ExitPlanMode tool estimate · request

{
  "id": "ca647c6ed9524facbb39390ac58f30539aef9c3e9868662dcad711c51c258053",
  "label": "estimate-tool-ExitPlanMode",
  "generatedAt": "2026-06-09T00:30:01.720Z",
  "url": "https://api.anthropic.com/v1/messages/count_tokens?beta=true",
  "headers": {
    "anthropic-beta": "claude-code-20250219,context-1m-2025-08-07,interleaved-thinking-2025-05-14,context-management-2025-06-27,prompt-caching-scope-2026-01-05,mid-conversation-system-2026-04-07,advisor-tool-2026-03-01,effort-2025-11-24,token-counting-2024-11-01",
    "anthropic-version": "2023-06-01",
    "content-type": "application/json",
    "x-api-key": "<redacted>"
  },
  "body": {
    "model": "claude-opus-4-8",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "<system-reminder>\nAs you answer the user's questions, you can use the following context:\n# currentDate\nToday's date is 2026-06-08.\n\n      IMPORTANT: this context may or may not be relevant to your tasks. You should not respond to this context unless it is highly relevant to your task.\n</system-reminder>\n\n"
          },
          {
            "type": "text",
            "text": "say hi",
            "cache_control": {
              "type": "ephemeral"
            }
          },
          {
            "type": "text",
            "text": "{\"description\":\"Use this tool when you are in plan mode and have finished writing your plan to the plan file and are ready for user approval.\\n\\n## How This Tool Works\\n- You should have already written your plan to the plan file specified in the plan mode system message\\n- This tool does NOT take the plan content as a parameter - it will read the plan from the file you wrote\\n- This tool simply signals that you're done planning and ready for the user to review and approve\\n- The user will see the contents of your plan file when they review it\\n\\n## When to Use This Tool\\nIMPORTANT: Only use this tool when the task requires planning the implementation steps of a task that requires writing code. For research tasks where you're gathering information, searching files, reading files or in general trying to understand the codebase - do NOT use this tool.\\n\\n## Before Using This Tool\\nEnsure your plan is complete and unambiguous:\\n- If you have unresolved questions about requirements or approach, use AskUserQuestion first (in earlier phases)\\n- Once your plan is finalized, use THIS tool to request approval\\n\\n**Important:** Do NOT use AskUserQuestion to ask \\\"Is this plan okay?\\\" or \\\"Should I proceed?\\\" - that's exactly what THIS tool does. ExitPlanMode inherently requests user approval of your plan.\\n\\n## Examples\\n\\n1. Initial task: \\\"Search for and understand the implementation of vim mode in the codebase\\\" - Do not use the exit plan mode tool because you are not planning the implementation steps of a task.\\n2. Initial task: \\\"Help me implement yank mode for vim\\\" - Use the exit plan mode tool after you have finished planning the implementation steps of the task.\\n3. Initial task: \\\"Add a new feature to handle user authentication\\\" - If unsure about auth method (OAuth, JWT, etc.), use AskUserQuestion first, then use exit plan mode tool after clarifying the approach.\\n\",\"input_schema\":{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"additionalProperties\":{},\"properties\":{\"allowedPrompts\":{\"description\":\"Prompt-based permissions needed to implement the plan. These describe categories of actions rather than specific commands.\",\"items\":{\"additionalProperties\":false,\"properties\":{\"prompt\":{\"description\":\"Semantic description of the action, e.g. \\\"run tests\\\", \\\"install dependencies\\\"\",\"type\":\"string\"},\"tool\":{\"description\":\"The tool this prompt applies to\",\"enum\":[\"Bash\"],\"type\":\"string\"}},\"required\":[\"tool\",\"prompt\"],\"type\":\"object\"},\"type\":\"array\"}},\"type\":\"object\"},\"name\":\"ExitPlanMode\"}"
          }
        ]
      },
      {
        "role": "system",
        "content": "The following skills are available for use with the Skill tool:\n\n- deep-research: \n- update-config: \n- keybindings-help: \n- verify: \n- code-review: \n- simplify: \n- fewer-permission-prompts: \n- loop: \n- claude-api: \n- run: \n- init: \n- review: \n- security-review: "
      }
    ],
    "thinking": {
      "type": "adaptive"
    },
    "output_config": {
      "effort": "high"
    },
    "system": [
      {
        "type": "text",
        "text": "x-anthropic-billing-header: cc_version=2.1.168.c27; cc_entrypoint=sdk-ts; cch=e5b75;"
      },
      {
        "type": "text",
        "text": "You are a Claude agent, built on Anthropic's Claude Agent SDK.",
        "cache_control": {
          "type": "ephemeral"
        }
      }
    ]
  },
  "bodyCanonicalSha256": "e0d62a681eeb96ba427f141eb9bb2f398c640baaa806a4565c4d304b974bb94a"
}