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.
npx skills add julianobarbosa/claude-code-skills --skill ship-taggit clone --depth 1 https://github.com/julianobarbosa/claude-code-skillsWrote 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.
[](https://agentmods.dev/skills/julianobarbosa/claude-code-skills/ship-tag)<a href="https://agentmods.dev/skills/julianobarbosa/claude-code-skills/ship-tag"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/ship-tag/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.
<a href="https://agentmods.dev/skills/julianobarbosa/claude-code-skills/ship-tag"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/ship-tag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00130 | $0.02513 |
| Opus 5.5 | $0.00052 | $0.01005 |
| Sonnet 5.5 | $0.00026 | $0.00503 |
| Haiku 4.5 | $0.00013 | $0.00251 |
Grade A, and why
ship-tag 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ship-tag
ship gets a change reviewed. ship-tag turns reviewed changes into a release someone else can install: one version string, carried the same way by a release branch, an annotated tag, the version file, the CHANGELOG heading and a published package, each read back from its authority rather than assumed.
Not
ship'sship-tag.ts. That script manages PR labels. This skill is about release versions: git tags, release branches, packages and the changelog.
Workflow Routing
| Trigger | Workflow |
|---|---|
| "add a changelog entry", "create CHANGELOG.md", "release notes", "backfill the changelog", "lint the changelog" | Workflows/Changelog.md |
| "cut a release", "release branch", "don't merge into main, target a release branch", "bump the version" | Workflows/CutRelease.md |
| "PR merged, tag it", "tag and publish", "publish the tar.gz", "universal package" | Workflows/TagAndPublish.md |
| "release locally", "no remote", "tag a release without a PR", "cut 1.4.0 on this branch" | Workflows/LocalRelease.md |
What a finished release looks like
- One SemVer string
X.Y.Zagrees in all five places: branchrelease/vX.Y.Z, tagvX.Y.Z, the version file (pyproject.toml/package.json), the## [X.Y.Z] - YYYY-MM-DDheading in CHANGELOG.md, and the package version in the feed. - The tag and the package both come from the merge commit of a pull request whose status is
completed. Nothing unreviewed carries the version. - The artifact was built from that commit in a clean worktree with
SOURCE_DATE_EPOCHpinned, and the copy a consumer downloads matches the built file's sha256 and installs. - A consumer can act on the package without asking anyone: the feed Description says what changed, how to install and how to run it, and a generated
README.mdinside the package has the full install, checksum and usage steps. - CHANGELOG.md tells users what changed, in the six Keep a Changelog categories, with compare links, and passes
Changelog.ts lint --strict. - The base branch gets the release back through its own PR, so a release branch never becomes a dead end.
What ships with it
17 files 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.
- References/ChangelogSamples.md 9.5 KB
- References/KeepAChangelog.md 9.5 KB
- References/Patterns.md 4.8 KB
- References/ReleaseWalkthrough.md 7.8 KB
- Tools/Changelog.test.ts 11 KB runs code
- Tools/Changelog.ts 25 KB runs code
- Tools/Lib.ts 13 KB runs code
- Tools/Release.test.ts 16 KB runs code
- Tools/ReleaseCut.ts 8.0 KB runs code
- Tools/ReleaseDocs.test.ts 4.4 KB runs code
- Tools/ReleaseDocs.ts 5.6 KB runs code
- Tools/ReleaseLocal.ts 5.2 KB runs code
- Tools/ReleasePublish.ts 13 KB runs code
- Workflows/Changelog.md 4.3 KB
- Workflows/CutRelease.md 3.4 KB
- Workflows/LocalRelease.md 1.7 KB
- Workflows/TagAndPublish.md 4.2 KB
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.
- 1mo ago First seen · 102 lines · 130 tokens per session scan A eff750d7af0e
ship-tag is a skill published in the GitHub repository julianobarbosa/claude-code-skills (14 stars, last pushed 11d ago), licensed MIT. It adds 130 tokens to every session and 2,513 once invoked, about $0.0005 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 2026-09-13.
Other skills, from other repositories
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.
release
Fully automate a release with version-bump and childhood.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.