Understand this story
On October 22, 2026, Shao Meng relayed Dan McAteer's article on latentspacepod, proposing that Claude Mods is an early form of the attention interface and that Harness may evolve into a platform. The view holds that Claude Mods lets users and Claude together use code to modify the human-facing layer of Claude Code, deciding when to interrupt, what to display, and which decisions to let users make. Mods are essentially TS/JS plugins that listen to prompt, tool call, and interface rendering events, usable in both CLI and desktop, and the official release has built in 6 Mods: agents-md, diff, plugin-authoring, sec-default, telemetry, and you-should-know. Dan also pointed out a noise problem: after installing on October 15, 99 of 111 rounds triggered Supervisor, each check consuming about 5–6k equivalent input tokens, and Mods run with user permissions and have no sandbox.
AI-generated from public reports
Latest development · Report
Claude Mods In-Depth: Harness Shifts from Managing Machines to Managing Human AttentionDevelopments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 22
Shao Meng
Claude Mods In-Depth: Harness Shifts from Managing Machines to Managing Human Attention
Shao Meng relays Dan McAteer's article on latentspacepod, arguing that Claude Mods lets users and Claude work together to use code to transform the human-facing layer of Claude Code—deciding when to interrupt, what to display, and which decisions to let users make—and that it is an early form of an attention interface. Mods are essentially TS/JS plugins that listen to prompt, tool-call, and interface-rendering events, and work in both the CLI and the desktop app. The official release already includes 6 built-in Mods: agents-md, diff, plugin-authoring, sec-default, telemetry, and you-should-know. Dan also points out the noise problem: after installing it on October 15, Supervisor was triggered in 99 out of 111 rounds; in addition, each check consumes about 5–6k equivalent input tokens, and Mods run with user permissions and have no sandbox.