i
News
All Research News
News · 2026-10-03

Anthropic adds Mods to let developers change Claude Code from within

@neuronium_ai @neuronium_ai

Anthropic has added Mods to Claude Code, a way to change how the coding tool behaves from inside the product. The extensions can run in the command-line and desktop apps, with partial support in the VS Code extension. Anthropic has also published example Mods on GitHub and introduced its first official plugin, which flags information in Claude’s answers that a user might have missed. The key trade-off is that Mods run with the user’s permissions and are not sandboxed.

Cover: Anthropic adds Mods to let developers change Claude Code from within

Where Mods run

Mods run with the user’s permissions, and Anthropic says they are not isolated in a sandbox. The company recommends installing them only from trusted sources. Organizations can restrict which Mods are allowed to load.

Support varies by interface:

Command-line app: supported
Desktop app: supported
VS Code extension: partial support

The first official plugin

Anthropic’s first official plugin is called “You Should Know.” It runs a separate agent that monitors Claude’s answers and sends a “Worth noting” message when it spots important information the user may have missed.

Enable it with:

Код
/plugin enable cc-plugin-you-should-know@builtin

The more interesting question is how much control users and organizations get over what a separate agent considers important. I think the permission model makes that question especially consequential: Mods can alter the tool from within, but they are not contained in a sandbox.

Source: the-decoder.com

Source

Daily AI news

Every day we pick what actually matters in AI and explain it plainly — no hype, no filler. Subscribe if you want to follow where the industry is going.

Only what matters — every day

Follow on X