claude-agent-terminal-ts

claude-agent-terminal-ts is a skill for Claude Code, Codex from olaservo/mcp-agent-skills. It costs 24 tokens per session (1,375 once invoked), scanned A, original, Apache-2.0.

A React chat interface styled like a terminal for Claude Agent SDK agents. It includes keyboard navigation, tool approval prompts, saved chat history, and session recovery after a page reload.

In plain words
What is it for?
Building a developer-focused agent console with command history, expandable tool calls, approval controls, a dark theme, and SQLite-backed conversations.
Why use it?
It provides the terminal-style client and supporting patterns needed to make an agent usable through a browser.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Building a developer-focused agent console with command history, expandable tool calls, approval controls, a dark theme, and SQLite-backed conversations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/olaservo/mcp-agent-skills/claude-agent-terminal-ts
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add olaservo/mcp-agent-skills --skill claude-agent-terminal-ts
Clone the repo
git clone --depth 1 https://github.com/olaservo/mcp-agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-agent-terminal-ts

README.md
[![agentmods](https://agentmods.dev/badge/skills/olaservo/mcp-agent-skills/claude-agent-terminal-ts/github.svg)](https://agentmods.dev/skills/olaservo/mcp-agent-skills/claude-agent-terminal-ts)
Your own site
<a href="https://agentmods.dev/skills/olaservo/mcp-agent-skills/claude-agent-terminal-ts"><img src="https://agentmods.dev/badge/skills/olaservo/mcp-agent-skills/claude-agent-terminal-ts/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-agent-terminal-ts

Your own site · 80×15
<a href="https://agentmods.dev/skills/olaservo/mcp-agent-skills/claude-agent-terminal-ts"><img src="https://agentmods.dev/badge/skills/olaservo/mcp-agent-skills/claude-agent-terminal-ts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,375 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.01375
Opus 5.5 $0.00010 $0.00550
Sonnet 5.5 $0.00005 $0.00275
Haiku 4.5 $0.00002 $0.00137

Measured 2mo ago against content hash 0b80187c7672, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-agent-terminal-ts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/claude-agent-terminal-ts/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Agent Terminal UI

A retro terminal-inspired chat interface for Claude Agent SDK agents.

Features

  • Dark monospace theme (VS Code-inspired colors)
  • Input history with arrow key navigation
  • Collapsible tool call blocks with status badges
  • Inline tool approval prompts (Approve/Reject)
  • Auto-scroll to latest message
  • SQLite persistence for chat history
  • SDK session resumption across page reloads

Prerequisites

  • Node.js 18+
  • Claude Agent SDK (@anthropic-ai/claude-agent-sdk)
  • Claude Code authentication (claude login)

Quick Start

1. Install Dependencies

# Server dependencies
npm install express cors ws @anthropic-ai/claude-agent-sdk better-sqlite3
npm install -D @types/better-sqlite3 @types/express @types/cors @types/ws tsx typescript

# Client dependencies
npm install react react-dom @mantine/core @mantine/hooks @tabler/icons-react

2. Copy Snippets

Copy these files to your project:

  • client.tsx and styles.css from this skill
  • websocket-server-sqlite.ts and websocket-types.ts from claude-agent-sdk-ts skill
your-project/
  src/
    client.tsx      # Terminal React component (this skill)
    styles.css      # Terminal theme (this skill)
    server.ts       # WebSocket server (from claude-agent-sdk-ts)
    types.ts        # Shared types (from claude-agent-sdk-ts)

3. Configure Server

Edit the server CONFIG section:

const CONFIG = {
  port: 3001,
  workingDirectory: process.cwd(),
  model: "sonnet",  // opus, sonnet, or haiku
  allowedTools: ["Bash", "Read", "Write", "Edit", "Glob", "Grep"],
  systemPrompt: "You are a helpful AI assistant.",
  dbPath: "./chat.db",
};

4. Start Server

npx tsx server.ts

5. Use Component

import { TerminalChat } from './client';
import './styles.css';

function App() {
  return (
    <div style={{ height: '100vh' }}>
      <TerminalChat wsEndpoint="ws://localhost:3001/ws" />
    </div>
  );
}

Architecture

Read the full file on GitHub · 207 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 207 lines · 24 tokens per session scan A 0b80187c7672

Subscribe to this mod's changes

claude-agent-terminal-ts is a skill published in the GitHub repository olaservo/mcp-agent-skills (2 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,375 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

claude-agent-terminal-ts compared with skills from other repositories

claude-agent-terminal-ts next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claude-agent-terminal-tsolaservo/mcp-agent-skillsSkill29mo agoApache-2.0A24Claude Code, Codex
build-ghost-appTryGhost/GhostSkill56ktodayMITA44Claude Code, Codex
chakra-ui-builderchakra-ui/chakra-uiSkill41k2d agoMITA214Claude Code, Codex
material-ui-tailwindmui/material-uiSkill99ktodayMITA67Claude Code, Codex
fuzzy-rankingTanStack/tableSkill29k5d agoMITA62Claude Code, Codex
r3f-best-practiceszebbern/claude-code-guideSkill4.7ktodayMITA74Claude Code, Codex
git-safetytamagui/tamaguiSkill14kyesterdayMITA0Claude Code