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.
npx agentmods add skills/juanmhidalgo/claude-plugins/shipnpx skills add juanmhidalgo/claude-plugins --skill shipgit clone --depth 1 https://github.com/juanmhidalgo/claude-pluginsWrote 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/juanmhidalgo/claude-plugins/ship)<a href="https://agentmods.dev/skills/juanmhidalgo/claude-plugins/ship"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/ship.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00036 | $0.02727 |
| Opus 5 | $0.00018 | $0.01363 |
| Sonnet 5 | $0.00007 | $0.00545 |
| Haiku 4.5 | $0.00004 | $0.00273 |
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship Workflow
Execute these phases in order. Stop and report at any failure.
Context
- Branch: !
git branch --show-current - Remote tracking: !
git rev-parse --abbrev-ref @{upstream} 2>/dev/null || echo "no upstream" - Uncommitted changes: !
git status --short | head -20 - Arguments: $ARGUMENTS
Phase 1: Status & Branch Detection
- Run
git status(never use-uall) - Run
git diff --statfor unstaged changes summary - Run
git diff --cached --statfor already-staged changes - Detect the repo's default branch:
gh repo view --json defaultBranchRef -q .defaultBranchRef.name 2>/dev/null || echo "main" - Detect branch type:
- Default branch (main, master, prod, or whatever the repo uses) → ask about branching (see below)
- Feature branch: anything else → PR workflow
If there are no changes (working tree clean, nothing staged), stop and inform the user.
If on the default branch, ask user with AskUserQuestion:
- "Create a new feature branch" — auto-generate a descriptive branch name from the changes (e.g.,
fix/null-check-auth-middleware,feat/add-billing-export). Use the conventional commit type as prefix. Create withgit checkout -b <name>. - "Continue on current branch" — proceed with direct push workflow
If the user creates a new branch, the rest of the workflow follows the feature branch path (PR offered at the end).
Phase 2: Smart Staging
If there are unstaged changes:
-
List all changed and untracked files
-
Exclude secrets automatically: skip
.env, credentials, tokens, private keys — warn the user about excluded files -
Analyze change cohesion — determine if all changes relate to a single concern or multiple:
Signals for mixed/unrelated changes:
- Files in different modules or directories with no logical connection
- Mix of change types (e.g., a bug fix in existing code + new feature files)
- Changes that touch different domains (e.g., auth code + billing logic)
- Diff content showing unrelated modifications (e.g., a typo fix + a refactor)
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.
- 2d ago First seen · 245 lines · 36 tokens per session scan A 67d75fe596ca
ship is a skill published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 11d ago), licensed MIT. It adds 36 tokens to every session and 2,727 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 2026-09-03.
Other skills, from other repositories
git-workflow
Use when naming or scoping a branch, writing or fixing a commit message, picking the gitmoji for a commit, untangling history (rebase versus merge versus squash), or cutting a versioned release — the portable git-convention layer for any repo. Covers gitmoji + Conventional Commits, SemVer tags, branch hygiene…
git-flow-pr
Executes the full PR-driven development workflow: create an isolated feature branch from the current work, commit all staged changes, rebase cleanly onto the selected base branch (skipping any ancestor commits already merged), push the branch, and open a GitHub pull request linked to a related issue. Includes guidance…
semantic-release-convention-skill
Source of truth for commit-to-PR-to-merge-to-release conventions — semver labels, branch-aware tagging, changelogs, release pipelines.
git-ship
自动化 Git 工作流一键发布助手,执行完整的「ship」流程: 基于最新 main 切新分支 → commit → 推送 → 创建 PR → squash merge → 回 main。 调用 ship 本身就是对完整流程的授权;自动推断分支名、commit message 和 PR 内容, 并主动解决 Git 冲突、测试、lint、类型检查、构建和 CI 失败,持续修复和重试, 直到改动成功合并。不要因可自行修复的失败暂停,只在认证、权限、仓库保护等 无法由当前环境解决的外部阻塞出现时请求用户介入。 仅在用户明确表达「ship」意图时触发,例如: 直接说「ship」「/ship」「git ship」 明确要求完整走完 git…
jig-conformance-audit
Use to check whether a repository's history actually followed the jig procedure: conventional squash subjects, Release-Grade trailers on unreleased work, version tag format and placement, the main/develop fast-forward invariant, and a committed rubric. Read-only, exits non-zero on violations, and runs in CI.
mk:ship
Ship workflow with explicit scopes: prepare stages and commits locally; release pushes and creates a PR; publish manages issues and versioning. Use when asked to "ship", "deploy", "push to main", "create a PR", or "merge and push". Proactively suggest when the user says code is ready or asks about deploying. Supports…