[
	{
		"scope": "https://api.anthropic.com:443",
		"method": "POST",
		"path": "/v1/messages",
		"body": {
			"model": "claude-haiku-4-5",
			"max_tokens": 64000,
			"system": [
				{
					"type": "text",
					"text": "Skill loading protocol:\nSkills are optional instruction packs, not execution tools. Use them to get extra guidance only when they are relevant to the user's current request.\n\nAvailable skills:\n- name: \"Engineering status formatter\"\n  description: \"Use for formatting engineering workflow status identifiers.\"\n  id: \"engineering-status\"\n  category: \"engineering\"\n\nWhen deciding whether to load a skill:\n- Match the user's request against the skill name and description.\n- If one skill clearly matches, call load_skill once with `{ \"skillId\": \"<id>\" }`, then follow the returned instructions.\n- If a loaded skill references a supporting file, call load_skill with `{ \"skillId\": \"<id>\", \"filePath\": \"<relative path>\" }`.\n- If the relevant skill was already loaded for this request, do not call load_skill again.\n- If no skill clearly matches, do not call load_skill.\n- Do not load a skill just because it is listed here.\n\nYou are testing runtime skill loading. Use the skill catalog in your instructions to pick a matching skillId. Call load_skill with the exact matching skillId before answering when a skill applies. After loading a skill, strictly follow its returned instructions. Do not answer from memory when a relevant skill applies."
				}
			],
			"messages": [
				{
					"role": "user",
					"content": [
						{
							"type": "text",
							"text": "The engineering-status skill applies. Load it first, then format status token waiting_on_vendor_info using the required tool."
						}
					]
				}
			],
			"tools": [
				{
					"name": "load_skill",
					"description": "Load a skill by skillId or name. This source does not support linked files, so do not pass filePath.",
					"input_schema": {
						"type": "object",
						"properties": {
							"skillId": {
								"type": "string",
								"minLength": 1,
								"description": "Skill id from the skill catalog."
							},
							"name": {
								"type": "string",
								"minLength": 1,
								"description": "Skill name from the skill catalog."
							}
						},
						"additionalProperties": false,
						"$schema": "http://json-schema.org/draft-07/schema#"
					}
				},
				{
					"name": "format_status",
					"description": "Format a workflow status token for display.",
					"input_schema": {
						"type": "object",
						"properties": {
							"status": {
								"type": "string",
								"description": "Workflow status token to format"
							}
						},
						"required": ["status"],
						"additionalProperties": false,
						"$schema": "http://json-schema.org/draft-07/schema#"
					}
				}
			],
			"tool_choice": {
				"type": "auto"
			}
		},
		"status": 200,
		"response": "{\"model\":\"claude-haiku-4-5-20251001\",\"id\":\"msg_0153mr7MZ5RaibNuJF3t1kkn\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"tool_use\",\"id\":\"toolu_017u8Xd5bungZRiNvzXXLg7p\",\"name\":\"load_skill\",\"input\":{\"skillId\":\"engineering-status\"},\"caller\":{\"type\":\"direct\"}}],\"stop_reason\":\"tool_use\",\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":1167,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":57,\"service_tier\":\"standard\",\"inference_geo\":\"not_available\"}}",
		"rawHeaders": {
			"anthropic-ratelimit-input-tokens-limit": "10000000",
			"anthropic-ratelimit-input-tokens-remaining": "10000000",
			"anthropic-ratelimit-input-tokens-reset": "2026-07-06T08:45:04Z",
			"anthropic-ratelimit-output-tokens-limit": "2000000",
			"anthropic-ratelimit-output-tokens-remaining": "2000000",
			"anthropic-ratelimit-output-tokens-reset": "2026-07-06T08:45:04Z",
			"anthropic-ratelimit-requests-limit": "20000",
			"anthropic-ratelimit-requests-remaining": "19999",
			"anthropic-ratelimit-requests-reset": "2026-07-06T08:45:03Z",
			"anthropic-ratelimit-tokens-limit": "12000000",
			"anthropic-ratelimit-tokens-remaining": "12000000",
			"anthropic-ratelimit-tokens-reset": "2026-07-06T08:45:04Z",
			"cf-cache-status": "DYNAMIC",
			"cf-ray": "a16d54c1fb0e589a-BCN",
			"connection": "keep-alive",
			"content-security-policy": "default-src 'none'; frame-ancestors 'none'",
			"content-type": "application/json",
			"date": "Mon, 06 Jul 2026 08:45:04 GMT",
			"request-id": "req_011CckWYjo6QtopbKeU9fVgX",
			"server": "cloudflare",
			"strict-transport-security": "max-age=31536000; includeSubDomains; preload",
			"traceresponse": "00-4575c6c2498118f4235cb15c53994d86-dd185342703b474e-01",
			"vary": "Accept-Encoding",
			"x-robots-tag": "none"
		},
		"responseIsBinary": false
	},
	{
		"scope": "https://api.anthropic.com:443",
		"method": "POST",
		"path": "/v1/messages",
		"body": {
			"model": "claude-haiku-4-5",
			"max_tokens": 64000,
			"system": [
				{
					"type": "text",
					"text": "Skill loading protocol:\nSkills are optional instruction packs, not execution tools. Use them to get extra guidance only when they are relevant to the user's current request.\n\nAvailable skills:\n- name: \"Engineering status formatter\"\n  description: \"Use for formatting engineering workflow status identifiers.\"\n  id: \"engineering-status\"\n  category: \"engineering\"\n\nWhen deciding whether to load a skill:\n- Match the user's request against the skill name and description.\n- If one skill clearly matches, call load_skill once with `{ \"skillId\": \"<id>\" }`, then follow the returned instructions.\n- If a loaded skill references a supporting file, call load_skill with `{ \"skillId\": \"<id>\", \"filePath\": \"<relative path>\" }`.\n- If the relevant skill was already loaded for this request, do not call load_skill again.\n- If no skill clearly matches, do not call load_skill.\n- Do not load a skill just because it is listed here.\n\nYou are testing runtime skill loading. Use the skill catalog in your instructions to pick a matching skillId. Call load_skill with the exact matching skillId before answering when a skill applies. After loading a skill, strictly follow its returned instructions. Do not answer from memory when a relevant skill applies."
				}
			],
			"messages": [
				{
					"role": "user",
					"content": [
						{
							"type": "text",
							"text": "The engineering-status skill applies. Load it first, then format status token waiting_on_vendor_info using the required tool."
						}
					]
				},
				{
					"role": "assistant",
					"content": [
						{
							"type": "tool_use",
							"id": "toolu_017u8Xd5bungZRiNvzXXLg7p",
							"name": "load_skill",
							"input": {
								"skillId": "engineering-status"
							},
							"caller": {
								"type": "direct"
							}
						}
					]
				},
				{
					"role": "user",
					"content": [
						{
							"type": "tool_result",
							"tool_use_id": "toolu_017u8Xd5bungZRiNvzXXLg7p",
							"content": [
								{
									"type": "text",
									"text": "[Skill: \"Engineering status formatter\"]\n[Skill category: \"engineering\"]\n[Skill hash: \"f62e1e0bd274\"]\n\nFor status-formatting requests, call the format_status tool with the exact status token from the user. Use the returned formatted value verbatim in the final answer and include STATUS_FORMATTED_BRAVO. Do not format the status manually."
								}
							]
						}
					]
				}
			],
			"tools": [
				{
					"name": "load_skill",
					"description": "Load a skill by skillId or name. This source does not support linked files, so do not pass filePath.",
					"input_schema": {
						"type": "object",
						"properties": {
							"skillId": {
								"type": "string",
								"minLength": 1,
								"description": "Skill id from the skill catalog."
							},
							"name": {
								"type": "string",
								"minLength": 1,
								"description": "Skill name from the skill catalog."
							}
						},
						"additionalProperties": false,
						"$schema": "http://json-schema.org/draft-07/schema#"
					}
				},
				{
					"name": "format_status",
					"description": "Format a workflow status token for display.",
					"input_schema": {
						"type": "object",
						"properties": {
							"status": {
								"type": "string",
								"description": "Workflow status token to format"
							}
						},
						"required": ["status"],
						"additionalProperties": false,
						"$schema": "http://json-schema.org/draft-07/schema#"
					}
				}
			],
			"tool_choice": {
				"type": "auto"
			}
		},
		"status": 200,
		"response": "{\"model\":\"claude-haiku-4-5-20251001\",\"id\":\"msg_01AncHteAYY9SRacTTHzKv6w\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"Now I'll format the status token as instructed:\"},{\"type\":\"tool_use\",\"id\":\"toolu_01LaHkuQAUWKJMdaMRfDEgPM\",\"name\":\"format_status\",\"input\":{\"status\":\"waiting_on_vendor_info\"},\"caller\":{\"type\":\"direct\"}}],\"stop_reason\":\"tool_use\",\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":1320,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":71,\"service_tier\":\"standard\",\"inference_geo\":\"not_available\"}}",
		"rawHeaders": {
			"anthropic-ratelimit-input-tokens-limit": "10000000",
			"anthropic-ratelimit-input-tokens-remaining": "9999000",
			"anthropic-ratelimit-input-tokens-reset": "2026-07-06T08:45:05Z",
			"anthropic-ratelimit-output-tokens-limit": "2000000",
			"anthropic-ratelimit-output-tokens-remaining": "2000000",
			"anthropic-ratelimit-output-tokens-reset": "2026-07-06T08:45:05Z",
			"anthropic-ratelimit-requests-limit": "20000",
			"anthropic-ratelimit-requests-remaining": "19999",
			"anthropic-ratelimit-requests-reset": "2026-07-06T08:45:04Z",
			"anthropic-ratelimit-tokens-limit": "12000000",
			"anthropic-ratelimit-tokens-remaining": "11999000",
			"anthropic-ratelimit-tokens-reset": "2026-07-06T08:45:05Z",
			"cf-cache-status": "DYNAMIC",
			"cf-ray": "a16d54c878bc589a-BCN",
			"connection": "keep-alive",
			"content-security-policy": "default-src 'none'; frame-ancestors 'none'",
			"content-type": "application/json",
			"date": "Mon, 06 Jul 2026 08:45:05 GMT",
			"request-id": "req_011CckWYpHUBbu1v83kyVSuv",
			"server": "cloudflare",
			"strict-transport-security": "max-age=31536000; includeSubDomains; preload",
			"traceresponse": "00-5d29afad8d6483cabba40e5acf4a5fbf-0d9b0424157724b8-01",
			"vary": "Accept-Encoding",
			"x-robots-tag": "none"
		},
		"responseIsBinary": false
	},
	{
		"scope": "https://api.anthropic.com:443",
		"method": "POST",
		"path": "/v1/messages",
		"body": {
			"model": "claude-haiku-4-5",
			"max_tokens": 64000,
			"system": [
				{
					"type": "text",
					"text": "Skill loading protocol:\nSkills are optional instruction packs, not execution tools. Use them to get extra guidance only when they are relevant to the user's current request.\n\nAvailable skills:\n- name: \"Engineering status formatter\"\n  description: \"Use for formatting engineering workflow status identifiers.\"\n  id: \"engineering-status\"\n  category: \"engineering\"\n\nWhen deciding whether to load a skill:\n- Match the user's request against the skill name and description.\n- If one skill clearly matches, call load_skill once with `{ \"skillId\": \"<id>\" }`, then follow the returned instructions.\n- If a loaded skill references a supporting file, call load_skill with `{ \"skillId\": \"<id>\", \"filePath\": \"<relative path>\" }`.\n- If the relevant skill was already loaded for this request, do not call load_skill again.\n- If no skill clearly matches, do not call load_skill.\n- Do not load a skill just because it is listed here.\n\nYou are testing runtime skill loading. Use the skill catalog in your instructions to pick a matching skillId. Call load_skill with the exact matching skillId before answering when a skill applies. After loading a skill, strictly follow its returned instructions. Do not answer from memory when a relevant skill applies."
				}
			],
			"messages": [
				{
					"role": "user",
					"content": [
						{
							"type": "text",
							"text": "The engineering-status skill applies. Load it first, then format status token waiting_on_vendor_info using the required tool."
						}
					]
				},
				{
					"role": "assistant",
					"content": [
						{
							"type": "tool_use",
							"id": "toolu_017u8Xd5bungZRiNvzXXLg7p",
							"name": "load_skill",
							"input": {
								"skillId": "engineering-status"
							},
							"caller": {
								"type": "direct"
							}
						}
					]
				},
				{
					"role": "user",
					"content": [
						{
							"type": "tool_result",
							"tool_use_id": "toolu_017u8Xd5bungZRiNvzXXLg7p",
							"content": [
								{
									"type": "text",
									"text": "[Skill: \"Engineering status formatter\"]\n[Skill category: \"engineering\"]\n[Skill hash: \"f62e1e0bd274\"]\n\nFor status-formatting requests, call the format_status tool with the exact status token from the user. Use the returned formatted value verbatim in the final answer and include STATUS_FORMATTED_BRAVO. Do not format the status manually."
								}
							]
						}
					]
				},
				{
					"role": "assistant",
					"content": [
						{
							"type": "text",
							"text": "Now I'll format the status token as instructed:"
						},
						{
							"type": "tool_use",
							"id": "toolu_01LaHkuQAUWKJMdaMRfDEgPM",
							"name": "format_status",
							"input": {
								"status": "waiting_on_vendor_info"
							},
							"caller": {
								"type": "direct"
							}
						}
					]
				},
				{
					"role": "user",
					"content": [
						{
							"type": "tool_result",
							"tool_use_id": "toolu_01LaHkuQAUWKJMdaMRfDEgPM",
							"content": "{\"formatted\":\"STATUS_FORMATTED_BRAVO: WAITING_ON_VENDOR_INFO\"}"
						}
					]
				}
			],
			"tools": [
				{
					"name": "load_skill",
					"description": "Load a skill by skillId or name. This source does not support linked files, so do not pass filePath.",
					"input_schema": {
						"type": "object",
						"properties": {
							"skillId": {
								"type": "string",
								"minLength": 1,
								"description": "Skill id from the skill catalog."
							},
							"name": {
								"type": "string",
								"minLength": 1,
								"description": "Skill name from the skill catalog."
							}
						},
						"additionalProperties": false,
						"$schema": "http://json-schema.org/draft-07/schema#"
					}
				},
				{
					"name": "format_status",
					"description": "Format a workflow status token for display.",
					"input_schema": {
						"type": "object",
						"properties": {
							"status": {
								"type": "string",
								"description": "Workflow status token to format"
							}
						},
						"required": ["status"],
						"additionalProperties": false,
						"$schema": "http://json-schema.org/draft-07/schema#"
					}
				}
			],
			"tool_choice": {
				"type": "auto"
			}
		},
		"status": 200,
		"response": "{\"model\":\"claude-haiku-4-5-20251001\",\"id\":\"msg_018vDNTGTPYvQft63MaduXM2\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"The status token has been formatted as requested:\\n\\n**STATUS_FORMATTED_BRAVO: WAITING_ON_VENDOR_INFO**\"}],\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":1425,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":33,\"service_tier\":\"standard\",\"inference_geo\":\"not_available\"}}",
		"rawHeaders": {
			"anthropic-ratelimit-input-tokens-limit": "10000000",
			"anthropic-ratelimit-input-tokens-remaining": "9999000",
			"anthropic-ratelimit-input-tokens-reset": "2026-07-06T08:45:06Z",
			"anthropic-ratelimit-output-tokens-limit": "2000000",
			"anthropic-ratelimit-output-tokens-remaining": "2000000",
			"anthropic-ratelimit-output-tokens-reset": "2026-07-06T08:45:06Z",
			"anthropic-ratelimit-requests-limit": "20000",
			"anthropic-ratelimit-requests-remaining": "19999",
			"anthropic-ratelimit-requests-reset": "2026-07-06T08:45:06Z",
			"anthropic-ratelimit-tokens-limit": "12000000",
			"anthropic-ratelimit-tokens-remaining": "11999000",
			"anthropic-ratelimit-tokens-reset": "2026-07-06T08:45:06Z",
			"cf-cache-status": "DYNAMIC",
			"cf-ray": "a16d54cf88d1589a-BCN",
			"connection": "keep-alive",
			"content-security-policy": "default-src 'none'; frame-ancestors 'none'",
			"content-type": "application/json",
			"date": "Mon, 06 Jul 2026 08:45:06 GMT",
			"request-id": "req_011CckWYu6wR6tBum89WmZrE",
			"server": "cloudflare",
			"strict-transport-security": "max-age=31536000; includeSubDomains; preload",
			"traceresponse": "00-0b21690b3bc7148f30f536a4baea9082-3a53115aa7a77a17-01",
			"vary": "Accept-Encoding",
			"x-robots-tag": "none"
		},
		"responseIsBinary": false
	}
]