Hidden Features

The Claude Code source contains several feature flags and capabilities that are not publicly documented. These were found by reading the source code directly.

10 feature flags 4 hidden capabilities

i These are source code findings, not official documentation

These features were identified by analyzing the Claude Code source code. Feature flags may be enabled in future releases, modified, or removed. Status reflects behavior at time of analysis.

Feature flags

PROACTIVE / KAIROS experimental

Autonomous mode. Claude receives <tick> prompts that keep it alive and acts without user input. When terminal is unfocused it commits, pushes, and explores independently.

COORDINATOR_MODE experimental

Multi-agent orchestration. The main session acts as a coordinator that dispatches work to sub-agents and synthesizes their results.

BRIDGE_MODE documented

IDE integration bridge. Connects Claude Code to VS Code, JetBrains, and other editors for inline suggestions and context sharing.

DAEMON experimental

Background daemon mode. Claude runs as a persistent background process, processing tasks without a visible terminal session.

VOICE_MODE internal only

Voice input support. Enables speech-to-text for submitting prompts. Infrastructure exists in the source but not publicly released.

AGENT_TRIGGERS experimental

Enables CronCreate, CronDelete, CronList and RemoteTrigger tools. Allows scheduling recurring agent tasks on a cron schedule.

MONITOR_TOOL experimental

Enables the MonitorTool for performance and observability monitoring during agent execution.

CACHED_MICROCOMPACT documented

Auto-cleanup of old tool results in the context window. Replaces stale Read/Bash/Grep outputs with [Old tool result content cleared] to free token budget.

EXPERIMENTAL_SKILL_SEARCH experimental

Skill discovery mechanism. Dynamically finds and loads available skills from the plugin system based on the current task context.

VERIFICATION_AGENT documented

Activates the built-in Verification Agent that runs in the background after implementations and emits PASS / FAIL / PARTIAL verdicts.

Hidden capabilities

Beyond feature flags, the source reveals several built-in capabilities that are not prominently documented.

Undercover mode

For internal Anthropic users, model names and IDs are hidden from the system prompt. This prevents unannounced models from leaking into commits, PRs, or conversation history.

Scratchpad

A temporary, isolated directory created per session. Claude can write freely here without triggering permission prompts. It's an alternative to /tmp and is cleaned up after the session.

User hooks

Shell commands configured in settings.json that execute in response to events (tool calls, session start, etc.). Claude treats hook output as if it came directly from the user.

Worktree detection

Claude detects if it's running inside a git worktree and adjusts behavior accordingly. Specifically, it will not cd to the original repo root and respects the worktree isolation.

→ User hooks are the most practical hidden feature

Hooks let you run shell commands automatically in response to Claude Code events: before tool calls, after sessions, on specific triggers. They're configured in settings.json and Claude treats their output as user messages. This makes hooks a powerful way to automate workflows without changing your prompts.