Skip to content
Trending storyDeveloping

Claude Mods: programmable harness plugins

1 reports1 sourcesUpdated 2 hours ago

What you need to know

AI summary

Dan McAteer describes Claude Mods as TypeScript or JavaScript plugins that hook into Claude Code events such as prompts, tool calls and interface renders, letting users shape the harness themselves. Anthropic already ships six built-in mods, including the off-by-default You Should Know side agent. McAteer contrasts this with OpenAI's ChatGPT Intelligent UI, where the model picks the interface, and Cursor's PR Routing & Approval, where teams write policy inside a fixed flow. He also flags downsides: noise, roughly 5–6k input-equivalent tokens per supervisor check, and no sandboxing.

Generated by AI from the reporting · updated 1 hour ago

Latest updateOct 21 13:04
Claude Mods: Flipping the Harness Inside Out

Timeline

Follow the reports to see every side of the story.

Oct 21
  1. Latent Space
    Claude Mods: Flipping the Harness Inside Out

    Dan McAteer argues Claude Mods turn Claude Code's harness into a programmable Attention Interface that users shape themselves. Mods are TypeScript or JavaScript plugins that hook into events like prompts, tool calls and interface renders, and Anthropic already ships six built-in ones, including the off-by-default You Should Know side agent. He contrasts this with OpenAI's ChatGPT Intelligent UI, where the model picks the interface, and Cursor's PR Routing & Approval, where teams write policy inside a fixed flow, and flags mod downsides: noise, roughly 5–6k input-equivalent tokens per supervisor check, and no sandboxing.

Heat trend for this story

Not enough continuous data yet to chart a trend.