A release workflow for Git projects that either opens a pull request or merges it and synchronizes the local base branch. It distinguishes submitted, pushed, merged, and deployed states.

Use it to create or update pull requests, merge approved changes, synchronize a local main branch, and report exactly what has happened.

It prevents code from being described as live when it was only committed or pushed, and stops releases when tests fail. It also avoids force-pushing.

forge-ship — Skill for Claude Code by yike-gunshi

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 yike-gunshi/forge-skills --skill forge-ship

Clone the repo

git clone --depth 1 https://github.com/yike-gunshi/forge-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-ship/github.svg)](https://agentmods.dev/skills/yike-gunshi/forge-skills/forge-ship)

Your own site

<a href="https://agentmods.dev/skills/yike-gunshi/forge-skills/forge-ship"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yike-gunshi/forge-skills/forge-ship"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,832 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.

Model	Per session	Once invoked
Fable 5.1	$0.00080	$0.02832
Opus 5	$0.00040	$0.01416
Sonnet 5	$0.00016	$0.00566
Haiku 4.5	$0.00008	$0.00283

Measured 11d ago against content hash 07b7d3295912, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

forge-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 11d 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/forge-ship/SKILL.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

文档落地路径：遵循 forge-doc-policy 规范。完整白名单 + frontmatter schema 见 ~/.claude/skills/forge-doc-policy/doc-paths.md。 当前文档加载顺序：涉及文档更新时，先读项目 CLAUDE.md、docs/README.md、 docs/INDEX.md 和相关根级当前真相源；archive/raw 只作历史证据。详细规则见 ~/.claude/skills/_shared/current-doc-loading.md。

/forge-ship：发布上线

核心原则

ship 不是“创建 PR 就结束”。它有两个模式：

PR only：提交、推送、创建或更新 PR，然后停止。
Full ship：提交、推送、创建或更新 PR，检查 PR 状态，合并 PR 到远程基础分支，再把本地基础分支 worktree 同步到 origin/<基础分支>。

当用户明确说“ship / 发布 / 合并 / 通过 PR / 更新远程和本地 main”时，默认使用 Full ship。当用户只说“创建 PR / 提交 PR / 先发 PR”时，使用 PR only。

永远区分这些状态：代码已提交、分支已推送、PR 已创建、PR 已合并、远程 main 已更新、本地 main 已同步、ECS 已部署。除非真的执行部署并验证运行态，否则不要说线上已更新。

前置脚本

每次先运行：

_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
echo "当前分支: $_BRANCH"
git status --short
git remote -v

如果当前分支就是基础分支（通常是 main），不要直接 ship。先询问用户是要：

A) 新建功能分支再 ship（推荐）
B) 只同步本地 main
C) 停止

提问格式与批量策略见 ~/.claude/skills/_shared/interaction-protocol.md。

第0步：确定 Ship 模式和基础分支

先根据用户措辞判断模式（PR only / Full ship），不确定时询问。

确定基础分支：

gh pr view --json baseRefName -q .baseRefName 2>/dev/null                   # 1. 已有 PR 则读 PR base
gh repo view --json defaultBranchRef -q .defaultBranchRef.name 2>/dev/null  # 2. 否则读仓库默认分支；都失败回退 main

记录：当前分支、基础分支、ship 模式、当前 HEAD、origin/<基础分支> HEAD。

第0.5步：生产写面授权门

账本"权限.生产操作点名授权清单"复发 5 次后的固化（2026-07-17）。

开工前枚举本轮全部仓库外写面。判断标准：动作对象不在本仓库工作区内，就是写面。常见：

self-PR merge / 删远程分支
部署（ssh / scp / 重启服务 / 改服务器 .env）
数据库写（迁移、pg_cron、生产数据修改）
第三方账号写（X List、飞书、发布平台）

把清单一次性列给用户请求点名授权，不要逐次撞权限门。同时给出用户可预置进 .claude/settings.local.json 的 allow 规则（如 Bash(ssh root@HOST *)、Bash(./scripts/deploy.sh*)），并说明：AI 代改 settings 会被反自授权设计拦截，这几条只能用户亲手加。

本轮没有仓库外写面就记录"无写面"跳过。中途被拦时按账本"被拦即换路勿重试"处理，禁止原样重试同一命令。

第1步：安全检查

检查当前 worktree：

git status --short --branch
git fetch origin <基础分支> --quiet
git diff origin/<基础分支> --stat
git log origin/<基础分支>..HEAD --oneline

如果有未提交更改，询问：

A) 将本次相关更改加入暂存区并提交（推荐）
B) 交互式选择文件
C) 停下来，让我处理

Read the full file on GitHub · 287 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/merge-and-sync.md 3.6 KB

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.

11d ago First seen · 287 lines · 80 tokens per session scan A 07b7d3295912

Subscribe to this mod's changes

forge-ship is a skill published in the GitHub repository yike-gunshi/forge-skills (13 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 2,832 once invoked, about $0.0004 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 2026-08-30.

Claude Code Git and workflow Releases agent-skills ai-development forge skill-md skillsmp

swarm-migrate

Cross-repo migration swarm — one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger. Coordinator handles topology, conflict auto-rebase, and stop-on-novel-failure. Use when bumping a shared dependency, rolling out…

yonatangross/orchestkit · 103 tokens

release-management

Automates GitHub releases with semantic versioning, changelog generation from merged PRs, and gh CLI integration. Supports draft, prerelease, and standard release workflows with task-tracked multi-phase execution. Use when creating releases, tagging versions, or publishing changelogs.

yonatangross/orchestkit · 58 tokens

release-sync

Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.

yonatangross/orchestkit · 62 tokens

forge-ship