Skill tool estimate · request
Stored count_tokens request for Skill tool estimate.
Record provenance
- Measurement
estimate-tool-Skill- Record ID
a345d53d4e5138dc88e183c6ecc664501e9a37f3fb179be7b42db8af2a381b8f- Exact artifact
raw/count-tokens/a345d53d4e5138dc88e183c6ecc664501e9a37f3fb179be7b42db8af2a381b8f.request.json
{
"id": "a345d53d4e5138dc88e183c6ecc664501e9a37f3fb179be7b42db8af2a381b8f",
"label": "estimate-tool-Skill",
"generatedAt": "2026-06-09T00:30:03.068Z",
"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\":\"Execute a skill within the main conversation\\n\\nWhen users ask you to perform tasks, check if any of the available skills match. Skills provide specialized capabilities and domain knowledge.\\n\\nWhen users reference a \\\"slash command\\\" or \\\"/<something>\\\", they are referring to a skill. Use this tool to invoke it.\\n\\nHow to invoke:\\n- Set `skill` to the exact name of an available skill (no leading slash). For plugin-namespaced skills use the fully qualified `plugin:skill` form.\\n- Set `args` to pass optional arguments.\\n\\nImportant:\\n- Available skills are listed in system-reminder messages in the conversation\\n- Only invoke a skill that appears in that list, or one the user explicitly typed as `/<name>` in their message. Never guess or invent a skill name from training data; otherwise do not call this tool\\n- When a skill matches the user's request, this is a BLOCKING REQUIREMENT: invoke the relevant Skill tool BEFORE generating any other response about the task\\n- NEVER mention a skill without actually calling this tool\\n- Do not invoke a skill that is already running\\n- Do not use this tool for built-in CLI commands (like /help, /clear, etc.)\\n- If you see a <command-name> tag in the current conversation turn, the skill has ALREADY been loaded - follow the instructions directly instead of calling this tool again\\n\",\"input_schema\":{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"additionalProperties\":false,\"properties\":{\"args\":{\"description\":\"Optional arguments for the skill\",\"type\":\"string\"},\"skill\":{\"description\":\"The name of a skill from the available-skills list. Do not guess names.\",\"type\":\"string\"}},\"required\":[\"skill\"],\"type\":\"object\"},\"name\":\"Skill\"}"
}
]
},
{
"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": "63d21970a4a400192c8be0ccbeebc97120036e1caaa25caa8f0118f57ad72417"
}