Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jtsternberg/claude-pluginsnpx agentmods add skills/jtsternberg/claude-plugins/publish-releaseWrote 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/jtsternberg/claude-plugins/publish-release)<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/publish-release"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/publish-release.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.01132 |
| Opus 5 | $0.00039 | $0.00566 |
| Sonnet 5 | $0.00016 | $0.00226 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade A, and why
publish-release 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish a plugin/skill release
Runbook for shipping a plugin change to the people who install these plugins.
Run it — using the judgment below, or on an explicit /publish-release — once a
change-set is complete and ready to release. It is the checklist; the
authoritative step-by-step procedure lives in
docs/release.md, which this skill
points into rather than duplicating.
A change that reaches only your local working tree is not released. "Released" means the version is bumped, tests pass, and the change is merged to the ref marketplace users install from.
When to run — and when not to
Run it when both are true:
- The change is installer-visible: a plugin's skills, commands, hooks, scripts, or manifest changed in a way someone who installs the plugin would notice.
- The change-set is complete — the feature or fix is done, not mid-flight. Commit and iterate freely while you work; a release is the moment the whole set is ready, not each step along the way.
The user saying ship / publish / release / push a plugin is an explicit signal that both are true.
Do not run for:
- Whitespace-, typo-, or comment-only commits, unless the user asks.
- Changes that never reach installers: repo-root
AGENTS.md/README.md,docs/, maintainerscripts/,tests/, CI config, or a repo-local.claude/skill like this one — none of these is a distributed plugin. - Local experiments not yet merged.
When it is genuinely ambiguous whether a change is installer-visible, remember a release is outward-facing and hard to walk back — confirm before shipping rather than bumping on a hunch.
The one non-negotiable
When you do release, the affected plugin's manifest version must be bumped as part of that release. Plugin versions are release identifiers and Codex cache keys — an installer-visible change that ships with no version bump defeats the cache transition and leaves users on stale content. Semver: patch for fixes, minor for non-breaking additions, major for breaking 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.
- 8d ago First seen · 96 lines · 79 tokens per session scan A 55ddbb72e0b9
publish-release is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 1,132 once invoked, about $0.0004 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.
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.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
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.
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.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".
updater_guide
Guidance for checking for and installing Row-Bot updates.