safe-ship

name

safe-ship

description

End-to-end safe shipping workflow — audit working tree, branch off main if needed, stage only intended files, verify, commit, push, open PR. Use when the user says $safe-ship, asks to "ship these changes", "commit and PR", "make a PR for this", "open a PR for these changes", or otherwise wants the entire commit-to-PR pipeline run safely. Prevents direct-to-main commits, accidental staging of personal/secret files, missed verification, and other procedural slips this project's CLAUDE.md forbids.

Codex Adapter

Read ../../../.claude/skills/safe-ship/SKILL.md completely and follow it as the canonical workflow for this skill.

• Resolve every relative script, reference, asset, and template path from the canonical skill directory under .claude/skills/safe-ship/.
• Read ../../../.agents/CODEX-SKILL-COMPATIBILITY.md and apply the status and exceptions for this skill.
• Translate Claude Code tool names to the available Codex equivalent as described by the repository AGENTS.md.
• Before any Claude Task, Agent, or Workflow step, confirm that the current Codex session exposes the required multi-agent tools. Do not replace independent review with self-review.
• Skill invocation alone does not authorize commit, push, PR, merge, deploy, migration, dependency installation, or another outward action unless that action is the user's explicit request.
• Follow Codex system, developer, sandbox, approval, and tool instructions when they differ from the canonical workflow.
• Keep the canonical Claude skill unchanged unless the user explicitly asks to edit the workflow itself.