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 lucasnad27/claude-plugins --skill cut-a-releasegit clone --depth 1 https://github.com/lucasnad27/claude-pluginsWrote 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/lucasnad27/claude-plugins/cut-a-release)<a href="https://agentmods.dev/skills/lucasnad27/claude-plugins/cut-a-release"><img src="https://agentmods.dev/badge/skills/lucasnad27/claude-plugins/cut-a-release/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/lucasnad27/claude-plugins/cut-a-release"><img src="https://agentmods.dev/badge/skills/lucasnad27/claude-plugins/cut-a-release.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 | $0.00091 | $0.01870 |
| Opus 5 | $0.00046 | $0.00935 |
| Sonnet 5 | $0.00018 | $0.00374 |
| Haiku 4.5 | $0.00009 | $0.00187 |
Grade A, and why
cut a 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 4d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cut a release for a plugin in this marketplace
This skill walks through releasing a plugin in the claude-plugins marketplace repo. The repo hosts multiple plugins; each has its own independent version. Releases are a git + GitHub affair — there's no build step or package registry to publish to. The "deploy" is just: bump versions, tag, push, and tell users to run /plugin marketplace update.
The critical gotcha (read this first)
Every plugin has its version declared in two separate files that must stay in sync:
.claude-plugin/marketplace.json— theversionfield inside the matching entry inplugins[](this is what Claude Code's update checker reads)plugins/<plugin-name>/.claude-plugin/plugin.json— the plugin's ownversionfield (this is what gets installed locally)
If these drift apart, Claude Code's /plugin will silently stop offering updates to users, even though the plugin code has moved on. Users appear stuck on an old version with no error message. Always bump both in the same commit.
Step 0: Smoke-test main first
Don't bump a version you haven't run. Load the working tree into a real project for one
session — see CLAUDE.md for the --plugin-dir recipe and the name-collision footgun.
Step 1: Determine version type
Based on changes since the last release, decide the SemVer bump:
- MAJOR (X.0.0) — Breaking changes to commands, skills, or agent interfaces; removed features; restructured workflow that existing users would need to relearn
- MINOR (x.X.0) — New commands, new skills, new agents, or new opt-in features
- PATCH (x.x.X) — Bug fixes, wording improvements, documentation fixes, small refinements to existing behavior
When in doubt for a plugin where users depend on muscle memory (command names, workflow steps), prefer MAJOR — being conservative here protects users.
Step 2: Identify the target plugin and gather info
ls plugins/ # list plugins in this marketplace
git status # confirm clean working tree
git log --oneline -20 # review recent 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.
- 4d ago Changed · +15 lines 300cef9409f7
- 9d ago First seen · 175 lines · 91 tokens per session scan A df66bbd800b5
cut a release is a skill published in the GitHub repository lucasnad27/claude-plugins (3 stars, last pushed 8d ago), licensed MIT. It adds 91 tokens to every session and 1,870 once invoked, about $0.0005 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.
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.
updater_guide
Guidance for checking for and installing Row-Bot updates.