claude-code

Delegate coding tasks to the Claude Code CLI via print mode or tmux interactive sessions.

1|Updated Jul 22, 2026
One-click install
npx skills add https://github.com/IceHeartGitH/Hermes-Agent-Android-Termux --skill claude-code-iceheartgith
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-code
Source: https://github.com/IceHeartGitH/Hermes-Agent-Android-Termux/tree/main/custom-skills/autonomous-ai-agents/claude-code
Command: npx skills add https://github.com/IceHeartGitH/Hermes-Agent-Android-Termux --skill claude-code-iceheartgith

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @anthropic-ai/claude-code, tmux.

What problem does it solve? Orchestrating an autonomous coding agent from a terminal assistant requires knowing the right CLI flags, handling interactive permission dialogs, and managing sessions, which is error-prone without a structured guide. ## Core Features & Use Cases - Two Orchestration Modes: Run one-shot non-interactive tasks with claude -p print mode, or drive multi-turn interactive REPL sessions through tmux with PTY dialog handling. - Structured Output & Automation: Extract JSON results, stream events, enforce JSON schemas, resume sessions, and cap spend with --max-turns and --max-budget-usd for CI/CD pipelines. - Full CLI Reference: Covers subcommands, permission flags, hooks, MCP server integration, custom subagents, slash commands, and CLAUDE.md memory configuration. - Use Case: Pipe a git diff into claude -p to get an automated PR review, or run parallel tmux sessions where separate Claude instances fix bugs, write tests, and update docs simultaneously. ## Quick Start Ask the agent to run claude -p with your coding task, allowed tools, and a max-turns limit in your project directory.

Frequently Asked Questions about claude-code

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run Claude Code non-interactively from a script?▼

Use print mode with claude -p followed by your prompt, which runs a one-shot task and exits without interactive prompts. Add --max-turns to limit agentic loops and --output-format json for structured results in CI pipelines.

How to handle Claude Code permission dialogs in tmux?▼

Send Enter via tmux send-keys to accept the default workspace trust dialog. For the bypass permissions warning, send Down then Enter since the safe default is 'No, exit'. The trust dialog only appears once per directory.

What is the difference between claude -p and interactive mode?▼

Print mode (-p) runs a single task and exits, skipping all interactive dialogs, making it ideal for automation. Interactive mode provides a conversational REPL with slash commands and follow-up prompts but requires tmux orchestration.

Can Claude Code resume a previous session?▼

Yes, use claude -c to continue the most recent conversation in the current directory, or claude -r with a session ID to resume a specific session. The --fork-session flag creates a new session ID while keeping history.

How do I limit Claude Code API costs in automation?▼

Set --max-turns to cap agentic loop iterations and --max-budget-usd to cap dollar spend in print mode. The JSON output includes total_cost_usd and usage fields for tracking spend per run.

Does Claude Code support MCP servers in CI mode?▼

Yes, load MCP servers in print mode with --mcp-config pointing to a JSON file, and use --strict-mcp-config to ignore all other MCP configurations. Combine with --bare for the fastest startup without hooks or plugins.