rohlik-mcp: Skill for Claude Code

.claude/skills/publish/SKILL.md

publish is a skill for Claude Code from tomaspavlin/rohlik-mcp. It costs 10 tokens per session (218 once invoked), scanned A, original, MIT.

A release helper for npm packages, which are reusable JavaScript or TypeScript projects shared through the npm registry. It asks for a version change, updates the package version, and creates a Git tag.

In plain words
What is it for?
Use it to prepare patch releases for bug fixes, minor releases for new features, or major releases with breaking changes.
Why use it?
It provides a structured versioning step while leaving the final upload to npm under the user's control.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is tomaspavlin/rohlik-mcp's own configuration. It tells Claude Code how to work on rohlik-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rohlik-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tomaspavlin/rohlik-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tomaspavlin/rohlik-mcp/main/.claude/skills/publish/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tomaspavlin/rohlik-mcp

Made for: Claude Code.

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 publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomaspavlin/rohlik-mcp/publish/github.svg)](https://agentmods.dev/skills/tomaspavlin/rohlik-mcp/publish)
Your own site
<a href="https://agentmods.dev/skills/tomaspavlin/rohlik-mcp/publish"><img src="https://agentmods.dev/badge/skills/tomaspavlin/rohlik-mcp/publish/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.

agentmods 80×15 button for publish

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomaspavlin/rohlik-mcp/publish"><img src="https://agentmods.dev/badge/skills/tomaspavlin/rohlik-mcp/publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 218 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00010 $0.00218
Opus 5 $0.00005 $0.00109
Sonnet 5 $0.00002 $0.00044
Haiku 4.5 $0.00001 $0.00022

Measured 11d ago against content hash 16a857f654a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

publish 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 11d 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.

.claude/skills/publish/SKILL.md · 28 lines

What it actually says

Publish NPM Package

1. Ask the user what version bump they want

  • patch (e.g. 3.2.0 → 3.2.1) - bug fixes
  • minor (e.g. 3.2.0 → 3.3.0) - new features
  • major (e.g. 3.2.0 → 4.0.0) - breaking changes

2. Bump the version

Run npm version patch, npm version minor, or npm version major based on the user's choice. This updates package.json and creates a git tag.

3. Tell the user to publish

Tell the user to run:

npm publish --access public

Do NOT run npm publish yourself. The user needs to authenticate with npm and must run this command manually.

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. 11d ago First seen · 28 lines · 10 tokens per session scan A 16a857f654a4

Subscribe to this mod's changes

publish is a skill published in the GitHub repository tomaspavlin/rohlik-mcp (120 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 218 once invoked, about $0.0001 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.