cskwork

Codex Goal Handoff — Testing skill for Claude Code

Testing community

Turn a ticket into a verified, deployed PR — wraps OpenAI Codex CLI's /goal Ralph loop with a 4-file durable spec, 4 HUMAN GATE approval tokens, and a one-line installer for Claude Code, Codex CLI, an.

How to install Codex Goal Handoff

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

What Codex Goal Handoff does

Alternatives in Testing

OpenAgentsControl — AI agent framework for plan-first development workflows with approval-based execution 4.8k ★
Goal — Đóng vai Skill Architect — phỏng vấn thông minh để trích xuất quy trình từ đầu người dùng, sinh AI Skill hoàn 310 ★
Baro — A CLI that turns a goal into a pull request - and a sandbox for testing concurrent AI coding agents on the Moz 120 ★

README

codex-goal-handoff

**Turn a ticket into a verified, reviewed, deployed PR — using OpenAI Codex `/goal`.**

What you get: a reproduction script, a scoped fix on a branch, green local + dev verification, an as-is/to-be PDF report, and a posted ticket comment — all from one ticket ID.
What you do: approve four APPROVED:Gx gate tokens (push, merge, deploy, public comment). Everything between gates is autonomous.
What it costs: one Codex /goal token budget (~500k–2M tokens for a typical ticket), and the four gate reviews. No proxy-signal completions: the agent re-runs every Verification command before claiming done.

[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](#license) [![Codex CLI ≥ 0.128.0](https://img.shields.io/badge/Codex_CLI-%E2%89%A50.128.0-black)](https://developers.openai.com/codex/cli) [![Works with Claude Code](https://img.shields.io/badge/Works_with-Claude_Code-D97757)](https://docs.claude.com/en/docs/claude-code) [![Works with Codex CLI](https://img.shields.io/badge/Works_with-Codex_CLI-000)](https://developers.openai.com/codex/cli) [![Works with .agents/skills](https://img.shields.io/badge/Works_with-.agents%2Fskills-555)](#install)

Why this exists

OpenAI's Codex CLI 0.128.0 shipped [`/goal`](https://developers.openai.com/blog/run-long-horizon-tasks-with-codex) — a persistent objective that runs the **Ralph Loop** (Plan → Act → Test → Review → Iterate) until done, paused, or out of budget. It's a real long-horizon agent.

But raw `/goal` has three problems for production work:

It does not stop on its own for irreversible actions (push, merge, deploy, externally-visible comments).
It happily accepts proxy signals as completion — "tests should pass," "the fix is in place" — without running them.
A short inline goal text gets truncated by mid-turn compaction (codex#19910), so substance has to live in f