ClaudeCode Community
@claude_code
Followers
13K
Following
46
Media
25
Statuses
50
Community account for sharing ClaudeCode related projects and releases. Views/shares independent from @AnthropicAI positions.
United States
Joined March 2025
Tip: . Try approaching @claude_code and its underlying models as an intelligence, rather than merely a Q&A chatbot or an answer machine. 1) If you’re thinking of something open-ended. Proactively ask it to pose clarifying questions back to you. This is often an overlooked step.
btw by far the most interesting new pattern we are seeing in @latentspacepod (upcoming with @olivierddr and @sdrzn and @pashmerepat) . is that people are using @claude_code and @Cline for non-coding tasks and this is becoming surprisingly effective for things like sales/BI
3
5
60
PSA: There is a spike in intermittent errors on Opus. Tip: .Switch to Sonnet (`/model`) to mitigate. It's effective for executing tasks. API Error 529 - overloaded_error: Anthropic’s API is temporarily overloaded.
8
7
82
1) Try Bun @bunjavascript for faster compilation than (p)npm or Yarn. Bun fetches and installs packages in parallel. 2) Consider a Claude Max subscription if you're exceeding credits: 5x ($100/month) or 20x usage ($200/month) limit. 3) Use `ccusage` to track Claude code usage.
got claude code max subscriptions for all the engineers at bun after looking at my usage
8
11
165
Tip: Use subagents on @claude_code. @claude_code supports ~10 parallel tasks, coordinating via a task queue. Avoid specifying parallelism; let Claude Code determine task distribution. Cuong's article, "Claude Code: Subagent Deep Dive" is worth the read. @codecentrevibe
19
83
894
Tip: "export ENABLE_BACKGROUND_TASKS=1" . To keep long-running tasks in the background.
Claude Code pro tip:. add this line to your .zshrc or .bashrc (ask CC to do it for you) and you can move long running tasks to the background to keep chatting. export ENABLE_BACKGROUND_TASKS=1
2
6
51
Treasure Trove of Actionable Information for Multi-agents. Tip for @ claude_code users: Launch subagents by requesting it. "Explore codbase with 3 parallel tasks. Each agent handles a different stack ( frontend, services, database ) and updates the readme README." . ---. Key
New on the Anthropic Engineering blog: how we built Claude’s research capabilities using multiple agents working in parallel. We share what worked, what didn't, and the engineering challenges along the way.
6
44
484
Tips:. 1) Plan with Opus and execute with Sonnet. Shift + Tab to toggle. 2) Use to clarify project terminology and venv setups. 3) Use `ccusage` to track usage. Claude Max subscription offers 5x ($100/month) and 20x usage ($200/month).
C++ dev and ex-FAANG staff engineer with 30+yrs of experience was stuck on a bug for ~200hrs over 4 years. Claude Opus 4 solved it, and was the only model that could.
17
91
1K
Use `ccusage` to track @claude_code usage across daily, monthly, and repository levels. In latest v15.0.0 update, supports real-time with an interactive dashboard. Amazing work by @ryoppippi, いつも本当にお疲れ様です！. 日本の @claude_code
9
189
1K
Please note, if you're having trouble authenticating with the MCP server . check your VPN as it can cause sporadic connection errors. A difference in connecting to the MCP server on versus Claude Code is a useful signal.
Claude Code can now connect to remote MCP servers. Pull context from your tools directly into Claude Code with no local setup required.
4
13
148
Claude code supports integration with @linear MCP server. This is a great demonstration of human (task setting) and agentic (task completion) collaboration. Writes tickets, verifies, and proceeds to the next ticket.
9
36
574
Cool project by @brendankblong using Claude code to play a text-based game (Dwarf Fortress). Claude with visual feedback is a great combination.
@thebes @janbamjan The first one didn't record and the second one hit my Claude usage limits. Here's a video but Claude doesn't get very far:
3
11
173
One major change from its predecessor (3.7 to 4) is focusing on reducing over-eagerness and unnecessary complexity. Sometimes, simply: "Your app is working fine.".
I asked Claude Code to fix my bug and it just refused lol. "Your app is working fine. This is a minor issue that doesn't break core functionality."
9
13
258
Remember to use plan mode to clarify feature specifications and expected behavior. Ask it to bring up any clarifying questions that need to be addressed. Then it will draft a plan, and the magic begins.
New in Claude Code: Plan mode. Review implementation plans before making changes. Perfect for complex changes where you want to nail the approach before diving in.
25
63
1K
How Anthropic Teams Use Claude Code:. Create self-contained loops.Configure Claude to verify work by automatically running builds, tests, and lints, especially when generating tests before coding. Develop task intuition.Use "auto-accept mode" for abstract edge tasks (peripheral.
Since we originally built Claude Code as an internal tool, we've heard a ton of questions about how our teams use it at Anthropic. Here’s an inside look on how our teams—from product engineering, to growth marketing, to legal—use Claude Code:
2
0
47
It's not perfect, but occasionally it reminds us technology can be used to bring joy ☺️.
A love letter to @claude_code: Over the past two days, I built a stock analysis web app for loved ones that includes auth, charting tools, stock data/llm apis, db persistance, and more. (see 1 min demo). The velocity was only possible with claude code—please try it if you haven't
1
2
28
Claude 4 Sonnet is now available in Claude Code. It is the new default (recommended) model. Be cautious with Claude Opus, as its cost can escalate quickly.
Introducing the next generation: Claude Opus 4 and Claude Sonnet 4. Claude Opus 4 is our most powerful model yet, and the world’s best coding model. Claude Sonnet 4 is a significant upgrade from its predecessor, delivering superior coding and reasoning.
0
1
13