How Do Claude Code Mods Go Beyond Hooks?

Thariq Shihipar says Claude Code mods run inside the TypeScript runtime and go further than hooks. Internally the feature started under the name function hooks. Hooks register an event and then call a script. A mod can see how many turns are in the conversation, how many tokens have been used, and what the messages are, and there are many more events to register on. Because the work happens in process, a mod can spawn sub-agents, parse what comes back, use structured output, and modify the user interface. Hooks could never modify the user interface.

A dashboard mod he is building prompts Claude to keep a dashboard that is an artifact. Mods and artifacts compose. Mods sit in the Claude Code harness and change the agent loop, and the interface change is an added benefit. Artifacts are for viewing work at a high level and staying highly interactive, with room that can be much larger than a TUI or the desktop app.

Claude Code still asks people to remember a lot: call the dashboard skill that runs the loop, then test assumptions afterward. Little classifiers can hold the things a person cares about and what they want done, so the person does not have to remember as much.