[BUG] Skill `model:` frontmatter triggers 429 "Extra usage required" on 2.1.76 when session uses opus[1m]
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) 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? On Claude Code 2.1.76, invoking any skill with `model: sonnet` in frontmatter from an `opus[1m]` (1M context) session immediately fails with: ``` API Error: Rate limit reached ``` This happens on a fresh session with zero prior API calls. It does not happen on 2.1.75. ### What Should Happen? When opus[1m] is used, the skill using sonnet (sonnet[1m] more specifically) should be invoked without any issue. ### Error Messages/Logs ```shell Run `claude --debug`, invoke the skill, check `~/.claude/debug/*.txt`: [ERROR] API error (attempt 1/11): 429 429 { "type": "error", "error": { "type": "rate_limit_error", "message": "Extra usage is required for long context requests." } } The error is not a rate limit — it's an access restriction. The API rejects `sonnet[1m]` because the account doesn't have "extra usage" enabled for sonnet long-context. ``` ### Steps to Reproduce 1. Claude Code 2.1.76, Max plan, `opus[1m]` as session model (default) 2. Create a skill: ```yaml --- name: test-sonnet description: Test sonnet model switch model: sonnet user-invocable: true --- Say hello. ``` 3. Invoke `/test-sonnet` → immediate 42
Posted by tfvchow on Mar 14, 2026, 8:02 AM
Tags
Related issues
- [Meta] Feedback on granular control over Copilot changes
- unexpected status 401 Unauthorized issue
- [MODEL] Measurable quality regression in Claude generation 5 (Fable 5 / Opus 5 / Sonnet 5): worse nonsense detection, ~2x verbosity, under-disclosed model fallb
- [CRITICAL] Subagent spawning and subagent pattern bugs trigger infinite recursion, infinite token usage, grossly inefficient token usage, and lost accumulated s
- Video stops playing after some minutes
- [MODEL] Claude verbose code comments by default — ignores instructions to stop.
Raise real-world problems, find people facing the same issue, and discuss solutions.2,000 issues0 comments
github (Software)
[Meta] Feedback on granular control over Copilot changes
unexpected status 401 Unauthorized issue
[MODEL] Measurable quality regression in Claude generation 5 (Fable 5 / Opus 5 / Sonnet 5): worse nonsense detection, ~2x verbosity, under-disclosed model fallb
[CRITICAL] Subagent spawning and subagent pattern bugs trigger infinite recursion, infinite token usage, grossly inefficient token usage, and lost accumulated s
Video stops playing after some minutes
[MODEL] Claude verbose code comments by default — ignores instructions to stop.
Scope Codex VS Code chats to the current workspace/project
Update on "Co-authored-by: Copilot" in commit messages
[BUG] Skill `model:` frontmatter triggers 429 "Extra usage required" on 2.1.76 when session uses opus[1m]
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) 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? On Claude Code 2.1.76, invoking any skill with `model: sonnet` in frontmatter from an `opus[1m]` (1M context) session immediately fails with: ``` API Error: Rate limit reached ``` This happens on a fresh session with zero prior API calls. It does not happen on 2.1.75. ### What Should Happen? When opus[1m] is used, the skill using sonnet (sonnet[1m] more specifically) should be invoked without any issue. ### Error Messages/Logs ```shell Run `claude --debug`, invoke the skill, check `~/.claude/debug/*.txt`: [ERROR] API error (attempt 1/11): 429 429 { "type": "error", "error": { "type": "rate_limit_error", "message": "Extra usage is required for long context requests." } } The error is not a rate limit — it's an access restriction. The API rejects `sonnet[1m]` because the account doesn't have "extra usage" enabled for sonnet long-context. ``` ### Steps to Reproduce 1. Claude Code 2.1.76, Max plan, `opus[1m]` as session model (default) 2. Create a skill: ```yaml --- name: test-sonnet description: Test sonnet model switch model: sonnet user-invocable: true --- Say hello. ``` 3. Invoke `/test-sonnet` → immediate 42
Comments (0)
No comments yet. Start the discussion.