ship

ship is a skill for Claude Code from dryvist/claude-code-plugins. It costs 30 tokens per session (2,962 once invoked), scanned A, original, Apache-2.0.

An automation command that commits changes, pushes them to GitHub, creates pull requests, and finishes the required follow-up checks.

In plain words
What is it for?
Use it to publish one or more sets of changes through Git, create pull requests, and finalize them.
Why use it?
It removes repetitive release steps and handles the common path from local changes to a completed pull request.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Part of the github-workflows plugin — 16 skills shipped together

Good fit Use it to publish one or more sets of changes through Git, create pull requests, and finalize them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dryvist/claude-code-plugins/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 dryvist/claude-code-plugins --skill ship
Clone the repo
git clone --depth 1 https://github.com/dryvist/claude-code-plugins

Made for: Claude Code.

Or install github-workflows, the plugin that ships this one along with the rest of its 16 skills.

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/dryvist/claude-code-plugins/ship.svg)](https://agentmods.dev/skills/dryvist/claude-code-plugins/ship)
Your own site
<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/ship"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/ship.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,962 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 $0.00030 $0.02962
Opus 5 $0.00015 $0.01481
Sonnet 5 $0.00006 $0.00592
Haiku 4.5 $0.00003 $0.00296

Measured 3d ago against content hash 0bebfe57334e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 3d 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.

github-workflows/skills/ship/SKILL.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship

Single command to commit, push, create PR(s), and auto-finalize everything. Handles commit, push, PR creation, and /finalize-pr in one pipeline.

NOT RESUMABLE — run from Step 0 on every /ship invocation. Do not refer to "the PR I just finalized" or "already verified" from any earlier message in this session — those are stale snapshots. The world changes between invocations: CodeQL completes async, required reviewers post async, Renovate force-pushes, branch protection re-evaluates. Re-run everything from Step 0.

Rate Limit Awareness

This skill orchestrates many downstream API calls via /finalize-pr, which itself invokes /resolve-codeql, /resolve-pr-threads, /simplify, and metadata updates. To avoid API rate limit errors:

  • Process PRs sequentially — never dispatch parallel subagents for multiple PRs
  • Allow /finalize-pr to manage its own internal concurrency — it can run its fixes in parallel since they're scoped to a single PR
  • Pause after PR creationsleep 2 after gh pr create to let GitHub index

Step 0: Verify Working Directory

Before anything else, confirm the working directory is valid:

git rev-parse --git-dir 2>/dev/null

If this fails (exits non-zero or the current directory doesn't exist), stop immediately and report: "Working directory is not a git repository. This usually means the worktree was cleaned up after a PR merge. Start a new session and create a worktree using /superpowers:using-git-worktrees to continue working."

Do NOT attempt to recover, cd elsewhere, or fall through to Step 1.

Step 1: Detect Scope

Identify all PRs that need finalization.

1.1 Check for Uncommitted Changes

git status --porcelain

If changes exist (staged or unstaged), execute inline:

  1. Claim check (session-coordination rule): before creating a new PR, search for a competing claim — an open PR (draft or ready) from another session covering the same issue or files:

Read the full file on GitHub · 280 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. 3d ago First seen · 280 lines · 30 tokens per session scan A 0bebfe57334e

Subscribe to this mod's changes

ship is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 2,962 once invoked, about $0.0002 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 2026-09-04.