claude-code

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

1|Updated Aug 11, 2026
One-click install
npx skills add https://github.com/Chia1104/agent-air --skill claude-code-chia1104
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-code
Source: https://github.com/Chia1104/agent-air/tree/main/skills/hermes/autonomous-ai-agents/claude-code
Command: npx skills add https://github.com/Chia1104/agent-air --skill claude-code-chia1104

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Orchestrating an autonomous coding agent from another agent requires knowing the right CLI flags, handling interactive permission dialogs, and managing sessions, which is error-prone without a reference guide. ## Core Features & Use Cases - Print Mode Automation: Run one-shot non-interactive tasks with claude -p, structured JSON output, JSON schema extraction, session resumption, and cost caps via --max-turns and --max-budget-usd. - Interactive PTY Orchestration: Drive multi-turn Claude Code sessions through tmux, including handling workspace trust and bypass-permissions dialogs with send-keys sequences. - Configuration & Extensibility: Covers settings hierarchy, CLAUDE.md memory files, custom subagents, hooks, MCP server integration, permissions, and slash commands. - Use Case: Pipe a git diff into claude -p for an automated PR review, or spawn 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 a coding task, an allowedTools whitelist, and a max-turns limit in the target 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 task prompt. It runs one-shot, skips all interactive dialogs, and exits when done. Add --max-turns to limit agentic loops and --output-format json for structured results.

How to handle Claude Code permission dialogs in tmux automation?▼

Send Enter via tmux send-keys to accept the default workspace trust dialog. For the --dangerously-skip-permissions warning, send Down then Enter to select "Yes, I accept", since the default is "No, exit".

Can Claude Code output structured JSON for parsing?▼

Yes, use --output-format json to get a result object with session_id, num_turns, total_cost_usd, and the result text. Add --json-schema to force output matching a specific schema, or stream-json for real-time events.

How do I resume a previous Claude Code session?▼

Use claude -c to continue the most recent conversation in the current directory, or claude -r with a session ID from a prior JSON output. Add --fork-session to branch the history into a new session ID.

What is the difference between print mode and interactive mode in Claude Code?▼

Print mode (-p) runs a single task and exits, ideal for automation and CI. Interactive mode provides a multi-turn REPL with slash commands like /compact and /review, requiring tmux orchestration when driven by another agent.

How do I limit Claude Code API costs in automated runs?▼

Set --max-turns to cap agentic loop iterations and --max-budget-usd to cap dollar spend in print mode. Use --fallback-model haiku to switch to a cheaper model when the default is overloaded.