Orchestrate Codex, Claude Code, Pi, and OpenCode agents for coding tasks.
npx skills add https://github.com/bitan-del/gods-eye --skill coding-agent-bitan-del
Please help me install this Agent Skill. Skill: coding-agent Source: https://github.com/bitan-del/gods-eye/tree/main/skills/coding-agent Command: npx skills add https://github.com/bitan-del/gods-eye --skill coding-agent-bitan-del
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
Start a quick one-shot coding task by launching Codex in a git-tracked workspace or a scratch repository and issuing your prompt.
Start a quick one-shot coding task by launching Codex in a git-tracked workspace or a scratch repository and issuing your prompt.
High-intent search queries and answers about installing and using this skill.
You can delegate coding tasks to background AI agents by orchestrating Codex, Claude Code, Pi, or OpenCode agents for feature development, PR reviews in temporary directories, and refactoring. This automation coordinates multiple agents using specific invocation rules and safety guardrails.
Use background coding agents for building new features, reviewing PRs in temp directories, refactoring large codebases, and iterative coding needing file exploration. Avoid them for simple one-liner fixes—just edit directly—or for reading code, where standard read tools are faster.
Claude Code does not require a PTY for background coding orchestration. It must be invoked with the --print and --permission-mode bypassPermissions flags. Conversely, Codex, Pi, and OpenCode agents strictly require pty:true to function properly.
Yes, you can use background AI agents to review PRs by spawning the agent in a temporary directory. This isolates the review process, allowing the AI agent to safely explore files and assess changes without affecting your main workspace.
Limitations include avoiding use for simple one-liner fixes, reading code, or thread-bound ACP harness requests in chat. Additionally, you must never spawn background agents within the ~/clawd workspace to ensure secure and predictable automation.
To start a quick one-shot coding task, launch Codex in a git-tracked workspace or a scratch repository and issue your prompt. This allows the background agent to safely make changes and explore files within a controlled environment.
JansenAnalyticsDelegate coding tasks to Codex, Claude Code, or Pi agents via background PTY sessions.
rjroyDelegate coding, testing, and review tasks to specialized agents with phased execution.
bitan-delRoute plain-language ACP harness requests to OpenClaw or acpx runtime paths.
Solitude01Delegate coding tasks to AI agents via a background PTY-enabled process.
