[BUG] Claude Code Pro Subscription — Rate Limited After Single Deep Research Run

Preflight Checklist

• [x] I have searched existing issues and this hasn't been reported yet
• [x] This is a single bug report (please file separate reports for different bugs)
• [x] I am using the latest version of Claude Code

What's Wrong?

I am a Claude Code subscriber (Pro plan). After running a single deep-research report, I immediately hit rate limits and was unable to continue working.
No other significant usage preceded this event.

What Should Happen?

• Increase rate limits for Pro subscribers, especially for multi-agent workflows like deep-research
• Or provide clearer documentation on how many deep-research runs are supported per hour/day at each subscription tier
• Consider a separate, higher quota pool for Claude Code's built-in multi-agent skills

Account email: hualu.qi@tokenlulu.com

Error Messages/Logs

Steps to Reproduce

1. Open Claude Code with an active Pro subscription
2. Invoke the /deep-research skill with a single research query
3. Rate limit is triggered before or immediately after the report completes

Expected Behavior:
A Pro subscription should reasonably support at least one complete deep-research workflow without hitting rate limits.

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.179 (Claude Code)

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

I am a Claude Code subscriber (Pro plan). After running a single deep-research report, I immediately hit rate limits and was unable to continue working.
No other significant usage preceded this event.

Steps to Reproduce:

1. Open Claude Code with an active Pro subscription
2. Invoke the /deep-research skill with a single research query
3. Rate limit is triggered before or immediately after the report completes

Expected Behavior:
A Pro subscription should reasonably support at least one complete deep-research workflow without hitting rate limits.

Actual Behavior:
Rate limited after a single invocation. Workflow is blocked and I must wait for the limit to reset.

Impact:
The deep-research skill is a core, advertised feature of Claude Code. If a single use exhausts the rate limit for a Pro subscriber, the feature is
effectively unusable for professional workflows.

Request:

• Increase rate limits for Pro subscribers, especially for multi-agent workflows like deep-research
• Or provide clearer documentation on how many deep-research runs are supported per hour/day at each subscription tier
• Consider a separate, higher quota pool for Claude Code's built-in multi-agent skills

Account email: hualu.qi@tokenlulu.com