Delegate coding tasks to alternative AI agent CLIs with session persistence.
npx skills add https://github.com/yoonhwan/ai-feature-pack --skill agent-cli
Please help me install this Agent Skill. Skill: agent-cli Source: https://github.com/yoonhwan/ai-feature-pack/tree/main/feature-pack/agent-cli Command: npx skills add https://github.com/yoonhwan/ai-feature-pack --skill agent-cli
When using an AI coding agent, you often need a second opinion, adversarial review, or specialized design input from a different model. Switching sessions breaks flow and loses context. This skill enables you to delegate tasks to other AI coding CLIs—Claude Code, Codex, Gemini, OpenCode, and Cursor Agent—directly from your current session, maintaining workflow continuity through non-interactive execution, persona injection, and session resume chains.
Use the agent-cli skill to delegate the current code review to Codex in DA mode for adversarial validation and resume the session with follow-up questions.
High-intent search queries and answers about installing and using this skill.
Cross-CLI delegation enables you to launch alternative AI coding agents non-interactively for code review or adversarial validation directly from your current session, maintaining workflow continuity without context switching. It supports session persistence for multi-round follow-ups.
Yes, you can run Gemini, Codex, Claude Code, OpenCode, or Cursor Agent non-interactively to cross-check code. The delegation mechanism applies autonomous driving flags and timeout protection via process group SIGKILL to ensure execution completes safely.
Persona injection works by injecting specialized system prompts into delegated agents, instantly assigning roles like Devil's Advocate, designer, or architect for targeted output. This enables adversarial validation, design critique, and architecture review workflows.
Cross-model session resume supports macOS, Linux, and WSL environments. Built-in environment validation automatically detects your OS and available CLIs, running self-test scripts to verify non-interactive execution and resume functionality.
Yes, perl and python3 are required dependencies to run the delegation scripts. These components handle non-interactive execution, autonomous driving flags, and environment validation across supported platforms.
The best way to perform adversarial validation is delegating tasks to alternative AI agent CLIs with persona injection and session resume chains. This enables progressive decision-making and human-in-the-loop refinement across different AI providers without manual context switching.
happy-nutInstall viban dependencies and configure CLAUDE.md workflows via interactive interview.
KohlexCoordinates multi-session loops across waves with validation and escalation handling.
edheltzelConvert Claude Code slash commands to OpenCode command format.
Manvendra08Manages REPL coding sessions with persistent cloudless storage and backups.
