Unverified50% confidenceFactExact time
Configuring disable model invocation: true prevents the model from actively invoking the Skill; it can only be triggered manually by the user via a slash command, and the content will not be sent to the model.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/7/2026
First Seen
Valid until: 1/5/2027
Sources
Related Entities
Related Claims
UnverifiedSystem Prompt与用户输入本质上都是模型的输入token，模型并不存在独立的规则执行引擎来强制保证指令被遵守72% similarUnverifiedIn tool calling, the model itself does not execute code but is only responsible for deciding which tool to call, while actual execution authority remains in the host program controlled by the developer.64% similarUnverifiedPlaywright runs in headless mode by default; setting the configuration option headless to false or adding the --headed parameter on the command line switches it to headed mode.61% similarUnverified通过Bedrock访问Claude模型，用户无需直接与Anthropic签约，且数据不会被用于模型训练60% similarUnverifiedModelsphere claims to make no code modifications to the Cursor client, with the tool serving only two functions: intelligently allocating available accounts and recording consumption bills60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/985636API
curl https://kongchang.com/api/v1/knowledge/claims/985636MCP
get_claim(id=985636)