claude code doesn’t index codebase, and it works perfectly fine; @cline also shared similar view: - Versioning: Gemini CLI has this checkpointing feature built in, which auto save a snapshot whenever Edit tool is called ----- One of key learnings here is even with basic setup (Base tools, no codebase index), agent already doing a great job; So keep the simplest setup possible and get the model do its work (e.g. I was surprised Edit tool just asking agent to output string to replace, and it does it well!) Comment below if i missed anything

Is there any typescript equivalent for LiteLLM package?

Is there any existing tool where I can spin up multiple terminal (e.g. multiple Claude Code instances) And send the same command to both terminals to get them execute the same task?

Should you use Claude Code SDK? My answer is - NO; We shipped v0.005 of @SuperDesignDev using Claude Code SDK last week (Prob the first product built on top of Claude Code SDK too) But a few issues: 1. Expensive - With Claude Code SDK, it is not using the Claude Code max plan, but consume Anthropic API credits and it is VERY expensive 2. Security risk - If you are building a cloud based coding agent, with Claude Code operating a sandbox, you will either risk exposing the Anthropic key as users can prompt hack it, OR you need to build a translation layer between Claude Code & sandbox environment --- Most importantly, as @Google released Gemini CLI, which is fully open-source, it gave us a good insights of how to build such coding agent - it is NOT that hard We can easily fork Gemini CLI repo with its agent tools and spin up our own custom agents; Gonna build custom coding agent for both @RelevanceAI_ & @SuperDesignDev Let me know if you guys will be interested in kinda 'How to build your own Claude Code' type tutorial, happy to break it down for ya

Cursor for Design? This Claude Code UI workflow is insane And many vibe coders not aware of it: 1. Claude Code can assign parallel tasks to sub agents 2. Integrate with git worktree to create sandbox env This means you can get Claude Code generate 10 design at the same time, fork & iterate 🔁 Design is an explorative process, by leveraging sub agent + parallel task capabilities, many interesting product UX can be built; Also turned this workflow into an open-source IDE extension here: