Ship Off — Development skill for Claude Code
Disable ship-sop auto-mode.
How to install Ship Off
Installs to ~/.claude/commands/mmjclayton-ship-sop-ship-off.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/mmjclayton/ship-sop/HEAD/.claude/commands/ship-off.md -o ~/.claude/commands/mmjclayton-ship-sop-ship-off.md Restart Claude Code, or start a new session, for it to be picked up.
What Ship Off does
description: Disable ship-sop auto-mode. Sets trigger.mode to "manual" so the agent-sop Stop hook (`sop-stop-drift.sh`, user-scope) becomes a no-op. /ship and /release continue to work manually. ship_sop_version: "2026-04-25"
Flip ship-sop auto-mode off. The SessionStop hook stays wired but becomes a no-op — it reads the config, sees `trigger.mode: "manual"`, and exits silently. Manual `/ship` and `/release` continue to work.
Workflow
- Locate
ship-sop.config.json(project-level
Alternatives in Development
- Claude Context Mode — An MCP server that sits between Claude Code and these outputs 5.3k ★
- /discover — Run a full discovery loop without manually stitching together skills 2.3k ★
- Icpg Intent — Manually create or update an iCPG intent (ReasonNode) for a file before implementing 705 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Ship On
Enable ship-sop auto-mode. Sets trigger.mode to "auto" in ship-sop.config.json so the agent-sop Stop hook (sop
Work Release
Coordinate a release session — confirm scope, brief and run the required agents, verify against acceptance cri
Fly Action
Release management platform for software teams. Every build your CI produces becomes a tracked release — linke
Manual Context Update
Manually edit and synchronize CONTEXT.md and CLAUDE.md
Release & Shipping Burn Patterns — Research Summary
Research completed: 2026-02-10 Sources: ~/.claude/CLAUDE.md (This Has Burned You Before table), SESSION_HANDOF
Learn Review
Manually trigger a learning review of the current session
Related Agents
Part 11: Auto-Capture Hook (Stop Manually Writing Memory)
By Terp - Terp AI Labs --- The vault system from Part 9 is powerful, but there's a gap: you have to manually w
Comment Pruner
Autonomously prune bad comments from code added in the current session. Dispatched by the comment-pruner Stop
Story Doctor
Judges whether a video tells a whole story - does the hook promise something, is that promise paid off, does t