Expired50% confidenceFactExact time
In Claude Code Skills, bound scripts are executed via the command line and the script code itself does not enter the context window—only execution results consume tokens
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Claude Code Skill Mechanism Explained: Progressive Loading & Practical Creation Guide
bilibili土木ai提效大古6/7/2026
Related Claims
UnverifiedScripts bound to a Skill are executed via the command line; the script code itself does not enter the context window, and only the execution results consume tokens.80% similarUnverifiedIn Claude Code's architecture, the model cannot directly execute tool operations; it can only return instructions to the harness for processing.64% similarUnverifiedIn Claude Code, background commands only notify the main session after the command completely exits, not during execution.63% similarUnverifiedIn Claude Code, foreground commands occupy the foreground and prevent users from entering other instructions simultaneously.62% similarUnverifiedCopilot CLI has Read Bash and Write Bash tools, which are features that Claude Code does not have.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/50630API
curl https://kongchang.com/api/v1/knowledge/claims/50630MCP
get_claim(id=50630)