Devashish Jadhav

@Im_IrushiK Your session limit resets at 02:30 AM

I'm a vibe coder, scare me with one word.

@md_kasif_uddin is it just me who uses yarn

What’s your preferred package manager?

@lydiahallie there are no updates from anthropic if the limits are going to be fixed or are they fixing it. Whats exactly is going on?

@TTrimoreau Claude is just being annoying right now really with its limits

OpenAI vs Anthropic Who’s actually ahead right now?

@Star_Knight12 One prompt

bro claude's $20 plan is seriously so trash 3 prompts and it's already over, what the fcuk

@manoj_ahi One prompt costed me this

Ok enough!! time to cancel my claude subscription is codex any good?

Just one prompt costed me this

@lydiahallie I know you guys are trying hard but this is too much just one prompt and its hitting its limit😞

Most developers think Claude Code = terminal + prompt. That barely scratches the surface. The real power of Claude Code isn’t the prompt. It’s the system around the prompt. Once you understand this, everything changes. Claude Code actually works like a 4-layer AI engineering system: 1️⃣ CLAUDE.md → Project memory Persistent context for your project. Stores rules, conventions, and architecture decisions. 2️⃣ Skills → Reusable knowledge packs Claude automatically invokes them when relevant. Think: reusable workflows and expertise. 3️⃣ Hooks → Deterministic guardrails Safety gates that run automatically. Unlike prompts, hooks are 100% enforced. 4️⃣ Agents → Specialized sub-agents Each with their own context window. Great for complex, multi-step tasks. Most engineers install Claude Code and immediately start prompting. But the difference between average output and production-level results usually comes down to setup. Practices that make a huge difference: → Run /init on day one to generate CLAUDE.md → Organize the .claude/ directory (skills, hooks, permissions) → Write clear skill descriptions so Claude knows when to trigger them → Use the memory hierarchy (global → project → folder) → Add hooks for critical rules (hooks = enforced, memory = advisory) When structured properly, Claude Code stops feeling like a chatbot. It starts behaving like a real AI development system. If you want to learn it properly, Anthropic released several free courses: Claude 101 anthropic.skilljar.com/claude-101 AI Fluency: Framework & Foundations anthropic.skilljar.com/ai-fluency-fra… AI Fluency for Students anthropic.skilljar.com/ai-fluency-for… AI Fluency for Educators anthropic.skilljar.com/ai-fluency-for… Teaching AI Fluency anthropic.skilljar.com/teaching-ai-fl… Also includes developer topics like: • Claude Code in Action • Building with the Claude API • Prompt Engineering tutorials • Model Context Protocol (MCP) fundamentals Bookmark this if you're building with Claude. The future of AI development isn't just prompts. It's systems around prompts. #AI #Claude #AIAgents #LLM #GenAI #AIEngineering

@delveroin 2 years into my dev career and this kills me: Pick ticket → read code → no idea why it exists. Ticket closed. Ask senior dev → he forgot too. So I built Loom — links Jira tickets to the code that implements them. github.com/ddevilz/loom

Builders on X What are you building right now? An app? A startup? A side project? Content? I want more builders on my timeline. Let’s connect

@S_N_SH_E_ 2 years into my dev career and this kills me: Pick ticket → read code → no idea why it exists. Ticket closed. Ask senior dev → he forgot too. So I built Loom — links Jira tickets to the code that implements them. github.com/ddevilz/loom

Devs, What are you building right now? Reply with: Project name + 1 line about it + Link

@abhijitwt 2 years into my dev career and this kills me: Pick ticket → read code → no idea why it exists. Ticket closed. Ask senior dev → he forgot too. So I built Loom — links Jira tickets to the code that implements them. github.com/ddevilz/loom

Drop your project URL Let’s drive some traffic

Early stage. Solo build. Open source. I’ll be posting every step here as I build. Follow if this problem sounds familiar

No existing tool does this. Jira shows you tickets. Sourcegraph helps you search code. But nothing connects why a piece of code exists to what happens if you change it.

2 years into my dev career and this already kills me — Pick up a ticket → read the code → have no idea why it exists → original ticket closed → ask senior dev → even he forgot So I’m building something. 🧵 github.com/ddevilz/loom

@heyblake 2 years into my dev career and this kills me: Pick ticket → read code → no idea why it exists. Ticket closed. Ask senior dev → he forgot too. So I built Loom — links Jira tickets to the code that implements them. github.com/ddevilz/loom

Drop your project URL Let’s drive some traffic