ship

ship is a skill for Claude Code, Codex from cubha/claude-workflow-plugins. It costs 113 tokens per session (2,865 once invoked), scanned A, original, MIT.

An automated release workflow that commits current changes, pushes them, opens and merges a pull request, and cleans up the branch. A pull request is a proposed code change for review; the workflow adapts to repositories using either a develop branch or direct feature-to-main merging.

In plain words
What is it for?
Use it when a finished change needs to be committed, reviewed, merged into the appropriate branch, and tidied afterward.
Why use it?
It turns several release steps into one guided process and includes checks for features, security, databases, and sensitive files before merging.

Skill for Claude CodeCodex

Part of the ship plugin — 1 skill, 2 agents shipped together

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.

agentmods
npx agentmods add skills/cubha/claude-workflow-plugins/ship
Any agent
npx skills add cubha/claude-workflow-plugins --skill ship
Clone the repo
git clone --depth 1 https://github.com/cubha/claude-workflow-plugins

Made for: Claude Code, Codex.

Or install ship, the plugin that ships this one along with the rest of its 1 skill, 2 agents.

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/cubha/claude-workflow-plugins/ship.svg)](https://agentmods.dev/skills/cubha/claude-workflow-plugins/ship)
Your own site
<a href="https://agentmods.dev/skills/cubha/claude-workflow-plugins/ship"><img src="https://agentmods.dev/badge/skills/cubha/claude-workflow-plugins/ship.svg" alt="Measured on agentmods" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,865 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00113 $0.02865
Opus 5 $0.00056 $0.01432
Sonnet 5 $0.00023 $0.00573
Haiku 4.5 $0.00011 $0.00286

Measured 3d ago against content hash 9875958f0a2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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.

plugins/ship/skills/ship/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship 파이프라인 (Commit → Push → PR → Merge)

$ARGUMENTS 를 파싱해 모드를 결정하고 전체 파이프라인을 실행한다.

브랜치 전략 자동 적응: 리포지토리에 develop 브랜치가 있으면 git-flow(feature → develop → main)로, 없으면 GitHub Flow(feature → main)로 자동 동작한다. 별도 설정 없이 현재 리포의 브랜치 구조를 감지해 맞춘다.


파이프라인 구성

[파이프라인 A]  --dev  : feature/* → develop
[파이프라인 B]  --main : develop   → main

[GitHub Flow]   develop 브랜치 없음 → feature/* → main

[체인 모드]     --main + feature/* + 미push 변경사항
                = 파이프라인 A 자동 실행 → 완료 후 파이프라인 B 자동 실행

Step 0 — $ARGUMENTS 파싱

$ARGUMENTS에서 아래 항목을 순서대로 추출한다:

항목 추출 대상 기본값
타겟 플래그 --dev 또는 --main 없음 (브랜치로 자동 결정)
머지 방식 --merge 또는 --rebase squash
커밋 메시지 플래그 제외 나머지 문자열 변경사항 분석해 자동 생성

두 타겟 플래그 동시 입력 시 → 즉시 중단: "플래그는 --dev 또는 --main 중 하나만 사용 가능합니다."


Step 1 — 사전 확인 및 모드 결정

1-1. 기본 정보 수집

git branch --show-current          # 현재 브랜치
git status --short                 # 변경사항 여부
git remote get-url origin          # owner/repo 파싱
git ls-remote --heads origin develop  # develop 브랜치 존재 여부

origin 미설정 시 → 즉시 중단: "git remote add origin 후 재시도하세요."

1-2. 모드 결정 분기

develop 브랜치 없음?
  └─▶ GitHub Flow MODE (Step 2L)

develop 브랜치 있음?
  ├─ 현재: main/master → 즉시 중단
  ├─ 현재: develop + --dev 플래그 → 즉시 중단
  │        ("develop에서 --dev 불가. feature 브랜치에서 사용하세요.")
  │
  ├─ 현재: develop + (--main | 플래그 없음)
  │   └─▶ PIPELINE B (Step 2B)
  │
  └─ 현재: feature/*
      ├─ --dev 또는 플래그 없음
      │   └─▶ PIPELINE A (Step 2A)
      │
      └─ --main
          ├─ 변경사항 없음 → checkout develop → PIPELINE B (Step 2B)
          └─ 변경사항 있음 → CHAIN MODE (Step 2A → Step 2B 자동 연결)

변경사항 없고 현재 브랜치 = develop이며 develop == main 이면 → 즉시 중단: "develop이 이미 main과 동일합니다."

1-3. 기능·보안·DB 사전검토

커밋 직전 기능 검증 게이트를 통과시킨 뒤 경량 보안/DB 검토를 수행한다.

1-3-0. 기능 검증 게이트 (verify.sh — 항상 우선 실행)

커밋·머지 전에 코드가 정적+단위 게이트를 통과하는지 확인한다. --no-verify 금지(아래 정책)의 상위 보증.

[ -f verify.sh ] && bash verify.sh --full
  • --full: 커밋 전 시점이라 git diff 스코프가 좁을 수 있으므로 전체 검사로 vacuous-pass(아무것도 검사 안 하고 통과)를 방지한다.
  • verify.sh 부재 시 → 조용히 통과시키지 않는다. 프로젝트에 통합 검증 스크립트가 없다는 뜻이므로:
    1. 프로젝트에 관례적 검증 명령이 있으면(package.jsontest/build/lint, Makefiletest 등) 그걸 실행한다.
    2. 그것도 없으면 REPORT 상단에 "⚠️ 기능 게이트 없음 — 미검증 코드 ship" 경고를 크게 표시하고, 네이티브 /verify(앱 실행·동작 확인)·/security-review(변경 diff 보안 검토)로 최소 확인을 권한다.
    3. 사용자가 명시적으로 진행을 승인하지 않는 한, 완전 미검증 상태로 protected 브랜치 머지까지 자동 진행하지 않는다.
  • FAIL → 즉시 중단, 사용자에게 실패 항목 보고. tsc/lint/build/단위테스트 미통과 코드는 ship하지 않는다.
  • 이미 구현·리팩토링 파이프라인을 거쳐 통과 상태라면 빠르게 재확인되어 통과한다 — /ship 직접 진입 시의 최소 기능 안전망.

Read the full file on GitHub · 276 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 · 276 lines · 113 tokens per session scan A 9875958f0a2e

Subscribe to this mod's changes

ship is a skill published in the GitHub repository cubha/claude-workflow-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 2,865 once invoked, about $0.0006 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.