Claude Code gets mods: extend behavior and UI via plugins
- Source
- x.com
- Date
Claude Code plugins can now carry mods: TypeScript extensions that reach into the agent's behavior and its interface rather than only adding commands or prompts. The team's examples show the range. One mod forecasts how much of the context window is left, another guards against risky shell commands, and a third adds a pane that replays diffs. Because mods ship through the existing plugin mechanism, teams can distribute internal guardrails or UI changes the same way they already share plugins. The caution is the same as for any local extension: mods run with the same machine access as Claude Code itself, so a mod from an untrusted source has the same reach as the agent. Treat installing one like adding a dependency, and review what it does before enabling it on a machine with credentials.
You can now mod Claude Code: - Change how it behaves - Customize the UI - Swap in your own features Write one with a few lines of TypeScript, or have Claude build it for you. Mods ship inside plugins, so you install them with /plugin in the CLI or desktop app. A few examples:
Token Weather adds a forecast of your context window: how full it is, plus a sparkline of your last 12 turns.
Blast Radius catches risky shell commands like rm -rf, git reset --hard, or a force push before they run. It shows what the command would touch in a side pane.
Replay Theater records every file edit Claude makes in a turn. Run /replay to step through the diffs one at a time in a docked pane.
Context
Anthropic's Claude Code mods let developers add behavior and interface elements to the coding . The announcement thread says mods are written in TypeScript and distributed inside plugins installed through the CLI or desktop application.
One example, Replay Theater, records the file edits made during a turn and lets users step through the changes in a docked pane. That makes the agent's work inspectable inside its own interface. The thread also states that mods have the same machine access as Claude Code, so installing one grants capabilities beyond changing its appearance.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Checking sign-in…
Loading comments…