phiat

Claude Esp Rs — Productivity skill for Claude Code

Productivity community

Stream Claude Code's hidden output (thinking, tool calls, subagents) to a separate terminal in real-time (Rust port).

How to install Claude Esp Rs

This entry records only its repository, not the path inside it, so there is no exact command to give. Open phiat/claude-esp-rs and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claude Esp Rs does

Stream Claude Code's hidden output (thinking, tool calls, subagents) to a separate terminal in real-time (Rust port).

Alternatives in Productivity

Tradingview MCP — Real-time crypto & stock screening, advanced technical indicators, Bollinger Bands intelligence, candlestick p 2.6k ★
GrokSearch — Integrate Grok's powerful real-time search capabilities into Claude via the MCP protocol 1.8k ★
Claude Code Hooks Multi Agent Observability — Real-time monitoring for multi-agent Claude Code sessions via hook event tracking 1.3k ★

README

claude-esp-rs

[![Crates.io](https://img.shields.io/crates/v/claude-esp)](https://crates.io/crates/claude-esp)

Stream Claude Code's hidden output (thinking, tool calls, subagents) to a separate terminal in real-time.

![claude-esp-rs screenshot](docs/screenshot.png)

**Note:** This is a Rust port of the [Go version](https://github.com/phiat/claude-esp). The binary is named `claude-esp-rs` to allow running both versions side-by-side.

The Problem

When using Claude Code interactively, tool outputs and thinking are collapsed by default and require pressing `Ctrl+O` to toggle visibility. This tool lets you watch all that output in a **separate terminal** with a nice TUI, without interrupting your main Claude Code session.

Features

Multi-session support - Watch all active Claude sessions simultaneously
Hierarchical tree view - Sessions with nested Main/Agent nodes
Real-time streaming - See thinking, tool calls, and outputs as they happen
Subagent tracking - Automatically discovers and displays subagent activity
Session events - Compaction boundaries, hook output, post-edit LSP diagnostics, PR-link events, prompt-cache misses (with reason + extra tokens), queue operations, slash-command invocations, transient notices, killed-subagent markers, plan/auto mode transitions, and skill/MCP/tool deltas surfaced inline
Agent type labels - Shows agent types (Explore, code-reviewer, etc.) from .meta.json
Token usage tracking - Cumulative input/output token counts in the header bar
Per-agent context size - Each Main/subagent row shows current context as a percentage of the model's max context window (Main 18%, Explore 9%). Denominator is the model's max window (1M for the Claude 5 family and opus-4-6 through 4-8 / sonnet-4-6, 200k for haiku-4-5), not the auto-compact threshold
Tool execution duration - Shows how long each tool call took
Background task visibility - See background tasks (⏳/✓) under