mcp-replay-dota2: Skill for Claude Code

.claude/skills/release-version/SKILL.md

release-version is a skill for Claude Code from DeepBlueCoding/mcp-replay-dota2. It costs 122 tokens per session (1,222 once invoked), scanned A, original, MIT.

A release guide for the mcp-replay-dota2 Dota 2 replay MCP server. It describes how to change its version and publish packages, releases, and Docker images.

In plain words
What is it for?
Bump versions, update the changelog, create release tags, publish stable versions to PyPI, send prereleases to TestPyPI, and push Docker images.
Why use it?
It prevents release failures caused by mismatched versions, incorrect tags, or sending prerelease builds to the wrong package repository.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is DeepBlueCoding/mcp-replay-dota2's own configuration. It tells Claude Code how to work on mcp-replay-dota2 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 mcp-replay-dota2 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DeepBlueCoding/mcp-replay-dota2. 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/DeepBlueCoding/mcp-replay-dota2/master/.claude/skills/release-version/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/DeepBlueCoding/mcp-replay-dota2

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 release-version

README.md
[![agentmods](https://agentmods.dev/badge/skills/deepbluecoding/mcp-replay-dota2/release-version/github.svg)](https://agentmods.dev/skills/deepbluecoding/mcp-replay-dota2/release-version)
Your own site
<a href="https://agentmods.dev/skills/deepbluecoding/mcp-replay-dota2/release-version"><img src="https://agentmods.dev/badge/skills/deepbluecoding/mcp-replay-dota2/release-version/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 release-version

Your own site · 80×15
<a href="https://agentmods.dev/skills/deepbluecoding/mcp-replay-dota2/release-version"><img src="https://agentmods.dev/badge/skills/deepbluecoding/mcp-replay-dota2/release-version.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,222 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 $0.00122 $0.01222
Opus 5.5 $0.00049 $0.00489
Sonnet 5.5 $0.00024 $0.00244
Haiku 4.5 $0.00012 $0.00122

Measured 1mo ago against content hash 3df471657efc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-version 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 1mo 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/release-version/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release mcp-replay-dota2

release.yml is triggered ONLY by pushing a tag matching v*. It HARD-FAILS the build if the tag version != pyproject.toml [project].version. Get these aligned before pushing or the whole run dies.

Current version is 1.2.0 in BOTH [project].version AND [tool.commitizen].version. The commitizen version_files is a single regex (pyproject.toml:^version) that matches BOTH line-anchored version lines, so cz bump rewrites both at once — keep them aligned.

Workflow

  1. Pick the version. For a prerelease use a PEP440 suffix (.dev, aN, bN, rcN) — these route to TestPyPI, NOT PyPI. Stable versions go to PyPI + GitHub release + Docker.
  2. Bump with commitizen (preferred — keeps pyproject.toml and CHANGELOG.md in sync and creates the v$version tag):
    uv run cz bump          # auto-detects bump from conventional commits
    # or force: uv run cz bump --increment PATCH|MINOR|MAJOR
    
    commitizen config: cz_conventional_commits, tag_format=v$version, update_changelog_on_bump=true, changelog_file=CHANGELOG.md, incremental. The single version_files regex rewrites both [project].version and [tool.commitizen].version.
  3. Verify tag == version (release.yml does exactly this and exits 1 on mismatch):
    uv run python -c "import tomllib; print(tomllib.load(open('pyproject.toml','rb'))['project']['version'])"
    git describe --tags --abbrev=0
    
    The two must be identical (tag without the leading v).
  4. Run the local CI gate — release.yml re-runs ruff + mypy before building, so failures there waste a tagged run:
    uv run ruff check src/ tests/ dota_match_mcp_server.py
    uv run mypy src/ dota_match_mcp_server.py --ignore-missing-imports
    uv run pytest
    
  5. Update docs/changelog.md (Keep-a-Changelog, user-facing) for release notes if not already done. CHANGELOG.md is the commitizen-generated one — let cz bump own it.
  6. Push the tag to trigger the release pipeline (only when the user asks to push):
    git push origin master
    git push origin v<version>
    
  7. Ad-hoc image only: use the docker-manual.yml workflow (workflow_dispatch, input version) — pushes an image without a full release.

Read the full file on GitHub · 85 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. 1mo ago First seen · 85 lines · 122 tokens per session scan A 3df471657efc

Subscribe to this mod's changes

release-version is a skill published in the GitHub repository DeepBlueCoding/mcp-replay-dota2 (3 stars, last pushed 4mo ago), licensed MIT. It adds 122 tokens to every session and 1,222 once invoked, about $0.0005 per session on Opus 5.5. 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.