claude-code

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

Updated Aug 19, 2026
One-click install
npx skills add https://github.com/swcstudiospace/aimeecodes --skill claude-code-swcstudiospace
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-code
Source: https://github.com/swcstudiospace/aimeecodes/tree/main/.aimee/skills/claude-code
Command: npx skills add https://github.com/swcstudiospace/aimeecodes --skill claude-code-swcstudiospace

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Orchestrating an autonomous coding agent from another AI agent or automation pipeline requires knowing the exact CLI flags, output formats, and interactive dialog handling of Claude Code, which are easy to get wrong and cause hung sessions or runaway costs. ## 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 the workspace trust and permissions-bypass confirmation dialogs with send-keys sequences. - Full CLI Reference: Covers subcommands, permission flags, hooks, MCP server configuration, custom subagents, slash commands, keyboard shortcuts, and CLAUDE.md memory hierarchy. - Use Case: From a CI pipeline, pipe a git diff into claude -p to get an automated code review as structured JSON, then resume that session later to request fixes. ## Quick Start Ask the agent to run a one-shot Claude Code task such as fixing a bug in a specific file using print mode with a turn limit and restricted allowed tools.

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 "your task"` which runs a one-shot task and exits without interactive prompts. Add `--max-turns` to limit agentic loops and `--output-format json` to get a structured result object with session_id, cost, and token usage.

How do I handle Claude Code confirmation dialogs in tmux?▼

The workspace trust dialog accepts the default with a plain Enter via tmux send-keys. The bypass-permissions dialog defaults to No, so you must send Down then Enter to select "Yes, I accept" before Claude starts working.

Can Claude Code output structured JSON for automation?▼

Yes, use `--output-format json` for a single result object or `--output-format stream-json --verbose` for newline-delimited streaming events. You can also pass `--json-schema` to force the output to validate against a specific schema.

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 <session_id>` to resume a specific session. In print mode, capture the session_id from the JSON output and pass it with `--resume`.

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. You can also use `--fallback-model haiku` to switch to a cheaper model when the default is overloaded.

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

Print mode (`-p`) runs a single task non-interactively and exits, skipping all dialogs, making it ideal for CI and scripting. Interactive mode provides a full REPL with slash commands and multi-turn conversation but requires PTY handling such as tmux for automation.