{ "id": "2f54b7403c3cac0bad04974e7afe5bc2e5cc4cdcc1403d9683902bc3b5b0e271", "label": "estimate-tool-Agent", "generatedAt": "2026-06-09T00:30:00.018Z", "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": "" }, "body": { "model": "claude-opus-4-8", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "\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\n\n" }, { "type": "text", "text": "say hi", "cache_control": { "type": "ephemeral" } }, { "type": "text", "text": "{\"description\":\"Launch a new agent to handle complex, multi-step tasks. Each agent type has specific capabilities and tools available to it.\\n\\nAvailable agent types and the tools they have access to:\\n- claude: Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed. (Tools: *)\\n- Explore: Read-only search agent for broad fan-out searches — when answering means sweeping many files, directories, or naming conventions and you only need the conclusion, not the file dumps. It reads excerpts rather than whole files, so it locates code; it doesn't review or audit it. Specify search breadth: \\\"medium\\\" for moderate exploration, \\\"very thorough\\\" for multiple locations and naming conventions. (Tools: All tools except Agent, ExitPlanMode, Edit, Write, NotebookEdit)\\n- general-purpose: General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you. (Tools: *)\\n- Plan: Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs. (Tools: All tools except Agent, ExitPlanMode, Edit, Write, NotebookEdit)\\n- statusline-setup: Use this agent to configure the user's Claude Code status line setting. (Tools: Read, Edit)\\n\\nWhen using the Agent tool, specify a subagent_type parameter to select which agent type to use. If omitted, the general-purpose agent is used.\\n\\n## When to use\\n\\nReach for this when the task matches an available agent type, when you have independent work to run in parallel, or when answering would mean reading across several files — delegate it and you keep the conclusion, not the file dumps. For a single-fact lookup where you already know the file, symbol, or value, search directly. Once you've delegated a search, don't also run it yourself — wait for the result.\\n\\n- The agent's final message is returned to you as the tool result; it is not shown to the user — relay what matters.\\n- Use SendMessage with the agent's ID or name to continue a previously spawned agent with its context intact; a new Agent call starts fresh.\\n- `isolation: \\\"worktree\\\"` gives the agent its own git worktree (auto-cleaned if unchanged).\\n- `run_in_background: true` runs the agent asynchronously; you'll be notified when it completes.\\n- When you launch multiple agents for independent work, send them in a single message with multiple tool uses so they run concurrently\",\"input_schema\":{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"additionalProperties\":false,\"properties\":{\"description\":{\"description\":\"A short (3-5 word) description of the task\",\"type\":\"string\"},\"isolation\":{\"description\":\"Isolation mode. \\\"worktree\\\" creates a temporary git worktree so the agent works on an isolated copy of the repo.\",\"enum\":[\"worktree\"],\"type\":\"string\"},\"model\":{\"description\":\"Optional model override for this agent. Takes precedence over the agent definition's model frontmatter. If omitted, uses the agent definition's model, or inherits from the parent.\",\"enum\":[\"sonnet\",\"opus\",\"haiku\"],\"type\":\"string\"},\"prompt\":{\"description\":\"The task for the agent to perform\",\"type\":\"string\"},\"run_in_background\":{\"description\":\"Set to true to run this agent in the background. You will be notified when it completes.\",\"type\":\"boolean\"},\"subagent_type\":{\"description\":\"The type of specialized agent to use for this task\",\"type\":\"string\"}},\"required\":[\"description\",\"prompt\"],\"type\":\"object\"},\"name\":\"Agent\"}" } ] }, { "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": "cec9f79bbdcb389c5d3ac1aab5ebf657fb147e1664949e6bb9b992bb67c281ac" }