autoship

autoship is a skill for Claude Code, Codex from OutlineDriven/outline-driven-development. It costs 41 tokens per session (2,036 once invoked), scanned A, original, Apache-2.0.

An automated release workflow for npm packages that use Changesets, a tool that records version and release notes for package changes.

In plain words
What is it for?
It helps create or use a changeset, run quality checks, commit and push changes, merge the versioning pull request, and publish the package to npm.
Why use it?
It removes repetitive release steps while checking that the new package version was actually published.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present.

Good fit It helps create or use a changeset, run quality checks, commit and push changes, merge the versioning pull request, and publish the package to npm.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outlinedriven/outline-driven-development/autoship
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 OutlineDriven/outline-driven-development --skill autoship
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/outline-driven-development

Made for: Claude Code, Codex.

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 autoship

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/autoship/github.svg)](https://agentmods.dev/skills/outlinedriven/outline-driven-development/autoship)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/autoship"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/autoship/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 autoship

Your own site · 80×15
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/autoship"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/autoship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,036 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 64
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium MCP Rug Pull · line 41
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
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 $0.00041 $0.02036
Opus 5 $0.00020 $0.01018
Sonnet 5 $0.00008 $0.00407
Haiku 4.5 $0.00004 $0.00204

Measured 2d ago against content hash eecc3e92fe6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

autoship 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.

.devin/skills/autoship/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autoship

Contract

Field Bound contract
Trigger release this, publish this package, autoship, cut a release, npm release flow
Authority Remote: pushes commits, merges the Version Packages PR, and publishes to npm; requires explicit human invocation. Invoking autoship is standing consent for the full release flow; gate risky steps on objective preconditions instead of pausing mid-flow. Force-push, history rewrites, and destructive git operations require explicit confirmation.
Side effect Writes a changeset file, runs quality-gate fixers, commits and pushes, merges the bot-opened Version Packages PR, and publishes to npm. Restricted to VCS-tracked targets and the npm registry.
Done New version is published on npm and confirmed by npm view <package> version matching the merged package.json.

Inputs

  • A changesets-based npm package with a release workflow in .github/workflows/ using changesets/action.
  • Optional bump level: defaults to patch; minor or major only on explicit user instruction.
  • No new changeset is required if one already exists on the default branch and the intent is to watch or merge only.

Procedure

The release workflow runs twice. First, push a commit carrying a pending .changeset/*.md file. The workflow runs changeset version in CI and opens a "Version Packages" PR on branch changeset-release/main. Merge that PR; the workflow runs again and, with no pending changesets left, runs changeset publish. The local job ends at pushing the changeset file. CI owns versioning and publishing; anything versioned locally breaks the loop.

  1. Create the changeset. Check for pending changesets (ls .changeset/*.md excluding README.md). If any exist, ask whether to add another or skip. Write the file directly because npm run changeset needs a TTY:
    cat > .changeset/<short-id>.md << 'EOF'
    ---
    "<package-name>": patch
    ---
    <one or two sentences of user-facing change>
    EOF
    
    Generate the short id with node -e "console.log(Math.random().toString(36).slice(2,10))". The description ships verbatim in CHANGELOG.md and is the only thing consumers read about this version. Done when: the changeset file is written with a valid package bump and user-facing description.

Read the full file on GitHub · 72 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. 2d ago Changed eecc3e92fe6b
  2. 4d ago First seen · 72 lines · 41 tokens per session scan A 99b59bd81a01

Subscribe to this mod's changes

autoship is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 41 tokens to every session and 2,036 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

git-branchless

Use when asked for multi-commit stack edits, rebases, fixups, or stacked-PR publishing with branchless git idioms. Not for plain-git workflows in repos without branchless.

OutlineDriven/odin-claude-plugin · 45 tokens

atomic-issues-prs

Use when the user says "atomic PRs" or requests one issue or PR per logical change. Don't use for single-change pushes or uncommitted change-sets.

OutlineDriven/odin-claude-plugin · 40 tokens

post-merge-cleanup

Use when a landed merge, release, or completed change needs its cleanup surface reconciled. Scans for stale TODOs, deprecations, unused flags, and doc gaps. Not for unrelated refactoring.

OutlineDriven/odin-claude-plugin · 48 tokens

git-workflow-and-versioning

Use when the user asks for release, version bump, changelog, or branch workflow beyond a single commit. Don't use for single commits or for publishing to a package registry.

OutlineDriven/odin-claude-plugin · 42 tokens

lockstep-version-guard

Use when a human invokes the release gate to prove all 28 ODIN plugins share one canonical version. Emits a per-file comparison and exits non-zero on mismatch. Don't use to edit release metadata or for remote, credential, publish, deploy, or irreversible changes.

OutlineDriven/odin-claude-plugin · 59 tokens

release-announcement

Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.

paperclipai/paperclip · 42 tokens