czech-mtg-price-comparator-mcp: Skill for Claude Code

.claude/skills/publish/SKILL.md

publish is a skill for Claude Code from xvyslo05/czech-mtg-price-comparator-mcp. It costs 92 tokens per session (1,447 once invoked), scanned A, original, MIT.

Release instructions for publishing the cz-mtg-compare-mcp Python package to PyPI, the main package registry for Python software.

In plain words
What is it for?
Use them to bump the package version, commit and tag the release, push it to GitHub, and let the approved GitHub Actions workflow build and upload it.
Why use it?
They check the repository and tests before creating a version tag that starts the automated release process, reducing avoidable publishing errors.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: names the AskUserQuestion tool.

This is xvyslo05/czech-mtg-price-comparator-mcp's own configuration. It tells Claude Code how to work on czech-mtg-price-comparator-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 czech-mtg-price-comparator-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xvyslo05/czech-mtg-price-comparator-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/xvyslo05/czech-mtg-price-comparator-mcp/main/.claude/skills/publish/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/xvyslo05/czech-mtg-price-comparator-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/xvyslo05/czech-mtg-price-comparator-mcp/publish/github.svg)](https://agentmods.dev/skills/xvyslo05/czech-mtg-price-comparator-mcp/publish)
Your own site
<a href="https://agentmods.dev/skills/xvyslo05/czech-mtg-price-comparator-mcp/publish"><img src="https://agentmods.dev/badge/skills/xvyslo05/czech-mtg-price-comparator-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/xvyslo05/czech-mtg-price-comparator-mcp/publish"><img src="https://agentmods.dev/badge/skills/xvyslo05/czech-mtg-price-comparator-mcp/publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,447 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 $0.00092 $0.01447
Opus 5 $0.00046 $0.00724
Sonnet 5 $0.00018 $0.00289
Haiku 4.5 $0.00009 $0.00145

Measured 12d ago against content hash 1488fb2d0427, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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 · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish a new version

This skill drives a release of cz-mtg-compare-mcp to PyPI. The actual publishing is done by the .github/workflows/publish.yml workflow on tag push — it builds an sdist + wheel, smoke-tests the wheel install, and uploads via PyPI Trusted Publishing (OIDC, no stored token). The workflow pauses at a manual approval gate on the pypi environment.

The skill itself only takes the local steps that lead up to the tag push. It does NOT run twine upload or any direct publish command.

Steps

1. Pre-flight checks (fail fast)

Run these and stop if any fail. Surface the failure clearly to the user — don't try to "fix" by stashing or force-pushing.

  • Working tree must be clean: git status --porcelain returns nothing.
  • Branch must be main: git rev-parse --abbrev-ref HEAD == main.
  • Local main must be up to date with origin/main: git fetch origin then check git rev-list --count main..origin/main == 0. If behind, ask the user to pull/rebase first.
  • All tests pass: .venv/bin/pytest -q (NOT -m live — those hit real shops). The default suite must be green.

2. Pick the bump type

Read the current version from pyproject.toml (the version = "X.Y.Z" line under [project]).

Ask the user which semantic-versioning bump to apply (use AskUserQuestion):

  • patch (e.g. 0.1.0 → 0.1.1) — bug fixes only, no behavioural changes.
  • minor (e.g. 0.1.0 → 0.2.0) — new features, backwards compatible.
  • major (e.g. 0.1.0 → 1.0.0) — breaking changes (tool signatures change, removed fields, env-var renames, etc.).

Compute the new version string from the chosen bump.

3. Draft the release notes

Get the commits since the last tag:

git describe --tags --abbrev=0 2>/dev/null
# if a previous tag exists:
git log <last-tag>..HEAD --pretty=format:"- %s"
# if no tags yet:
git log --pretty=format:"- %s"

Draft a short release note:

  • One-sentence summary of the headline change.
  • Bullet list of the user-facing items only (skip internal refactors, doc-only commits, test-only commits unless they're regression-coverage worth flagging).
  • Group as Added / Changed / Fixed / Removed if there are enough entries to warrant grouping.

Read the full file on GitHub · 123 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. 12d ago First seen · 123 lines · 92 tokens per session scan A 1488fb2d0427

Subscribe to this mod's changes

publish is a skill published in the GitHub repository xvyslo05/czech-mtg-price-comparator-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,447 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.