Claude Code limit: make your quota last longer by handing the heavy work to XCR

How the Claude Code limit works

Anthropic's Pro and Max plan article describes two limits for Claude Code:

• A five-hour session limit.
• A weekly limit.

Both are shared across Claude and Claude Code, so a long chat in the browser and a coding session in your terminal or IDE draw from the same allowance. Claude Code shows warnings as you approach a limit, and you can monitor what's left with /status. One more thing to check: if an ANTHROPIC_API_KEY environment variable is set, Claude Code uses that key and bills API usage instead of your plan.

What uses up your Claude Code quota

Losing a session halfway through a feature is the real cost: the plan is in your head, the change is half done, and the session is over. The usage goes to a few predictable places:

• Agent loops. Writing code, running tests, reading the failure and trying again can take dozens of turns for one feature.
• Large context. Every turn carries the conversation so far plus the files Claude Code has opened.
• Exploring a big repository before writing the first line.
• The most capable models and higher effort settings on routine edits.

Planning and reviewing are light by comparison. The build is the heavy part.

Your options when you reach the limit

Anthropic lists the choices: enable usage credits to keep using your plan, upgrade (Pro to Max 5x, Max 5x to Max 20x), switch to a Claude Console account with API credits, or wait for the reset.

Split the work: Claude Code plans, XCR builds

XCR is a plugin that connects to Claude Code and takes over the expensive part of the job:

1. Claude Code hands the task over. Any request bigger than a small edit (roughly more than 30 lines, or more than one file) goes to XCR.
2. XCR builds it. It writes the change on a copy of your project, runs your project's own checks and repairs failures.
3. Claude Code reviews. It gets a short report with the requirements done, files changed and check results, and checks the change against your request.

XCR routes each task to models from OpenAI, Anthropic and Google, so one account covers all of them. Checks run on your machine. Code is sent to the model only for the task, and XCR doesn't store it. Quick questions and one-line fixes stay in Claude Code, exactly as before.

Your Claude Code quota now goes to understanding the request, choosing the approach and reviewing the result, while XCR takes on the heavy build work.

Habits that make every session go further

• Run /clear when you switch to an unrelated task.
• Use /compact in long sessions to shrink the history.
• Keep CLAUDE.md short and specific. It's loaded into every session.
• Describe the whole change, and how to test it, in one message.
• Use /model to pick a lighter model for routine edits.

More in 8 ways to make AI coding cheaper.

How to set up XCR in Claude Code: install and first task

What you need

• Claude Code installed and signed in on a computer running macOS or Linux.
• Node.js 20 or later. If it's missing, Claude Code installs it for you and asks before it does.
• A project in a folder on that computer. A git repository works best.

Step 1: Create your XCR account

Open the install page, enter your email and choose Email me a sign-in link. The link arrives in seconds and works for 15 minutes. There is no password, and the same link creates your account the first time.

Step 2: Connect XCR to Claude Code

1. Open Install on a computer and choose the Claude Code tab.
2. Read What XCR will change on your computer and tick the box to agree.
3. Click Copy install instruction, paste it into Claude Code and allow the command when it asks.
4. The command downloads the plugin from xcr.ai and checks its SHA-256 before it runs anything. Your console switches to Connected.
5. Restart Claude Code.

XCR registers itself as an MCP server for Claude Code and adds one short rule to your CLAUDE.md, so Claude Code hands bigger changes to XCR on its own. Your original files are backed up first, and every change sits between clearly marked XCR lines. The instruction works once, for the next 10 minutes; if it expires, copy it again.

Step 3: Hand off your first task

Once your console shows Connected, ask Claude Code for something bigger than a small edit, as you normally would:

• "Add CSV export to the orders page, with filters by date and status."
• "Add unit tests for the payment module and make them pass."

Claude Code hands the job to XCR, and the task appears under Tasks in your console.

Step 4: Review the result

XCR builds the change on a copy of your project and runs your project's own checks (type check, lint, tests). Claude Code gets back a short report: requirements done, files changed and check results. When the checks pass, the change lands in your working tree without a commit, ready to review in your usual diff. Anything that needs the internet, such as installing packages, comes back for Claude Code to finish.

Pause XCR anytime with the switch at the top of Overview, or tell Claude Code "Uninstall XCR from this computer" to remove exactly what XCR added. More detail: XCR quick start and how the plugin works with Claude Code.