claude-code

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

Updated Jun 7, 2026
One-click install
npx skills add https://github.com/Chensihakniroth/ANAKOT-AGENT --skill claude-code-chensihakniroth
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-code
Source: https://github.com/Chensihakniroth/ANAKOT-AGENT/tree/main/skills/autonomous-ai-agents/claude-code
Command: npx skills add https://github.com/Chensihakniroth/ANAKOT-AGENT --skill claude-code-chensihakniroth

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 cost limits, which is error-prone when done ad hoc. ## 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 explicit dialog handling for workspace trust and permission prompts. - Structured Output & Session Control: Capture JSON results with session IDs, token usage, and cost data, enforce JSON schemas for extraction, and resume or fork sessions across runs. - Use Case: A CI pipeline pipes a git diff into claude -p with --max-turns and --allowedTools to review a pull request for bugs and security issues, returning a structured JSON verdict without any interactive prompts. ## Quick Start Ask the agent to run claude -p with a coding task, an allowedTools whitelist, and a max-turns limit inside 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 in a script?▼

Use print mode with claude -p followed by your task prompt. It runs a one-shot task, skips all interactive dialogs, and exits when done. Add --max-turns to cap agentic loops and --allowedTools to whitelist tools like Read and Edit.

How do I get structured JSON output from Claude Code?▼

Pass --output-format json to receive a result object containing the response text, session_id, num_turns, total_cost_usd, and token usage. For validated structured data, add --json-schema with a JSON schema and parse the structured_output field.

How do I handle the Claude Code permission dialogs in tmux?▼

Send Enter for the workspace trust dialog since the default is Yes. For the bypass permissions warning, send Down then Enter because the default is No. The trust dialog appears only once per directory, while the permissions dialog recurs with --dangerously-skip-permissions.

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. Add --fork-session when resuming to create a new session ID while keeping the history.

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

Print mode runs a single task and exits, making it suited for automation and CI pipelines. Interactive mode provides a conversational REPL with slash commands like /compact and /review, requiring tmux orchestration for multi-turn iterative work.

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, both available in print mode. You can also select cheaper models with --model haiku or set --fallback-model for overload situations.