Skip to content
AI EmployeeSuper-AgentsAgent-to-AgentBenchmarksPricingBlog

Claude Code Mods and Custom Themes: What They Can Do

At a glanceQuick answers
What are Claude Code mods?
Plugins whose behavior lives in JavaScript or TypeScript handlers that Claude Code calls on events such as a tool call, a prompt or a redraw. They can change behavior, the interface and features.
Are mods safe to install?
Only from authors you trust. Anthropic’s docs say a mod runs with your permissions, is not sandboxed and can approve tool calls; inspect it first with claude plugin validate.
Can a Claude Code mod change the theme?
Yes, since November 13, 2026. A mod can set the Desktop app Code tab colors (v2.1.324 or later) and a backdrop in the Desktop or mobile app (v2.1.319 or later). The terminal keeps its own colors.
What version do I need?
Claude Code v2.1.287 or later. Mods are on by default; –safe-mode or disableAllHooks turns them off.
Editorial data illustration on a near-white ground titled Claude Code mods: puzzle pieces labeled pane, command, tool call and spinner snapping into a terminal window, with the permission prompt strip locked by an amber padlock, and the numbers 4 built-in mods and 2.1.287 minimum version
Fig 0Everything but the permission prompt. Made by CellCog's image agent, running GPT Image 2.5.

Anthropic has opened Claude Code to mods: plugins that change how the coding agent behaves and what it draws on screen. On October 1, 2026, the company’s developer account announced them in one line, “You can now mod Claude Code”, and the docs went live the same day. A mod is a set of JavaScript or TypeScript handlers that run inside Claude Code itself, not beside it.

This page is read from Anthropic’s mods documentation, the mods source folder on GitHub and the launch post on X.

On this page · 9 sectionsOpen
  1. What a mod can do
  2. Where they run
  3. November 13: custom themes on desktop
  4. The security fine print
  5. What is verified and what is not
  6. Why it matters
  7. What we are watching for
  8. Update log
  9. Sources
Key points6 · 7 min full read
  1. On October 1, 2026, Anthropic opened Claude Code to mods: JavaScript or TypeScript handlers that run inside Claude Code and change how it behaves and what it draws.
  2. A mod can draw panes and bands, restyle parts of Claude Code’s own interface, step into tool calls, answer them without running the tool, or send a request to a different model.
  3. Mods ship inside plugins, need Claude Code v2.1.287 or later, are on by default, and draw interface only in the terminal and the Desktop app’s Code tab.
  4. A mod runs with your permissions and is not sandboxed: it can read your files and API keys, see every prompt, approve tool calls and spend your usage.
  5. Since November 13, 2026, mods can set custom themes on desktop: colors for the Desktop app’s Code tab and a backdrop behind the conversation; the terminal keeps its own colors.
  6. Mods cannot change the permission prompt. Controls include claude plugin validate, –safe-mode, disableAllHooks and an administrator setting that limits which mods load.

§ 01What a mod can do

Claude Code already had settings hooks, skills, status lines and MCP servers. Those work from outside, by running a script or handing Claude text and tools. A mod is a function Claude Code calls when an event happens, such as a tool call, a submitted prompt or part of the interface being drawn, and the handler can watch, change or replace what happens next.

Capability Example from the docs
Draw your own interface A pane beside the transcript, or a band above the prompt with tabs, buttons and text fields
Redraw Claude Code’s interface Restyle a tool call’s row, the spinner, or the dialog Claude asks questions in
Step into a tool call or request Hold a call while you ask the user, answer it without running the tool, or send one request to a different model
Run code on a command A slash command that runs your function at once, with no Claude turn
Share data between hooks Count tool calls in one hook and show the count beside the spinner in another
Table 1What mods add, per Anthropic’s docs

The launch post sums up the authoring story: “Write one with a few lines of TypeScript, or have Claude build it for you.” Mods ship inside plugins and install from a marketplace with the usual plugin command. Four already ship inside Claude Code, including /diff and a mod that loads AGENTS.md as project instructions.

§ 02Where they run

Mods require Claude Code v2.1.287 or later and are on by default. Per the docs, “Mods work in the Claude Code CLI and in the Code tab of the Claude Desktop app.” Mod handlers can also run in other surfaces such as the VS Code extension and headless runs, but the interface a mod draws appears only in the terminal and the Desktop Code tab.

§ 03November 13: custom themes on desktop

On November 13, 2026, at 23:59 UTC, Anthropic’s developer account posted: “You can now build custom themes for Claude Code on desktop with mods!” (post). A follow-up a second later added: “Themes work in local sessions in the desktop app today, support for cloud sessions is coming soon.” (post). The launch post had about 1.8 million views by 14:00 UTC on November 15, and points to a theme-examples plugin for a quick start.

Piece What the docs say
Colors A mod calls $.theme.set with colors built from a few hex values by makeColors; it recolors the Desktop app’s Code tab and needs Claude Code v2.1.324 or later
Backdrop $.theme.set with a backdrop, drawn at the Backdrop render site, in the Desktop app or the mobile app; needs v2.1.319 or later
Terminal Draws no backdrop and keeps its own colors
One theme per session Any mod’s $.theme.set replaces the session’s colors and backdrop, and $.theme.clear() removes them, whichever mod set them
Old method $.ui.backdrop was removed in v2.1.319; $.theme.set and $.theme.clear replace it
Table 2Theming with mods, per Anthropic’s docs

The shortest path in the docs is to ask for it. Start a local session in the Code tab and describe the colors; the docs’ own example is “make a mod that makes the app cream in light mode and dark brown in dark mode”. Claude writes the mod’s files, asks you about them and about hot reloading, and the Code tab changes color when the mod loads. Per the docs, “The terminal draws no backdrop.” and “Claude Code in the terminal keeps its own colors.” Backdrops also widen one line above: they draw in the mobile app as well as the Desktop app.

A theme is still a mod, so everything in the next section applies to it: it runs with your permissions and is not sandboxed. A theme pack from a stranger is code from a stranger. The docs also ask mod authors to stay out of each other’s way: “Call $.theme.clear() only when the user asks for it.”

§ 04The security fine print

The docs are blunt about the risk, and this is the part teams should read before installing anything: “A mod is code that runs with your permissions.” It can read and write files anywhere your account can, read environment variables and settings files including API keys, see every prompt and tool call, and spend your usage. Mods are not sandboxed; turning on sandboxing isolates the Bash commands Claude runs, not processes a mod starts.

Access What it means
Your machine Read and write files, start programs, make network requests, as you
Your secrets Environment variables and settings files, including API keys
Your session Every prompt and tool call; it can rewrite them or submit prompts
Your approvals It can approve a tool call before you are asked
Your usage It can call a model on your plan or API key
Table 3What a loaded mod can reach, per Anthropic’s docs

One line holds firm: “A mod can restyle much of Claude Code’s interface, but not the permission prompt.” But a mod that approves tool calls can approve one an ask rule would have prompted for. Anthropic’s controls: inspect a mod first with claude plugin validate, start a session with --safe-mode, turn every mod off with disableAllHooks, and, for organizations, an administrator setting that limits which mods load.

§ 05What is verified and what is not

  • The feature and its limits are read from Anthropic’s docs on October 1, 2026.
  • No changelog entry yet. The public Claude Code changelog we checked did not list mods or v2.1.287 at the time of writing.
  • Themes are read from Anthropic’s mods interface docs on November 15, 2026, and the launch posts on X; we have not run a theme ourselves.
  • No marketplace of community mods has been announced; installs come from marketplaces you add.

§ 06Why it matters

Coding agents are becoming platforms. Mods turn Claude Code from a tool you configure into one you program, in the same way browsers became platforms through extensions. The trade is the same too: power arrives with a new supply chain. A mod from an untrusted marketplace can see everything the agent sees and approve what it does. For teams, the first job is the admin setting that decides which mods may load. For how agent harnesses compare, see our harness ranking and our post on Claude Code auto mode.

§ 07What we are watching for

  • A changelog entry and the first public mod marketplaces.
  • Security research on malicious mods, and any default change to how approving mods are flagged.
  • Whether Codex or Cursor answer with a comparable in-process extension model.

§ 08Update log

  • November 15, 2026: added custom themes on desktop (launch post November 13, 2026) and the theming table from Anthropic’s docs.
  • October 1, 2026: page opened, from Anthropic’s docs, the mods source folder and the launch post.

§ 09Sources

Frequently asked6 questions

Q1How do I install a Claude Code mod?

A mod installs as a plugin from a marketplace, with /plugin install name@marketplace in a session or claude plugin install in your shell. Run /reload-plugins to load it into an open session.

Q2Can a mod change the permission prompt?

No. Anthropic’s docs say mods can restyle much of the interface but not the permission prompt. A mod that approves tool calls can still approve a call before you are asked.

Q3How is a mod different from a Claude Code hook?

Settings hooks run a shell command, HTTP request or prompt from outside Claude Code. A mod’s handlers are functions that run inside Claude Code, so they can draw interface and share state.

Q4Can an organization block mods?

Yes. Anthropic documents an administrator setting that stops user-installed mods from loading while leaving managed ones running, plus disableAllHooks for individuals.

Q5How do I make a custom theme for Claude Code?

In a local session in the Desktop app’s Code tab, describe the colors you want and Claude writes the mod, or write one yourself with makeColors and $.theme.set. Anthropic also ships a theme-examples plugin.

Q6Where does CellCog fit?

We build AI employees for any role, engineering included. Each works in its own secure workspace, and commands that reach your world pass an approval step you control.

Published 02 October 2026 Last reviewed 15 November 2026 All Trust, permissions & security →