claude-code

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

Updated Aug 21, 2026
One-click install
npx skills add https://github.com/TylerSimons1127/vibe --skill claude-code-tylersimons1127
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-code
Source: https://github.com/TylerSimons1127/vibe/tree/main/skills/autonomous-ai-agents/claude-code
Command: npx skills add https://github.com/TylerSimons1127/vibe --skill claude-code-tylersimons1127

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Orchestrating an autonomous coding agent from another agent or automation pipeline requires handling interactive prompts, permission dialogs, session state, and structured output, which is error-prone when done ad hoc. ## Core Features & Use Cases - Print Mode Automation: Run one-shot non-interactive tasks with claude -p, capturing JSON results with session IDs, cost, and token usage for scripting and CI/CD. - Interactive PTY Orchestration: Drive multi-turn Claude Code sessions through tmux, including handling workspace trust and permissions dialogs with send-keys sequences. - Structured Extraction & Sessions: Enforce JSON schemas on output, resume or fork sessions by ID, pipe files and diffs as stdin context, and run parallel instances. - Use Case: Pipe a git diff into claude -p to get an automated PR review, or spawn three tmux sessions to fix a bug, write tests, and update docs in parallel. ## Quick Start Ask the agent to run claude -p with a coding task and a max-turns limit in your project directory to get a one-shot autonomous code change.

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 for automation?▼

Use print mode with `claude -p "task"` which runs a one-shot task and exits without interactive prompts. Add `--max-turns` to cap agentic loops and `--output-format json` to capture structured results including session ID and cost.

How to handle Claude Code permission dialogs in tmux?▼

The workspace trust dialog accepts the default with Enter, but the bypass-permissions dialog defaults to "No" and requires sending Down then Enter via tmux send-keys. Trust dialogs only appear once per directory.

Can Claude Code output structured JSON for data extraction?▼

Yes, combine `--output-format json` with `--json-schema` to force output matching a schema, parsed from the `structured_output` field. Streaming is available via `stream-json` with `--verbose` for real-time token 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 <session_id>` to resume a specific session. The session ID is available in the JSON output of print mode runs.

What is the difference between print mode and interactive mode?▼

Print mode (`-p`) runs a single task and exits, skipping all dialogs, making it ideal for scripts and CI. Interactive mode provides a multi-turn REPL with slash commands but requires tmux orchestration to send prompts and capture output.

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

Set `--max-turns` to bound agentic loops and `--max-budget-usd` to cap spend in dollars for print mode. The JSON result reports `total_cost_usd` and per-model usage for tracking.