Expertise·Developer Tools & Repos·v1.0.0

release-check Agent Skill

Before releasing, tagging or publishing an MCP server, check with toolmenu what changed in its tool list since the last release, whether it breaks clients, and whether the version bump is big…

Context cost
725 tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 2.9 kBtext throughout, nothing executable
Licence
MITthe author’s own terms
Last change
yesterdayv1.0.0
Servers it uses
1 servertoolmenu-mcp

What it does

Before releasing, tagging or publishing an MCP server, check with toolmenu what changed in its tool list since the last release, whether it breaks clients, and whether the version bump is big…

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

Expertise

Domain judgement the base model does not have.

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md2.9 kB · preview
--- name: release-check ---
6# Checking an MCP server release
7
8toolmenu compares the server's tool list now with the last release's, and reports
9what breaks clients (removed tools, new required parameters, narrowed types), what
10changes for agents, the token change per conversation, and the version bump it needs.
11
12## 1. Find the baseline
13
14The menu of the last release, in this order:
15
161. A committed menu.json (or the path toolmenu.config.json or the CI workflow's
17 baseline: input names). Check it matches the last release: git log -1 -- menu.json
18 against the last tag. If it was updated after the tag, use the tag's copy:
19 git show <last tag>:./menu.json > /tmp/baseline.json (./: the path from the
20 current folder, not the repository root).
212. No baseline: build the last release in a separate worktree
22 (git worktree add /tmp/last-release <last tag>), build it there, snapshot it with
23 snapshot_menu (cwd that worktree, save_as an absolute path outside the repo),
24 then git worktree remove /tmp/last-release.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md431 words
Files1
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈90
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
635
on trigger
The instruction body, read only when the skill fires.
0.36%
of a 200k window
Ten skills this size would take about 4% of the window before you open a file.
050k100k150k200k context window

725 tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Small enough to keep loaded permanently without thinking about it.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

It expects 1 MCP server to be connected. Each step names the tool it needs, so a missing server stops the skill with a plain message rather than an invented answer. They are not listed here yet — the names are the author’s own.

TOtoolmenu-mcpNamed by the author; not listed in this catalogue, so connect it yourself.
What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 2.9 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md2.9 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# release-check · 725 tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/niksa90-release-check/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/release-check" ] && { [ ! -e .claude/skills/release-check ] || { mv .claude/skills/release-check "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/release-check" .claude/skills/ && echo "Installed .claude/skills/release-check"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add niksa90/release-check

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/release-check/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/niksa90-release-check/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/release-check" ] && { [ ! -e ~/.claude/skills/release-check ] || { mv ~/.claude/skills/release-check "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/release-check" ~/.claude/skills/ && echo "Installed ~/.claude/skills/release-check" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/release-check/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version1.0.0
Publishedyesterday
PriceFree
Referenceniksa90/release-check

Versions

v1.0.0 shipped yesterday. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.0.0
7 Nov 2026
  • The version this listing went live with, after review.
Pinning

The install command always fetches the release that is current the day you run it — v1.0.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers1