ship

A deployment workflow with three stages: checks before release, the deployment itself, and verification afterward, including rollback planning.

In plain words
What is it for?
Use it when asked to ship, release, or deploy software, or when checking whether a deployment succeeded and deciding how to roll it back.
Why use it?
It makes release risks visible and requires approval before actions that change shared or production systems.

Skill for Claude CodeCodex

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/baleen37/bstack/ship
Any agent
npx skills add baleen37/bstack --skill ship
Clone the repo
git clone --depth 1 https://github.com/baleen37/bstack

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,172 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 $0.00060 $0.02172
Opus 5 $0.00030 $0.01086
Sonnet 5 $0.00012 $0.00434
Haiku 4.5 $0.00006 $0.00217

Measured yesterday against content hash 49ede3f288be, 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 yesterday.

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/me/skills/ship/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship

Overview

Deploy safely, observably, reversibly. Every launch goes through three phases: pre-deploy → deploy → post-deploy. Don't skip phases.

Automation Policy

Run safe read-only checks and local reversible work automatically (git/CI status, tests, lint, audits, drafting rollout/rollback plans). Classify each finding AUTO-COMPLETED, NEEDS_APPROVAL, BLOCKED, or READY_FOR_SHIP_REVIEW.

Ask for approval before anything that changes shared or external state: pushes, PR creation/merge, releases, deploys, infra/flag/config/secret/DB changes, external notifications, rollbacks, destructive commands, data migrations.

When to Delegate to Subagents

Fan-out is a tool, not a requirement.

  • Delegate when 2+ independent analyses can run in parallel, a specialist fits (me:security-auditor, me:test-engineer, Explore), or output would pollute main context.
  • Run directly when a single command answers it, the result must be reasoned about immediately, or blast radius is small.

When delegating, batch independent calls in one message so they run in parallel.

Execution Workflow

Three phases: pre-deploy → deploy → post-deploy. Do not skip phases.

First, classify the change:

  • Deployable (touches code/infra that runs in production) → full three-phase flow.
  • Non-deployable (docs, skills, internal scripts, CI config without runtime effect) → run Phase 1 checks (tests/lint relevant to the change), commit/PR per normal flow, skip Phases 2–3. State explicitly: "Non-deployable change, skipping deploy/verify phases."

If unsure, ask the user once. Don't invent a deploy step for a doc change.

Phase 1 — Pre-deploy (배포 전 점검)

  1. Identify scope — launch type, changed files, blast radius, production systems touched.
  2. Read the deploy convention — see "Reading Deploy Convention" below. If the project has none, ask once and offer to record the answer.
  3. Run checks — local verification (tests, lint, type, build), CI/PR status, dependency/security audits, docs. For non-trivial changes consider fanning out per "When to Delegate".
  4. Draft artifacts — rollout stages, rollback triggers/procedure, monitoring targets, owners, post-deploy checks.
  5. Classify and decide — mark each item AUTO-COMPLETED, NEEDS_APPROVAL, BLOCKED, or READY_FOR_SHIP_REVIEW. Stop and report evidence if anything is BLOCKED. Present GO/NO-GO with the rollback plan.

Read the full file on GitHub · 200 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. yesterday First seen · 200 lines · 60 tokens per session scan A 49ede3f288be

Subscribe to this mod's changes

ship is a skill published in the GitHub repository baleen37/bstack (4 stars, last pushed 11d ago), licensed MIT. It adds 60 tokens to every session and 2,172 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens