deep-research skill description estimate · request

{
  "id": "1892011bd21efd6d949268e3f99cf224c3e43a376ddc220c085b03ece9733661",
  "label": "estimate-skill-description-deep-research",
  "generatedAt": "2026-06-09T00:29:57.486Z",
  "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": "Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. - When the user wants a deep, multi-source, fact-checked research report on any topic. BEFORE invoking, check if the question is specific enough to research directly — if underspecified (e.g., \"what car to buy\" without budget/use-case/region), ask 2-3 clarifying questions to narrow scope. Then pass the refined question as args, weaving the answers in."
          }
        ]
      },
      {
        "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": "2eaa1f0a5d7ce4f65f567ac5da8072c9eedc51957d26b74ac4207f7b27300eff"
}