ship

ship is a skill for Claude Code from TweekFawkes/prompts. It costs 134 tokens per session (3,362 once invoked), scanned A, original, Unlicense.

A workflow for finishing a coding task by committing changes, opening and merging a GitHub pull request, updating main, and checking that the worktree is safe to delete.

In plain words
What is it for?
Shipping work created through the ticket workflow, optionally opening a pull request for review only, and verifying the completed worktree.
Why use it?
It handles the release steps after implementation and checks that no work or project files are left behind.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument; mentions Codex.

Good fit Shipping work created through the ticket workflow, optionally opening a pull request for review only, and verifying the completed worktree.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tweekfawkes/prompts/ship
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add TweekFawkes/prompts --skill ship
Clone the repo
git clone --depth 1 https://github.com/TweekFawkes/prompts

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ship

README.md
[![agentmods](https://agentmods.dev/badge/skills/tweekfawkes/prompts/ship/github.svg)](https://agentmods.dev/skills/tweekfawkes/prompts/ship)
Your own site
<a href="https://agentmods.dev/skills/tweekfawkes/prompts/ship"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/ship/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ship

Your own site · 80×15
<a href="https://agentmods.dev/skills/tweekfawkes/prompts/ship"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00134 $0.03362
Opus 5 $0.00067 $0.01681
Sonnet 5 $0.00027 $0.00672
Haiku 4.5 $0.00013 $0.00336

Measured 9d ago against content hash c7a6b8aba352, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ship scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ship/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ship — Commit, PR, merge, and prove this worktree is safe to delete

Run this inside the feature worktree, after /dowork has finished (or after any other change you're ready to land).

Goal: every change in this worktree lands on main through a merged GitHub PR, the main checkout is current, and you can state plainly whether deleting the worktree would lose anything. You do the merge; the user deletes the worktree.

This does the same job as /landtomain, tuned for the /newticket/dowork/ship pipeline: it expects (but doesn't require) a ticket that just moved to z_tickets/closed/, and it fast-forwards main correctly even when main is checked out in a different worktree than this one — the normal setup once you're running multiple worktrees off one repo (see /gitready). If your worktree setup always keeps main checked out right here, /landtomain and /ship behave identically; pick whichever name matches your muscle memory.

--pr-only: stop cleanly after phase 4 (PR open, nothing merged) and say so. Use it when the PR should sit for review. Everything after phase 4 is skipped, including phase 7.

Work the phases in order. Stop and ask if any phase fails or surfaces something unexpected — a merge to main and the delete that follows are hard to walk back.

Authoritative facts (verify, don't assume)

  • Remote: origin → your GitHub repo. Confirm with git remote -v.
  • Base branch: main. Main checkout: discover it, don't hardcode. Two shapes are common:
    • Linked worktrees off one shared repo (what /gitready sets up): main stays checked out in one worktree — usually the original clone — while every task gets its own linked worktree on a feature branch. git checkout main from a linked worktree fails ("already used by worktree at …") because git refuses to have the same branch checked out twice. Find the worktree with main checked out via git worktree list --porcelain (the entry whose branch line reads refs/heads/main) and run anything that touches local main as git -C "$MAIN_WT" ….
    • A single checkout, branch-switching in place: there is no separate main worktree — git checkout main works directly. The commands below handle both; the worktree-list lookup simply comes back empty and you fall back to a plain checkout.
  • CLI: use gh for all GitHub operations. Never hand-craft API calls.
  • Branch naming: feature branches follow your convention (e.g. <username>/<slug>); agent branches may be codex/<slug> or claude/<slug>. Use whatever branch is checked out — never rename it.
  • Merge style: a merge commit — gh pr merge <n> --merge. Not squash, not rebase, so the PR title becomes the merge subject. Write the title as the real change summary. (Use squash/rebase instead if that's your repo's convention — just be consistent with your last few merges.)
  • Worktree gitignored artifacts: env files, dependency caches, and other seeded-but-ignored local state never appear in git status, are never force-added, and are never "lost work" — they're reproducible.
  • What deleting a worktree actually loses: only things that exist solely in this working tree and aren't on main — uncommitted changes, untracked non-ignored files (e.g. a new z_tickets/** file), and unmerged local commits. Stashes live in the shared .git and survive the delete, but still report them.

Read the full file on GitHub · 205 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 205 lines · 134 tokens per session scan A c7a6b8aba352

Subscribe to this mod's changes

ship is a skill published in the GitHub repository TweekFawkes/prompts (2 stars, last pushed 1mo ago), licensed Unlicense. It adds 134 tokens to every session and 3,362 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.