ship-it

ship-it is a skill for Claude Code from adamlinscott/claude-skills. It costs 134 tokens per session (1,910 once invoked), scanned A, original, MIT.

A release workflow for taking completed code from the current branch through review, merging, deployment, and production, where applicable. It checks the repository's actual branches, pull requests, environments, and delivery process first.

In plain words
What is it for?
Use it to finish a change across the repository's defined environments, verify the deployed commit, and report what was merged, released, and running.
Why use it?
It helps prevent stopping after a merge or assuming that a successful deployment means the intended code is running. It also checks what other unreleased changes might be included.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the claude-skills plugin — 18 skills shipped together

Good fit Use it to finish a change across the repository's defined environments, verify the deployed commit, and report what was merged, released, and running.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adamlinscott/claude-skills/ship-it
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 adamlinscott/claude-skills --skill ship-it
Clone the repo
git clone --depth 1 https://github.com/adamlinscott/claude-skills

Made for: Claude Code.

Or install claude-skills, the plugin that ships this one along with the rest of its 18 skills.

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.

agentmods badge for ship-it

README.md
[![agentmods](https://agentmods.dev/badge/skills/adamlinscott/claude-skills/ship-it/github.svg)](https://agentmods.dev/skills/adamlinscott/claude-skills/ship-it)
Your own site
<a href="https://agentmods.dev/skills/adamlinscott/claude-skills/ship-it"><img src="https://agentmods.dev/badge/skills/adamlinscott/claude-skills/ship-it/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.

agentmods 80×15 button for ship-it

Your own site · 80×15
<a href="https://agentmods.dev/skills/adamlinscott/claude-skills/ship-it"><img src="https://agentmods.dev/badge/skills/adamlinscott/claude-skills/ship-it.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,910 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00134 $0.01910
Opus 5 $0.00067 $0.00955
Sonnet 5 $0.00027 $0.00382
Haiku 4.5 $0.00013 $0.00191

Measured 9d ago against content hash d86e9eb9f511, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ship-it 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 9d 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-it/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship It

The work of this conversation is finished, or the user thinks it is. Your job is to get it all the way out — merged, released, and running in every environment this repo deploys to, production included — and to prove it got there rather than assume it did.

Two failure modes to hold in mind. The first is stopping early: a merged PR is not a shipped change, and a green deploy job is not proof the environment is running your commit. The second is shipping more than the user knows about: on most repos a release carries everything sitting unreleased on the target branch, which can include work by other people and other agent sessions. Section 4 exists entirely for that.

1. Ground yourself before doing anything

Take no action until you can name, from evidence, all four of these. Read; do not recall.

The work. What this session actually produced — the branches you created or committed to, and the commits on them. If the session is long or compacted and you cannot reconstruct it confidently, do not guess: check git log --author for the configured user, recent branches (git branch --sort=-committerdate), and the current branch, and state which of it you are treating as "the work" so the user can correct you.

The PRs. For each branch: is there a PR, is it open, merged, or closed-unmerged? A branch whose PR was closed without merging is a trap — the work looks done and is not. gh pr list --state all --head <branch> and gh pr view settle it.

The environments. What this repo actually deploys, and where. Do not assume a shape. Read the CI/CD definitions: .github/workflows/*, gh api repos/{owner}/{repo}/environments, plus whatever config is present — vercel.json, fly.toml, Procfile, Dockerfile, .circleci/, charts/, terraform/. Work out from those files what triggers each deploy: a push to a branch, a tag or release, a manual workflow_dispatch, or an external system Claude cannot reach at all.

The route. The ordered path from the branch to production — for example branch → PR → main → auto-deploy staging → tag → production. Name the base branch from the repo, not from habit.

Read the full file on GitHub · 145 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. 9d ago First seen · 145 lines · 134 tokens per session scan A d86e9eb9f511

Subscribe to this mod's changes

ship-it is a skill published in the GitHub repository adamlinscott/claude-skills (3 stars, last pushed 9d ago), licensed MIT. It adds 134 tokens to every session and 1,910 once invoked, about $0.0007 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.