vegastack-cli: Skill for Claude Code

.claude/skills/ship/SKILL.md

ship is a skill for Claude Code from vegastack/vegastack-cli. It costs 299 tokens per session (4,267 once invoked), scanned A, original, MIT.

An internal release workflow for the @vegastack/cli npm package, covering checks, documentation review, version updates, changelog work, and tagged release preparation.

In plain words
What is it for?
Use it only in the vegastack-cli repository to test the CLI and related apps, update package versions, prepare a changelog, and push the release tag that triggers publishing.
Why use it?
It keeps versions aligned across the repository and ensures the correct GitHub Packages publishing process is followed.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions .claude-plugin; mentions Claude Code.

This is vegastack/vegastack-cli's own configuration. It tells Claude Code how to work on vegastack-cli 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 vegastack-cli configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/mk/projects/vegastack-cli.

Part of the vegastack-cli plugin — 3 skills, 1 hook, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to vegastack/vegastack-cli. 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/vegastack/vegastack-cli/main/.claude/skills/ship/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vegastack/vegastack-cli

Made for: Claude Code.

Or install vegastack-cli, the plugin that ships this one along with the rest of its 3 skills, 1 hook, 1 MCP server.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/vegastack/vegastack-cli/ship"><img src="https://agentmods.dev/badge/skills/vegastack/vegastack-cli/ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 299 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,267 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 $0.00299 $0.04267
Opus 5.5 $0.00120 $0.01707
Sonnet 5.5 $0.00060 $0.00853
Haiku 4.5 $0.00030 $0.00427

Measured 1mo ago against content hash 579ae6d58836, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

.claude/skills/ship/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship Workflow — @vegastack/cli internal release

Full release cycle for v0.1 internal GitHub Packages publishing: pre-flight tests across all 3 codebases, diff + doc audit, version bump synced across package.json × 3, changelog entry, commit + tag push, post-ship verification.

The actual npm publish is performed by .github/workflows/publish-internal.yml when it sees the v* tag — this skill prepares the release locally and then triggers the workflow by pushing the tag. Do not invoke gh workflow run publish-internal.yml — the tag push is the only correct trigger. Calling the workflow manually risks publishing without a corresponding git tag, which breaks the version-tag-matches-package-version check.

Project context this skill encodes

  • 3 codebases under one repo, all version-synced: package.json (CLI, 398 tests), apps/mcp/package.json (Cloudflare Workers MCP server, 19 tests), apps/dashboard/package.json (Astro Cloudflare Workers eval dashboard, 9 tests). All three carry the same version even though only the CLI publishes via this skill — keeping them aligned makes "what version is this code?" answerable from any package.json.
  • Bundle is a separate repo (engg-vegastack-agent-tf-providers). It ships on its own daily cron via build-and-publish.yml. This skill never touches it.
  • App deploys are automatic. Cloudflare Workers Builds watches the repo and redeploys apps/mcp + apps/dashboard on every push to main. This skill never invokes wrangler deploy.
  • The dormant release.yml is the future public-npm path with cosign + SLSA. It auto-trigger on v* is commented out. This skill never modifies or invokes it.
  • prepublishOnly guard at scripts/check-bundle-pin.js refuses to publish if expectedBundleSha is the placeholder. The CI workflow sets VEGASTACK_ALLOW_PENDING_BUNDLE_SHA=1 to bypass for v0.1 internal builds. Never bypass the guard locally — locally the guard's role is to remind you that the bundle SHA is still stub-pinned, which matters when v1.0 ships publicly.

Read the full file on GitHub · 262 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. 1mo ago First seen · 262 lines · 299 tokens per session scan A 579ae6d58836

Subscribe to this mod's changes

ship is a skill published in the GitHub repository vegastack/vegastack-cli (2 stars, last pushed 5mo ago), licensed MIT. It adds 299 tokens to every session and 4,267 once invoked, about $0.0012 per session on Opus 5.5. 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.