iiwish

Agent CLI Runtime — Productivity skill for Claude Code

Productivity community

Unified TypeScript runtime for Codex CLI, Claude Code, and OpenCode with typed events, lifecycle control, permissions, and task graphs.

How to install Agent CLI Runtime

This entry records only its repository, not the path inside it, so there is no exact command to give. Open iiwish/agent-cli-runtime and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agent CLI Runtime does

Unified TypeScript runtime for Codex CLI, Claude Code, and OpenCode with typed events, lifecycle control, permissions, and task graphs.

Alternatives in Productivity

Grow A Product — Workflow recipe — turn a growth goal into a funnel diagnosis, experiment backlog, retention loop, and lifecycl 1.3k ★
Maestro Issue — Intent-driven issue lifecycle management — describe what you want in natural language (报告一个 bug / 列出开放 issue / 530 ★
Obsidian Daily — Create or update today's daily note — pulls calendar events, overdue tasks, and conversation context 277 ★

README

Agent CLI Runtime

[!IMPORTANT] **Maintenance mode.** This repository is archived and is not under active development. Existing releases remain available without compatibility guarantees or planned feature updates. For new multi-agent integrations, prefer [Agent Client Protocol](https://agentclientprotocol.com/) or the official SDK of your selected agent.

The Universal Adapter & Execution Engine for Local Coding Agents

English | 简体中文

**Agent CLI Runtime** is the dependable adapter layer you reach for when you do **not** want to build yet another coding agent.

Modern local coding agents (like Codex CLI, Claude Code, and OpenCode) already excel at planning, editing files, running tools, asking for permissions, and managing LLM loops. This runtime keeps those complex loops *inside* the user's installed CLI while giving product builders and developers a unified, typed Node.js/TypeScript API to programmatically orchestrate them.

💡 Why Agent CLI Runtime?

Building developer tools with local coding agents usually means wrestling with non-standardized CLI flags, parsing chaotic terminal streams, managing subprocess timeouts, and dealing with permission leaks.

Agent CLI Runtime normalizes this chaotic landscape into a clean, predictable, and local-first execution layer: