Delegate coding tasks to the Claude Code CLI via print mode or tmux sessions.
npx skills add https://github.com/loteiron/ZeusAgent --skill claude-code-loteiron
Please help me install this Agent Skill. Skill: claude-code Source: https://github.com/loteiron/ZeusAgent/tree/main/skills/autonomous-ai-agents/claude-code Command: npx skills add https://github.com/loteiron/ZeusAgent --skill claude-code-loteiron
claude -p, structured JSON output, JSON schema extraction, piped input, session resumption, and cost/turn limits for CI pipelines. - Interactive PTY Orchestration: Manage multi-turn Claude Code sessions through tmux, including handling workspace trust and permission-bypass dialogs with send-keys sequences. - Configuration & Extensibility: Covers CLI flags, settings hierarchy, CLAUDE.md memory files, custom subagents, hooks, MCP server integration, and parallel instance management. - Use Case: Pipe a git diff into claude -p for an automated PR review, or spawn parallel tmux sessions where separate Claude instances fix a bug, write tests, and update docs simultaneously. ## Quick Start Ask the agent to run claude -p with your coding task, an allowedTools whitelist, and a max-turns limit in your project directory.High-intent search queries and answers about installing and using this skill.
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 --output-format json for structured results.
The workspace trust dialog defaults to "Yes", so send Enter via tmux send-keys. The bypass-permissions warning defaults to "No", so send Down then Enter to select "Yes, I accept". Trust dialogs only appear once per directory.
Yes, use --output-format json to get a result object with session_id, num_turns, total_cost_usd, and the result text. You can also pass --json-schema to force output matching a specific schema, or stream-json for real-time events.
Use claude -c to continue the most recent conversation in the current directory, or claude -r with a session ID to resume a specific one. In print mode, extract session_id from JSON output and pass it with --resume.
Print mode (-p) runs a single task and exits, ideal for scripting and CI. Interactive mode provides a conversational REPL with slash commands and follow-up prompts, but requires tmux orchestration to send input and capture output programmatically.
Set --max-turns to cap agentic iterations (5-10 works for most tasks) and --max-budget-usd to cap API spend in dollars. Both flags work in print mode only, and --fallback-model switches models when the default is overloaded.
samuelbonifacio015Automate coding tasks via the Claude Code CLI with Git integration.
kiranimmadi2Reviews local git changes and remote GitHub pull requests for correctness and maintainability.
DrinkBooozOrchestrate parallel AI agent sessions across multiple harnesses using dmux panes.
buvisAutomate Codex CLI code analysis, refactoring, and edits with permission controls.