[BUG] Opus 1M context window suddenly returns "Rate limit reached" on both Max and Team plans (200K works fine)

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?

Opus 1M context window suddenly returns "Rate limit reached" on both Max and Team plans (200K works fine)

Bug description

The Opus model with 1M context window was working fine until this afternoon, but now it consistently returns a "Rate limit reached" error and is completely unusable. The standard 200K context window works normally.

Environment

• Claude Code version: 2.1.62
• Model: opus[1m] (claude-opus-4-6[1m])
• Plans tested: Max ($200/month) and Team (Premium)
• OS: macOS Tahoe 26.3
• Key config:
• Auto-compact: true
• Thinking mode: true
• Verbose output: true
• Default permission mode: Default
• Auto-update channel: latest

Expected behavior

Opus 1M context window should be available as advertised on both Max and Team plans without hitting rate limits under normal usage.

Error log analysis

The JSONL session log (attached) contains this critical event:

{
  "type": "rate_limit_event",
  "rate_limit_info": {
    "status": "rejected",
    "overageDisabledReason": "org_level_disabled",
    "isUsingOverage": false
  }
}

The assistant response object confirms zero token usage and an immediate synthetic error:

{
  "model": "<synthetic>",
  "usage": { "input_tokens": 0, "output_tokens": 0 },
  "content": [{ "type": "text", "text": "API Error: Rate limit reached" }],
  "error": "rate_limit"
}

Questions for the team

1. Is there a separate rate limit quota for opus[1m] that differs from standard opus?
2. Does overageDisabledReason: "org_level_disabled" indicate an intentional policy change for 1M context, or is this a bug?
3. Why would a Max ($200/month) personal account be subject to org_level_disabled overage restrictions?

What Should Happen?

1. Start a Claude Code session with model set to opus[1m]
2. Attempt any operation that utilizes the 1M extended context
3. Receive "Rate limit reached" error immediately

Error Messages/Logs

{"type":"system","subtype":"hook_started","hook_id":"7c24ca8a-e2da-429d-ad2f-720312a5018e","hook_name":"SessionStart:startup","hook_event":"SessionStart","uuid":"0146eed4-8dcc-4827-989b-f6c857663be8","session_id":"119ea4da-9b47-46b0-8cd3-3ab1f2e64f57"}
{"type":"system","subtype":"hook_response","hook_id":"7c24ca8a-e2da-429d-ad2f-720312a5018e","hook_name":"SessionStart:startup","hook_event":"SessionStart","output":"{\n  \"additional_context\": \"<EXTREMELY_IMPORTANT>\\nYou have superpowers.\\n\\n**Below is the full content of your 'superpowers:using-superpowers' skill - your introduction to using skills. For all other skills, use the 'Skill' tool:**\\n\\n---\\nname: using-superpowers\\ndescription: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions\\n---\\n\\n<EXTREMELY-IMPORTANT>\\nIf you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.\\n\\nIF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.\\n\\nThis is not negotiable. This is not optional. You cannot rationalize your way out of this.\\n</EXTREMELY-IMPORTANT>\\n\\n## How to Access Skills\\n\\n**In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.\\n\\n**In other environments:** Check your platform's documentation for how skills are loaded.\\n\\n# Using Skills\\n\\n## The Rule\\n\\n**Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.\\n\\n\\ndigraph skill_flow {\\n    \\\"User message received\\\" [shape=doublecircle];\\n    \\\"About to EnterPlanMode?\\\" [shape=doublecircle];\\n    \\\"Already brainstormed?\\\" [shape=diamond];\\n    \\\"Invoke brainstorming skill\\\" [shape=box];\\n    \\\"Might any skill apply?\\\" [shape=diamond];\\n    \\\"Invoke Skill tool\\\" [shape=box];\\n    \\\"Announce: 'Using [skill] to [purpose]'\\\" [shape=box];\\n    \\\"Has checklist?\\\" [shape=diamond];\\n    \\\"Create TodoWrite todo per item\\\" [shape=box];\\n    \\\"Follow skill exactly\\\" [shape=box];\\n    \\\"Respond (including clarifications)\\\" [shape=doublecircle];\\n\\n    \\\"About to EnterPlanMode?\\\" -> \\\"Already brainstormed?\\\";\\n    \\\"Already brainstormed?\\\" -> \\\"Invoke brainstorming skill\\\" [label=\\\"no\\\"];\\n    \\\"Already brainstormed?\\\" -> \\\"Might any skill apply?\\\" [label=\\\"yes\\\"];\\n    \\\"Invoke brainstorming skill\\\" -> \\\"Might any skill apply?\\\";\\n\\n    \\\"User message received\\\" -> \\\"Might any skill apply?\\\";\\n    \\\"Might any skill apply?\\\" -> \\\"Invoke Skill tool\\\" [label=\\\"yes, even 1%\\\"];\\n    \\\"Might any skill apply?\\\" -> \\\"Respond (including clarifications)\\\" [label=\\\"definitely not\\\"];\\n    \\\"Invoke Skill tool\\\" -> \\\"Announce: 'Using [skill] to [purpose]'\\\";\\n    \\\"Announce: 'Using [skill] to [purpose]'\\\" -> \\\"Has checklist?\\\";\\n    \\\"Has checklist?\\\" -> \\\"Create TodoWrite todo per item\\\" [label=\\\"yes\\\"];\\n    \\\"Has checklist?\\\" -> \\\"Follow skill exactly\\\" [label=\\\"no\\\"];\\n    \\\"Create TodoWrite todo per item\\\" -> \\\"Follow skill exactly\\\";\\n}\\n\\n\\n## Red Flags\\n\\nThese thoughts mean STOP—you're rationalizing:\\n\\n| Thought | Reality |\\n|---------|---------|\\n| \\\"This is just a simple question\\\" | Questions are tasks. Check for skills. |\\n| \\\"I need more context first\\\" | Skill check comes BEFORE clarifying questions. |\\n| \\\"Let me explore the codebase first\\\" | Skills tell you HOW to explore. Check first. |\\n| \\\"I can check git/files quickly\\\" | Files lack conversation context. Check for skills. |\\n| \\\"Let me gather information first\\\" | Skills tell you HOW to gather information. |\\n| \\\"This doesn't need a formal skill\\\" | If a skill exists, use it. |\\n| \\\"I remember this skill\\\" | Skills evolve. Read current version. |\\n| \\\"This doesn't count as a task\\\" | Action = task. Check for skills. |\\n| \\\"The skill is overkill\\\" | Simple things become complex. Use it. |\\n| \\\"I'll just do this one thing first\\\" | Check BEFORE doing anything. |\\n| \\\"This feels productive\\\" | Undisciplined action wastes time. Skills prevent this. |\\n| \\\"I know what that means\\\" | Knowing the concept ≠ using the skill. Invoke it. |\\n\\n## Skill Priority\\n\\nWhen multiple skills could apply, use this order:\\n\\n1. **Process skills first** (brainstorming, debugging) - these determine HOW to approach the task\\n2. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution\\n\\n\\\"Let's build X\\\" → brainstorming first, then implementation skills.\\n\\\"Fix this bug\\\" → debugging first, then domain-specific skills.\\n\\n## Skill Types\\n\\n**Rigid** (TDD, debugging): Follow exactly. Don't adapt away discipline.\\n\\n**Flexible** (patterns): Adapt principles to context.\\n\\nThe skill itself tells you which.\\n\\n## User Instructions\\n\\nInstructions say WHAT, not HOW. \\\"Add X\\\" or \\\"Fix Y\\\" doesn't mean skip workflows.\\n\\n\\n</EXTREMELY_IMPORTANT>\",\n  \"hookSpecificOutput\": {\n    \"hookEventName\": \"SessionStart\",\n    \"additionalContext\": \"<EXTREMELY_IMPORTANT>\\nYou have superpowers.\\n\\n**Below is the full content of your 'superpowers:using-superpowers' skill - your introduction to using skills. For all other skills, use the 'Skill' tool:**\\n\\n---\\nname: using-superpowers\\ndescription: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions\\n---\\n\\n<EXTREMELY-IMPORTANT>\\nIf you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.\\n\\nIF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.\\n\\nThis is not negotiable. This is not optional. You cannot rationalize your way out of this.\\n</EXTREMELY-IMPORTANT>\\n\\n## How to Access Skills\\n\\n**In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.\\n\\n**In other environments:** Check your platform's documentation for how skills are loaded.\\n\\n# Using Skills\\n\\n## The Rule\\n\\n**Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.\\n\\n\\ndigraph skill_flow {\\n    \\\"User message received\\\" [shape=doublecircle];\\n    \\\"About to EnterPlanMode?\\\" [shape=doublecircle];\\n    \\\"Already brainstormed?\\\" [shape=diamond];\\n    \\\"Invoke brainstorming skill\\\" [shape=box];\\n    \\\"Might any skill apply?\\\" [shape=diamond];\\n    \\\"Invoke Skill tool\\\" [shape=box];\\n    \\\"Announce: 'Using [skill] to [purpose]'\\\" [shape=box];\\n    \\\"Has checklist?\\\" [shape=diamond];\\n    \\\"Create TodoWrite todo per item\\\" [shape=box];\\n    \\\"Follow skill exactly\\\" [shape=box];\\n    \\\"Respond (including clarifications)\\\" [shape=doublecircle];\\n\\n    \\\"About to EnterPlanMode?\\\" -> \\\"Already brainstormed?\\\";\\n    \\\"Already brainstormed?\\\" -> \\\"Invoke brainstorming skill\\\" [label=\\\"no\\\"];\\n    \\\"Already brainstormed?\\\" -> \\\"Might any skill apply?\\\" [label=\\\"yes\\\"];\\n    \\\"Invoke brainstorming skill\\\" -> \\\"Might any skill apply?\\\";\\n\\n    \\\"User message received\\\" -> \\\"Might any skill apply?\\\";\\n    \\\"Might any skill apply?\\\" -> \\\"Invoke Skill tool\\\" [label=\\\"yes, even 1%\\\"];\\n    \\\"Might any skill apply?\\\" -> \\\"Respond (including clarifications)\\\" [label=\\\"definitely not\\\"];\\n    \\\"Invoke Skill tool\\\" -> \\\"Announce: 'Using [skill] to [purpose]'\\\";\\n    \\\"Announce: 'Using [skill] to [purpose]'\\\" -> \\\"Has checklist?\\\";\\n    \\\"Has checklist?\\\" -> \\\"Create TodoWrite todo per item\\\" [label=\\\"yes\\\"];\\n    \\\"Has checklist?\\\" -> \\\"Follow skill exactly\\\" [label=\\\"no\\\"];\\n    \\\"Create TodoWrite todo per item\\\" -> \\\"Follow skill exactly\\\";\\n}\\n\\n\\n## Red Flags\\n\\nThese thoughts mean STOP—you're rationalizing:\\n\\n| Thought | Reality |\\n|---------|---------|\\n| \\\"This is just a simple question\\\" | Questions are tasks. Check for skills. |\\n| \\\"I need more context first\\\" | Skill check comes BEFORE clarifying questions. |\\n| \\\"Let me explore the codebase first\\\" | Skills tell you HOW to explore. Check first. |\\n| \\\"I can check git/files quickly\\\" | Files lack conversation context. Check for skills. |\\n| \\\"Let me gather information first\\\" | Skills tell you HOW to gather information. |\\n| \\\"This doesn't need a formal skill\\\" | If a skill exists, use it. |\\n| \\\"I remember this skill\\\" | Skills evolve. Read current version. |\\n| \\\"This doesn't count as a task\\\" | Action = task. Check for skills. |\\n| \\\"The skill is overkill\\\" | Simple things become complex. Use it. |\\n| \\\"I'll just do this one thing first\\\" | Check BEFORE doing anything. |\\n| \\\"This feels productive\\\" | Undisciplined action wastes time. Skills prevent this. |\\n| \\\"I know what that means\\\" | Knowing the concept ≠ using the skill. Invoke it. |\\n\\n## Skill Priority\\n\\nWhen multiple skills could apply, use this order:\\n\\n1. **Process skills first** (brainstorming, debugging) - these determine HOW to approach the task\\n2. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution\\n\\n\\\"Let's build X\\\" → brainstorming first, then implementation skills.\\n\\\"Fix this bug\\\" → debugging first, then domain-specific skills.\\n\\n## Skill Types\\n\\n**Rigid** (TDD, debugging): Follow exactly. Don't adapt away discipline.\\n\\n**Flexible** (patterns): Adapt principles to context.\\n\\nThe skill itself tells you which.\\n\\n## User Instructions\\n\\nInstructions say WHAT, not HOW. \\\"Add X\\\" or \\\"Fix Y\\\" doesn't mean skip workflows.\\n\\n\\n</EXTREMELY_IMPORTANT>\"\n  }\n}\n","stdout":"{\n  \"additional_context\": \"<EXTREMELY_IMPORTANT>\\nYou have superpowers.\\n\\n**Below is the full content of your 'superpowers:using-superpowers' skill - your introduction to using skills. For all other skills, use the 'Skill' tool:**\\n\\n---\\nname: using-superpowers\\ndescription: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions\\n---\\n\\n<EXTREMELY-IMPORTANT>\\nIf you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.\\n\\nIF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.\\n\\nThis is not negotiable. This is not optional. You cannot rationalize your way out of this.\\n</EXTREMELY-IMPORTANT>\\n\\n## How to Access Skills\\n\\n**In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.\\n\\n**In other environments:** Check your platform's documentation for how skills are loaded.\\n\\n# Using Skills\\n\\n## The Rule\\n\\n**Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.\\n\\n\\ndigraph skill_flow {\\n    \\\"User message received\\\" [shape=doublecircle];\\n    \\\"About to EnterPlanMode?\\\" [shape=doublecircle];\\n    \\\"Already brainstormed?\\\" [shape=diamond];\\n    \\\"Invoke brainstorming skill\\\" [shape=box];\\n    \\\"Might any skill apply?\\\" [shape=diamond];\\n    \\\"Invoke Skill tool\\\" [shape=box];\\n    \\\"Announce: 'Using [skill] to [purpose]'\\\" [shape=box];\\n    \\\"Has checklist?\\\" [shape=diamond];\\n    \\\"Create TodoWrite todo per item\\\" [shape=box];\\n    \\\"Follow skill exactly\\\" [shape=box];\\n    \\\"Respond (including clarifications)\\\" [shape=doublecircle];\\n\\n    \\\"About to EnterPlanMode?\\\" -> \\\"Already brainstormed?\\\";\\n    \\\"Already brainstormed?\\\" -> \\\"Invoke brainstorming skill\\\" [label=\\\"no\\\"];\\n    \\\"Already brainstormed?\\\" -> \\\"Might any skill apply?\\\" [label=\\\"yes\\\"];\\n    \\\"Invoke brainstorming skill\\\" -> \\\"Might any skill apply?\\\";\\n\\n    \\\"User message received\\\" -> \\\"Might any skill apply?\\\";\\n    \\\"Might any skill apply?\\\" -> \\\"Invoke Skill tool\\\" [label=\\\"yes, even 1%\\\"];\\n    \\\"Might any skill apply?\\\" -> \\\"Respond (including clarifications)\\\" [label=\\\"definitely not\\\"];\\n    \\\"Invoke Skill tool\\\" -> \\\"Announce: 'Using [skill] to [purpose]'\\\";\\n    \\\"Announce: 'Using [skill] to [purpose]'\\\" -> \\\"Has checklist?\\\";\\n    \\\"Has checklist?\\\" -> \\\"Create TodoWrite todo per item\\\" [label=\\\"yes\\\"];\\n    \\\"Has checklist?\\\" -> \\\"Follow skill exactly\\\" [label=\\\"no\\\"];\\n    \\\"Create TodoWrite todo per item\\\" -> \\\"Follow skill exactly\\\";\\n}\\n\\n\\n## Red Flags\\n\\nThese thoughts mean STOP—you're rationalizing:\\n\\n| Thought | Reality |\\n|---------|---------|\\n| \\\"This is just a simple question\\\" | Questions are tasks. Check for skills. |\\n| \\\"I need more context first\\\" | Skill check comes BEFORE clarifying questions. |\\n| \\\"Let me explore the codebase first\\\" | Skills tell you HOW to explore. Check first. |\\n| \\\"I can check git/files quickly\\\" | Files lack conversation context. Check for skills. |\\n| \\\"Let me gather information first\\\" | Skills tell you HOW to gather information. |\\n| \\\"This doesn't need a formal skill\\\" | If a skill exists, use it. |\\n| \\\"I remember this skill\\\" | Skills evolve. Read current version. |\\n| \\\"This doesn't count as a task\\\" | Action = task. Check for skills. |\\n| \\\"The skill is overkill\\\" | Simple things become complex. Use it. |\\n| \\\"I'll just do this one thing first\\\" | Check BEFORE doing anything. |\\n| \\\"This feels productive\\\" | Undisciplined action wastes time. Skills prevent this. |\\n| \\\"I know what that means\\\" | Knowing the concept ≠ using the skill. Invoke it. |\\n\\n## Skill Priority\\n\\nWhen multiple skills could apply, use this order:\\n\\n1. **Process skills first** (brainstorming, debugging) - these determine HOW to approach the task\\n2. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution\\n\\n\\\"Let's build X\\\" → brainstorming first, then implementation skills.\\n\\\"Fix this bug\\\" → debugging first, then domain-specific skills.\\n\\n## Skill Types\\n\\n**Rigid** (TDD, debugging): Follow exactly. Don't adapt away discipline.\\n\\n**Flexible** (patterns): Adapt principles to context.\\n\\nThe skill itself tells you which.\\n\\n## User Instructions\\n\\nInstructions say WHAT, not HOW. \\\"Add X\\\" or \\\"Fix Y\\\" doesn't mean skip workflows.\\n\\n\\n</EXTREMELY_IMPORTANT>\",\n  \"hookSpecificOutput\": {\n    \"hookEventName\": \"SessionStart\",\n    \"additionalContext\": \"<EXTREMELY_IMPORTANT>\\nYou have superpowers.\\n\\n**Below is the full content of your 'superpowers:using-superpowers' skill - your introduction to using skills. For all other skills, use the 'Skill' tool:**\\n\\n---\\nname: using-superpowers\\ndescription: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions\\n---\\n\\n<EXTREMELY-IMPORTANT>\\nIf you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.\\n\\nIF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.\\n\\nThis is not negotiable. This is not optional. You cannot rationalize your way out of this.\\n</EXTREMELY-IMPORTANT>\\n\\n## How to Access Skills\\n\\n**In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.\\n\\n**In other environments:** Check your platform's documentation for how skills are loaded.\\n\\n# Using Skills\\n\\n## The Rule\\n\\n**Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.\\n\\n\\ndigraph skill_flow {\\n    \\\"User message received\\\" [shape=doublecircle];\\n    \\\"About to EnterPlanMode?\\\" [shape=doublecircle];\\n    \\\"Already brainstormed?\\\" [shape=diamond];\\n    \\\"Invoke brainstorming skill\\\" [shape=box];\\n    \\\"Might any skill apply?\\\" [shape=diamond];\\n    \\\"Invoke Skill tool\\\" [shape=box];\\n    \\\"Announce: 'Using [skill] to [purpose]'\\\" [shape=box];\\n    \\\"Has checklist?\\\" [shape=diamond];\\n    \\\"Create TodoWrite todo per item\\\" [shape=box];\\n    \\\"Follow skill exactly\\\" [shape=box];\\n    \\\"Respond (including clarifications)\\\" [shape=doublecircle];\\n\\n    \\\"About to EnterPlanMode?\\\" -> \\\"Already brainstormed?\\\";\\n    \\\"Already brainstormed?\\\" -> \\\"Invoke brainstorming skill\\\" [label=\\\"no\\\"];\\n    \\\"Already brainstormed?\\\" -> \\\"Might any skill apply?\\\" [label=\\\"yes\\\"];\\n    \\\"Invoke brainstorming skill\\\" -> \\\"Might any skill apply?\\\";\\n\\n    \\\"User message received\\\" -> \\\"Might any skill apply?\\\";\\n    \\\"Might any skill apply?\\\" -> \\\"Invoke Skill tool\\\" [label=\\\"yes, even 1%\\\"];\\n    \\\"Might any skill apply?\\\" -> \\\"Respond (including clarifications)\\\" [label=\\\"definitely not\\\"];\\n    \\\"Invoke Skill tool\\\" -> \\\"Announce: 'Using [skill] to [purpose]'\\\";\\n    \\\"Announce: 'Using [skill] to [purpose]'\\\" -> \\\"Has checklist?\\\";\\n    \\\"Has checklist?\\\" -> \\\"Create TodoWrite todo per item\\\" [label=\\\"yes\\\"];\\n    \\\"Has checklist?\\\" -> \\\"Follow skill exactly\\\" [label=\\\"no\\\"];\\n    \\\"Create TodoWrite todo per item\\\" -> \\\"Follow skill exactly\\\";\\n}\\n\\n\\n## Red Flags\\n\\nThese thoughts mean STOP—you're rationalizing:\\n\\n| Thought | Reality |\\n|---------|---------|\\n| \\\"This is just a simple question\\\" | Questions are tasks. Check for skills. |\\n| \\\"I need more context first\\\" | Skill check comes BEFORE clarifying questions. |\\n| \\\"Let me explore the codebase first\\\" | Skills tell you HOW to explore. Check first. |\\n| \\\"I can check git/files quickly\\\" | Files lack conversation context. Check for skills. |\\n| \\\"Let me gather information first\\\" | Skills tell you HOW to gather information. |\\n| \\\"This doesn't need a formal skill\\\" | If a skill exists, use it. |\\n| \\\"I remember this skill\\\" | Skills evolve. Read current version. |\\n| \\\"This doesn't count as a task\\\" | Action = task. Check for skills. |\\n| \\\"The skill is overkill\\\" | Simple things become complex. Use it. |\\n| \\\"I'll just do this one thing first\\\" | Check BEFORE doing anything. |\\n| \\\"This feels productive\\\" | Undisciplined action wastes time. Skills prevent this. |\\n| \\\"I know what that means\\\" | Knowing the concept ≠ using the skill. Invoke it. |\\n\\n## Skill Priority\\n\\nWhen multiple skills could apply, use this order:\\n\\n1. **Process skills first** (brainstorming, debugging) - these determine HOW to approach the task\\n2. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution\\n\\n\\\"Let's build X\\\" → brainstorming first, then implementation skills.\\n\\\"Fix this bug\\\" → debugging first, then domain-specific skills.\\n\\n## Skill Types\\n\\n**Rigid** (TDD, debugging): Follow exactly. Don't adapt away discipline.\\n\\n**Flexible** (patterns): Adapt principles to context.\\n\\nThe skill itself tells you which.\\n\\n## User Instructions\\n\\nInstructions say WHAT, not HOW. \\\"Add X\\\" or \\\"Fix Y\\\" doesn't mean skip workflows.\\n\\n\\n</EXTREMELY_IMPORTANT>\"\n  }\n}\n","stderr":"","exit_code":0,"outcome":"success","uuid":"a3c81c1f-e1c4-4a08-8374-737e2ce440bf","session_id":"119ea4da-9b47-46b0-8cd3-3ab1f2e64f57"}
{"type":"system","subtype":"init","cwd":"/Users/sanghyunlee/.claude/projects/-Volumes-Personal-side-reze-system","session_id":"119ea4da-9b47-46b0-8cd3-3ab1f2e64f57","tools":["Task","TaskOutput","Bash","Glob","Grep","ExitPlanMode","Read","Edit","Write","NotebookEdit","WebFetch","TodoWrite","WebSearch","TaskStop","AskUserQuestion","Skill","EnterPlanMode","EnterWorktree","ToolSearch","mcp__magic__21st_magic_component_builder","mcp__magic__logo_search","mcp__magic__21st_magic_component_inspiration","mcp__magic__21st_magic_component_refiner"],"mcp_servers":[{"name":"magic","status":"connected"}],"model":"claude-opus-4-6[1m]","permissionMode":"default","slash_commands":["keybindings-help","debug","sc:agent","sc:document","sc:spawn","sc:estimate","sc:spec-panel","sc:index-repo","sc:implement","sc:troubleshoot","sc:business-panel","sc:improve","sc:recommend","sc:explain","sc:reflect","sc:analyze","sc:workflow","sc:select-tool","sc:help","sc:load","sc:README","sc:sc","sc:research","sc:index","sc:build","sc:save","sc:git","sc:task","sc:design","sc:pm","sc:cleanup","sc:test","sc:brainstorm","superpowers:execute-plan","superpowers:write-plan","superpowers:brainstorm","superpowers:using-git-worktrees","superpowers:test-driven-development","superpowers:systematic-debugging","superpowers:using-superpowers","superpowers:dispatching-parallel-agents","superpowers:executing-plans","superpowers:finishing-a-development-branch","superpowers:brainstorming","superpowers:writing-plans","superpowers:requesting-code-review","superpowers:receiving-code-review","superpowers:writing-skills","superpowers:verification-before-completion","superpowers:subagent-driven-development","document-skills:theme-factory","document-skills:doc-coauthoring","document-skills:xlsx","document-skills:pdf","document-skills:algorithmic-art","document-skills:internal-comms","document-skills:skill-creator","document-skills:canvas-design","document-skills:pptx","document-skills:slack-gif-creator","document-skills:webapp-testing","document-skills:frontend-design","document-skills:mcp-builder","document-skills:brand-guidelines","document-skills:docx","document-skills:web-artifacts-builder","frontend-design:frontend-design","skill-creator:skill-creator","compact","context","cost","init","pr-comments","release-notes","review","security-review","insights"],"apiKeySource":"none","claude_code_version":"2.1.62","output_style":"default","agents":["general-purpose","statusline-setup","Explore","Plan","superpowers:code-reviewer"],"skills":["keybindings-help","debug","superpowers:execute-plan","superpowers:write-plan","superpowers:brainstorm","superpowers:using-git-worktrees","superpowers:test-driven-development","superpowers:systematic-debugging","superpowers:using-superpowers","superpowers:dispatching-parallel-agents","superpowers:executing-plans","superpowers:finishing-a-development-branch","superpowers:brainstorming","superpowers:writing-plans","superpowers:requesting-code-review","superpowers:receiving-code-review","superpowers:writing-skills","superpowers:verification-before-completion","superpowers:subagent-driven-development","document-skills:theme-factory","document-skills:doc-coauthoring","document-skills:xlsx","document-skills:pdf","document-skills:algorithmic-art","document-skills:internal-comms","document-skills:skill-creator","document-skills:canvas-design","document-skills:pptx","document-skills:slack-gif-creator","document-skills:webapp-testing","document-skills:frontend-design","document-skills:mcp-builder","document-skills:brand-guidelines","document-skills:docx","document-skills:web-artifacts-builder","frontend-design:frontend-design","skill-creator:skill-creator"],"plugins":[{"name":"superpowers","path":"/Users/sanghyunlee/.claude/plugins/cache/superpowers-marketplace/superpowers/4.3.1"},{"name":"document-skills","path":"/Users/sanghyunlee/.claude/plugins/cache/anthropic-agent-skills/document-skills/1ed29a03dc85"},{"name":"frontend-design","path":"/Users/sanghyunlee/.claude/plugins/cache/claude-plugins-official/frontend-design/55b58ec6e564"},{"name":"skill-creator","path":"/Users/sanghyunlee/.claude/plugins/cache/claude-plugins-official/skill-creator/55b58ec6e564"},{"name":"swift-lsp","path":"/Users/sanghyunlee/.claude/plugins/cache/claude-plugins-official/swift-lsp/1.0.0"}],"uuid":"07d99189-0e6b-48dc-9b2e-206c46d2483b","fast_mode_state":"off"}
{"type":"rate_limit_event","rate_limit_info":{"status":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false},"uuid":"8c952288-966d-43e6-b6d7-6b87fabcc850","session_id":"119ea4da-9b47-46b0-8cd3-3ab1f2e64f57"}
{"type":"assistant","message":{"id":"4a38d7e0-7a96-4bfd-ba48-f01ac677f84b","container":null,"model":"<synthetic>","role":"assistant","stop_reason":"stop_sequence","stop_sequence":"","type":"message","usage":{"input_tokens":0,"output_tokens":0,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":null,"cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":null,"iterations":null,"speed":null},"content":[{"type":"text","text":"API Error: Rate limit reached"}],"context_management":null},"parent_tool_use_id":null,"session_id":"119ea4da-9b47-46b0-8cd3-3ab1f2e64f57","uuid":"4fbf0101-30dd-40d0-a8c0-716db38af9ce","error":"rate_limit"}
{"type":"result","subtype":"success","is_error":true,"duration_ms":788,"duration_api_ms":0,"num_turns":1,"result":"API Error: Rate limit reached","stop_reason":"stop_sequence","session_id":"119ea4da-9b47-46b0-8cd3-3ab1f2e64f57","total_cost_usd":0,"usage":{"input_tokens":0,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":0,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":"","iterations":[],"speed":"standard"},"modelUsage":{},"permission_denials":[],"uuid":"cef666b1-5ad0-492a-a232-9304c7a4c615"}

Steps to Reproduce

• The request is immediately rejected (788ms total, 0ms API time)
• Zero tokens consumed (input: 0, output: 0) — the request never reaches the model
• The session log shows a rate_limit_event with "status": "rejected" and "overageDisabledReason": "org_level_disabled"
• The issue first appeared on my Team (Premium) plan account
• Today it also started occurring on my Max ($200/month) plan account
• Standard 200K context window works normally on both accounts — the issue is isolated to the 1M context window

Claude Model

Opus

Is this a regression?

No, this never worked

Last Working Version

_No response_

Claude Code Version

2.1.62 (Claude Code)

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Warp

Additional Information

<img width="927" height="285" alt="Image" src="https://github.com/user-attachments/assets/4c76ad9d-3ced-4f67-9b26-ae4d2cb6644f" />