ship

A release-preparation workflow for work that is ready to move toward review or merging.

In plain words
What is it for?
Preparing pull-request descriptions, changelogs, version bumps, merge checklists, and post-merge verification steps. It produces written guidance rather than running release commands.
Why use it?
It helps turn completed code into a verifiable handoff by classifying the change and preparing release documentation and checks.

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

Made for: Claude Code, Codex.

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,127 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 $0.00119 $0.01127
Opus 5 $0.00060 $0.00563
Sonnet 5 $0.00024 $0.00225
Haiku 4.5 $0.00012 $0.00113

Measured 2d ago against content hash f12d40be8c6f, 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 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.

skills/ship/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

!../principles/SKILL_BODY.md

!../tool-gitnexus/SKILL_BODY.md


Ship / Release Preparation Workflow

Core Principle

Code is not done when it compiles — it is done when it is safely merged, documented, and verifiable by the next person who touches it. This skill bridges the gap between "implementation complete" and "PR merged."

Scope: This skill produces Markdown output only. It does not run CI commands, open browsers, push branches, or execute git commands on your behalf. Human-in-the-loop actions are listed as explicit checklist items.

Distinct from sextant:review-code: Review evaluates code quality before merging. Ship prepares the logistics — changelog, PR description, version bump, and post-merge verification — for code that has already passed review.


Complete Execution Workflow

Step 1: Assess Change Scope

Read the diff and classify the changes:

Change classification:

  • bug fix — corrects broken behavior, no new functionality
  • feature — adds new user-visible capability
  • refactor — restructures internals without behavior change
  • chore — dependency updates, build config, tooling
  • breaking change — removes or incompatibly changes a public interface
─── Change Scope Assessment ─────────────────────────
Classification:           <bug fix / feature / refactor / chore / breaking change>
Files changed:            <count> files, ~<count> insertions, ~<count> deletions
Public interface changes: Yes (list) / No
Breaking changes:         Yes (list affected callers) / No
New dependencies:         Yes (list) / No
─────────────────────────────────────────────────────

Step 2: Pre-Ship Checklist

Work through this checklist before generating the PR description. Items marked ❌ must be resolved before shipping; items marked ⚠️ should be resolved or explicitly accepted as known gaps.

─── Pre-Ship Checklist ──────────────────────────────
[ ] CHANGELOG entry written (or N/A for internal-only change)
[ ] Version bumped if this is a releasable unit
[ ] Breaking changes annotated with @deprecated or migration notes
[ ] No debug-only code left in (console.log, print, TODO: remove)
[ ] Public interface documentation updated (docstrings, README, OpenAPI spec)
[ ] Tests cover new behavior (link sextant:write-tests if coverage is missing)
[ ] No hardcoded credentials, tokens, or environment-specific values
[ ] No accidental file inclusions (build artifacts, .env files, IDE configs)
─────────────────────────────────────────────────────

Read the full file on GitHub · 127 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. 2d ago First seen · 127 lines · 119 tokens per session scan A f12d40be8c6f

Subscribe to this mod's changes

ship is a skill published in the GitHub repository hellotern/Sextant (15 stars, last pushed 4mo ago), licensed MIT. It adds 119 tokens to every session and 1,127 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 2026-08-30.

Related

Other skills, from other repositories

forge-deliver

端到端交付纯编排层:调用 forge- 子 skill 从需求一路编排到发布和文档,.deliver/state.json 检查点,支持 --auto / --resume。 触发方式:用户说"forge-deliver"、"端到端交付"、"全自动交付"。.

yike-gunshi/forge-skills · 73 tokens

forge-ship

发布上线:PR only(建 PR 即停)或 Full ship(合并 PR + 同步本地基础分支);测试失败不发布、不 force push,状态汇报严格区分提交/推送/合并/部署。 触发方式:用户说"ship"、"发布"、"合并上线"、"发 PR"。.

yike-gunshi/forge-skills · 80 tokens

forge-doc-release

发布后文档更新。读取所有项目文档,与 diff 交叉对照, 更新 README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md 使之匹配已发布内容, 润色 CHANGELOG 语气,清理 TODOS,可选地更新 VERSION。 触发方式:用户说"更新文档"、"文档同步"、"forge-doc-release",或 forge-ship 之后、PR 合并之前由 forge-dev --full 调度。.

yike-gunshi/forge-skills · 108 tokens

bump-version

Automate version bumping following semantic versioning and changelog management. Use when the user wants to bump a version, create a release, update the changelog, or tag a new version in a project using semver conventions and Keep a Changelog format.

jim60105/copilot-prompt · 56 tokens

git-workflow-and-versioning

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…

addyosmani/agent-skills · 74 tokens

release

Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.

openai/symphony · 42 tokens