Características Ocultas

El código fuente de Claude Code contiene varios feature flags y capacidades que no están documentados públicamente. Fueron encontrados leyendo el código fuente directamente.

10 feature flags 4 capacidades ocultas

i Estos son hallazgos del código fuente, no documentación oficial

Estas funciones se identificaron analizando el código fuente de Claude Code. Los feature flags pueden habilitarse en versiones futuras, modificarse o eliminarse. El estado refleja el comportamiento en el momento del análisis.

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 documentado

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 solo interno

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 documentado

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 documentado

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

Capacidades ocultas

Más allá de los feature flags, el código fuente revela varias capacidades integradas que no están documentadas de forma destacada.

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.

→ Los hooks de usuario son la característica oculta más práctica

Los hooks te permiten ejecutar comandos de shell automáticamente en respuesta a eventos de Claude Code: antes de llamadas a herramientas, al terminar sesiones, en triggers específicos. Se configuran en settings.json y Claude trata su salida como mensajes del usuario. Esto convierte los hooks en una forma potente de automatizar flujos de trabajo sin cambiar tus prompts.