Anthropic ships Mods to let devs rewrite Claude Code

3 Key Points

What happened
Anthropic released "Mods" for Claude Code, JavaScript or TypeScript functions that hook into events like tool calls, user prompts, and UI rendering. Mods can add custom panels, intercept tool calls, or create new commands.
Why it matters
The plugin system lets developers change how the coding tool looks and works from the inside, rather than only through settings Anthropic controls. Mods run with the user's own permissions and aren't sandboxed, so Anthropic warns users to install only from trusted sources.
What to watch
Organizations can control which Mods are allowed to load, so the test is whether that gate plus the unsandboxed design is enough to satisfy security teams. Watch the first official Mod plugin, "You Should Know."

WHO IT HITSDevelopers using Claude Code gain a way to customize the tool directly, but IT and security teams at organizations that deploy it will need to manage which Mods are allowed to load, since Mods run unsandboxed with the user's permissions.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Get news like this every morning, free

Context & Analysis

Anthropic built Mods as middleware that runs directly inside Claude Code, hooking into events from tool calls and user prompts to UI rendering. The company says some built-in features are already built as Mods, and it provides sample Mods on GitHub. The first official Mod plugin is called "You Should Know," which spins up a separate agent that watches Claude's output and sends a "Heads up" message when it spots important information users might have missed, enabled with the command /plugin enable cc-plugin-you-should-know@builtin.

The design trades openness for responsibility. Mods run with the user's permissions and aren't sandboxed, so Anthropic warns users to only install them from trusted sources. Organizations can control which Mods are allowed to load, which may be the main lever for businesses weighing the flexibility against the risk. How the system is used in practice may hinge on whether that organizational control is enough for security-conscious teams.

FAQ

Are Mods sandboxed for safety?: No. Mods run with the user's permissions and aren't sandboxed, so Anthropic warns users to only install them from trusted sources.
Can companies limit which Mods their developers use?: Yes. Organizations can control which Mods are allowed to load.
Where do Mods work?: They work in the CLI, the desktop app, and partly in the VS Code extension.

THE DECODERRead Original Article

Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Get it free

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.