Borrowing it
Nothing to install: this file belongs to bezhai/chiwei-platform. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bezhai/chiwei-platform/main/.claude/skills/ship/SKILL.mdgit clone --depth 1 https://github.com/bezhai/chiwei-platformWrote 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.
[](https://agentmods.dev/skills/bezhai/chiwei-platform/ship)<a href="https://agentmods.dev/skills/bezhai/chiwei-platform/ship"><img src="https://agentmods.dev/badge/skills/bezhai/chiwei-platform/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.
<a href="https://agentmods.dev/skills/bezhai/chiwei-platform/ship"><img src="https://agentmods.dev/badge/skills/bezhai/chiwei-platform/ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00015 | $0.00978 |
| Opus 5.5 | $0.00006 | $0.00391 |
| Sonnet 5.5 | $0.00003 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
ship scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/ship
一键完成:PR → 合码 → 部署生产。用户敲 /ship 即表示授权合并和部署。
合码规则(等用户确认、列出所有改动、冲突展示)以 CLAUDE.md「开发与上线」一节为准,本文件只描述执行流程。
参数
!`echo "$ARGUMENTS"`
可选传入 APP。不传则自动检测。
执行流程
1. 自动检测
- APP: 从参数获取,或从
git diff --name-only main...HEAD检测。涉及多个 app 且未指定时才问。如果只改了根目录文件(Makefile、CLAUDE.md 等),标记为"仅合码,无需部署"。 - 分支:
git branch --show-current,禁止在 main 上执行。
2. 检查是否有不属于当前工作的改动
对比分支上的全部改动文件(git diff --name-only main...HEAD)和当前对话中实际修改过的文件。如果发现有不是当前对话改动的文件(如之前遗留的 commit),必须提醒用户:
分支上还有以下不属于本次改动的文件:xxx,是否一起合入?
等用户确认后再继续。如果所有改动都是当前对话的工作范围内,直接继续。
3. 自动处理脏状态
不要问,直接做:
# 有未提交改动 → 自动 commit
git add -A && git commit -m "wip: auto commit before ship"
# 未推送 → 自动 push
git push -u origin <branch>
4. 创建 PR 并合码
# 创建 PR(已存在则跳过)
ghc pr create --fill 2>/dev/null || true
# 合码(不带 --delete-branch,避免 worktree 下切 main 失败)
ghc pr merge --squash
# 删除远端分支(合码成功后)
git push origin --delete <branch>
禁止使用 --delete-branch:在 worktree 中该参数会尝试本地切换到 main,导致 致命错误:'main' 已经检出到 ...。PR 实际已合并但命令报错,模型会误以为失败而重试。
合并冲突处理:遇到冲突时,展示冲突文件和冲突内容,等用户指示如何解决。解决后重新 push 并重试。不要自行选择保留哪个版本。
5. 部署
如果标记为"无需部署",跳到步骤 6。
必须在主仓库的 main 分支执行部署。通过 git worktree list 找到主仓库路径(bare 或 main worktree)。
cd <主仓库路径>
git checkout main && git pull
根据 APP 类型:
paas-engine:make self-deploy GIT_REF=main- 其他:
make deploy APP=<APP> GIT_REF=main
超时 10 分钟。
一镜像多服务自动同步:make deploy / make release 会按 Makefile 的 SIBLINGS 映射自动同步 release sibling 服务(channel-server → chat-response-worker,lark-service → lark-outbound),无需手动操作。agent-service 已无 sibling(vectorize-worker 随 v4 记忆整机删除)。
6. 清理当前分支的测试泳道
只清理当前分支对应的泳道(与 deploy-test 相同的推导:ppe- + 分支名小写、/ → -、截前 16 字符;或显式传入的 LANE),不要动其他泳道。
make undeploy APP=<APP> LANE=<当前分支对应的泳道名>
执行 /ops unbind bot dev 解绑 dev bot。
如果该泳道不存在则跳过,不报错。
7. 验证并输出
执行 /ops pods <APP> 确认 pod Running。
一行总结:✅ <APP> 已部署到生产环境,镜像: <version>
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.
- 1mo ago Changed 2a4228b1b219
- 2mo ago First seen · 101 lines · 15 tokens per session scan A e2e0eb89c935
ship is a skill published in the GitHub repository bezhai/chiwei-platform (22 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 978 once invoked, about $0.0001 per session on Opus 5.5. 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.
ship compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| shipbezhai/chiwei-platform | Skill | 22 | 2d ago | MIT | A | 15 | Claude Code |
| land-and-deploygarrytan/gstack | Skill | 140k | yesterday | MIT | A | 14 | Claude Code |
| publish-siteNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 19 | Claude Code, Codex |
| release-publishrohitg00/ai-engineering-from-scratch | Skill | 77k | yesterday | MIT | A | 9 | Claude Code, Codex |
| release-reviewrohitg00/ai-engineering-from-scratch | Skill | 77k | yesterday | MIT | A | 7 | Claude Code, Codex |
| orchard-releaserohitg00/ai-engineering-from-scratch | Skill | 77k | yesterday | MIT | A | 11 | Claude Code, Codex |
| orchard-reviewrohitg00/ai-engineering-from-scratch | Skill | 77k | yesterday | MIT | A | 8 | Claude Code, Codex |