semver-setup

semver-setup is a skill for Claude Code from artem-from-ua/claude-plugins. It costs 68 tokens per session (945 once invoked), scanned A, original, MIT.

An interactive setup command for semantic versioning, a system that uses MAJOR, MINOR, and PATCH numbers to communicate software changes. It creates or updates project settings for tracking versions and enforcing version rules.

In plain words
What is it for?
Use it to configure version files, choose version fields and formats, and set the project's version-change triggers and enforcement rules.
Why use it?
It avoids manually deciding which files contain versions and how version changes should be handled. It can also account for monorepos, which are projects containing multiple packages or applications in one repository.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Part of the semver plugin — 2 skills shipped together

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.

agentmods
npx agentmods add skills/artem-from-ua/claude-plugins/semver-setup
Any agent
npx skills add artem-from-ua/claude-plugins --skill semver-setup
Clone the repo
git clone --depth 1 https://github.com/artem-from-ua/claude-plugins

Made for: Claude Code.

Or install semver, the plugin that ships this one along with the rest of its 2 skills.

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 semver-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/artem-from-ua/claude-plugins/semver-setup.svg)](https://agentmods.dev/skills/artem-from-ua/claude-plugins/semver-setup)
Your own site
<a href="https://agentmods.dev/skills/artem-from-ua/claude-plugins/semver-setup"><img src="https://agentmods.dev/badge/skills/artem-from-ua/claude-plugins/semver-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 945 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00068 $0.00945
Opus 5 $0.00034 $0.00473
Sonnet 5 $0.00014 $0.00189
Haiku 4.5 $0.00007 $0.00094

Measured 6d ago against content hash b7766fecfc09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

semver-setup 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 6d 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.

plugins/semver/commands/semver-setup/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semver Setup

Configure semantic versioning enforcement for this project.

Steps

1. Detect existing config and version files

Check for existing configuration:

  • Read .claude-plugin/semver.json if present (use as defaults for all questions)
  • Auto-detect common version files in the project root: package.json, pyproject.toml, Cargo.toml, .claude-plugin/plugin.json, version.txt
  • For monorepos: also scan one level deep (e.g., packages/*/package.json)

Show the user what was found.

2. Ask: which version files to track

Use AskUserQuestion with multiSelect: true. List detected files with descriptions:

  • package.json — npm/Node.js projects
  • pyproject.toml — Python projects (field: project.version or tool.poetry.version)
  • Cargo.toml — Rust projects (field: package.version)
  • .claude-plugin/plugin.json — Claude Code plugins (field: version)
  • Other: ask user to enter path manually

For each selected file, ask:

  • Field path (dot notation for nested) — default by file type: version for JSON, project.version for pyproject.toml, package.version for Cargo.toml
  • Formatjson / toml / yaml / text (auto-detected from extension if possible)

3. Ask: trigger strategy

Use AskUserQuestion (single select):

  • auto — Claude evaluates each change and decides. New feature → MINOR, bug fix → PATCH, breaking change → MAJOR, docs/config only → skip. (Recommended)
  • always — Every commit with source file changes must include a version bump. No exceptions. Good for strict release workflows.

4. Ask: enforcement level

Use AskUserQuestion (single select):

  • ask — Warn and ask for confirmation before proceeding without a bump. (Default)
  • deny — Block commit/push/PR until a version bump is staged.
  • allow — No enforcement. Only session rules, no hook blocking.

5. Ask: base branch

Use AskUserQuestion (single select):

  • main (Default)
  • master
  • develop
  • Other (user enters custom name)

Read the full file on GitHub · 107 lines

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. 6d ago First seen · 107 lines · 68 tokens per session scan A b7766fecfc09

Subscribe to this mod's changes

semver-setup is a skill published in the GitHub repository artem-from-ua/claude-plugins (11 stars, last pushed 20d ago), licensed MIT. It adds 68 tokens to every session and 945 once invoked, about $0.0003 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 2026-08-30.