ai-engineering: Skill for Claude Code

.agents/skills/ai-ship/SKILL.md

ai-ship is a skill for Claude Code from arcasilesgroup/ai-engineering. It costs 122 tokens per session (854 once invoked), scanned A, original, Apache-2.0.

A release procedure for putting a completed change into a shared code repository through commits, a changelog entry, and a pull request—a request for others to review and merge the change.

In plain words
What is it for?
Use it to run the project gate, create appropriately scoped commits, update release notes, document readiness checks, open a pull request, close the related work item, and clean up the branch.
Why use it?
It organizes the final checks and repository cleanup needed before and after a change is merged.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is arcasilesgroup/ai-engineering's own configuration. It tells Claude Code how to work on ai-engineering itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-engineering configures →

Reuse

Borrowing it

Nothing to install: this file belongs to arcasilesgroup/ai-engineering. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/arcasilesgroup/ai-engineering/main/.agents/skills/ai-ship/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/arcasilesgroup/ai-engineering

Made for: Claude Code.

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 ai-ship

README.md
[![agentmods](https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-ship.svg)](https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-ship)
Your own site
<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-ship"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-ship.svg" alt="Measured on agentmods" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 854 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00122 $0.00854
Opus 5 $0.00061 $0.00427
Sonnet 5 $0.00024 $0.00171
Haiku 4.5 $0.00012 $0.00085

Measured 8d ago against content hash f0543ef9bcff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ai-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 8d 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.

.agents/skills/ai-ship/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Land the work

What it produces

Commits, a changelog entry, a pull request on origin/<branch>, and a branch that gets deleted after it merges.

Steps

  1. Run the repository's own gate — the recipe set CI runs, whatever it is called here — and show its output. Not a summary of it — the output. If it is red, stop here; nothing below this line is worth doing.
  2. Commit in the shape the change actually has: one commit, one change. A commit that needs the word "and" in its subject is two commits. Subject is <type>(<scope>): <what changed>, imperative, and the body says why rather than what. Never --no-verify: the hooks are the floor, and what they would have said is the thing that needs fixing.
  3. Update the changelog. A breaking change is written as a breaking change, in the words somebody upgrading would search for.
  4. Tick the production-ready boxes in the spec. Assertion 19 reads what is beside each tick, so a box with no command in backticks and no not applicable fails the gate.
  5. Open the pull request. The first paragraph is what changed, in plain words, for somebody who does not code. Then the spec link, then what to look at first, then what you are not confident about — that last section is the one reviewers use most.
  6. If the spec's frontmatter has a ref, append the closing keyword to the body: Closes owner/repo#45 on GitHub, Fixes #45 on Azure Repos, AB#45 where the Azure Boards app bridges the two. One constraint catches people: the pull request must target the default branch, or the keyword is ignored and nothing is linked or closed.
  7. After it merges, delete the branch, and say in one line what is now true that was not true before.
  8. A conflict is resolved by intent and never by taking a side. Read what each side was trying to do, say it in the merge in one line each, and keep the change that serves both — or stop and ask, because a conflict resolved by whoever pushed last is a decision nobody took. /ai-debug owns finding the cause when the merged result then misbehaves.

Read the full file on GitHub · 63 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 63 lines · 122 tokens per session scan A f0543ef9bcff

Subscribe to this mod's changes

ai-ship is a skill published in the GitHub repository arcasilesgroup/ai-engineering (54 stars, last pushed 7d ago), licensed Apache-2.0. It adds 122 tokens to every session and 854 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

git-workflow

Use this skill for anything related to Git and version control workflows. Trigger when the developer asks for help with commit messages, PR descriptions, pull request reviews, branching strategies, changelog generation, release notes, code review etiquette, or Git conventions. Keywords: commit, PR, pull request…

jamestorrevillas/dev-skills · 78 tokens

github-operations

WORKFLOW SKILL — Full GitHub contribution lifecycle: branches, conventional commits, issues, PRs, Actions, releases. gh CLI-first with MCP fallback. WHEN: "commit", "push", "open PR", "create branch", "create issue", "cut release", "GitHub operation". DO NOT USE FOR: Azure infrastructure, Bicep/Terraform code…

jonathan-vella/apex-accelerator · 101 tokens

git-commit-push-pr

Commit, push, and create a PR. Prompts for branch and PR target using quick multi-choice questions. Lightweight alternative to /workflow-ship without preflight checks.

charlesjones-dev/claude-code-plugins-dev · 43 tokens

brpr

(devtools plugin) Create a branch, commit changes, push, and open a PR — or just commit+push+PR if already on a feature branch. Links related issues from GitHub or Linear based on project tracker config.

feniix/pi-extensions · 49 tokens

plate

Turn finished local work into a commit, an ordinary pull request, or a pull request stack. Use this skill to commit changes or to publish a branch. Use it to open or update a pull request. Use it to create, sync, restack, or submit a pull request stack. You can also run /plate. This skill owns all staging, commits…

paulnsorensen/easy-cheese · 106 tokens

ag-versionar-codigo

Gerencia git - branches, commits semanticos, PRs, releases e changelog. Use ao final de cada fase ou feature para manter historico limpo.

andregusman-raiz/a-gusman-claude · 40 tokens