Claude Mods
A plugin system extension capability for Claude Code that allows third-party plugins to modify Claude Code's deeper behavioral logic and intervene in core operational processes, providing developers with a space for deep customization.
Timeline (last 90 days)
Claude Mods is an early form of the Attention Interface.
The core design philosophy of Claude Mods is to shift the focus of the Agent Harness from machine execution to the human side, making the Harness an interface through which humans express intent and adjust behavior.
The "flipped Harness" of Claude Mods is reflected on three levels: modifiability (humans can directly adjust the Harness's behavior rules without modifying the model), observability (the Harness shows humans the decision process rather than only the output results), and intervenability (humans can insert instructions or correct direction at any time during execution).
Claude Mods is still at an early stage, and the original text does not provide specific implementation details or performance data.
本次更新引入Claude Mods功能，使插件可以修改Claude Code更深层的行为
All Facts (5)
Claude Mods is an early form of the Attention Interface.
50%UnverifiedThe core design philosophy of Claude Mods is to shift the focus of the Agent Harness from machine execution to the human side, making the Harness an interface through which humans express intent and adjust behavior.
50%UnverifiedThe "flipped Harness" of Claude Mods is reflected on three levels: modifiability (humans can directly adjust the Harness's behavior rules without modifying the model), observability (the Harness shows humans the decision process rather than only the output results), and intervenability (humans can insert instructions or correct direction at any time during execution).
50%UnverifiedClaude Mods is still at an early stage, and the original text does not provide specific implementation details or performance data.
50%Unverified本次更新引入Claude Mods功能，使插件可以修改Claude Code更深层的行为
50%