FloatSoda: Skill for Claude Code

.agents/skills/floatsoda-release/SKILL.md

floatsoda-release is a skill for Claude Code, Codex from sumx21t-3310/FloatSoda. It costs 268 tokens per session (3,107 once invoked), scanned A, original, MIT.

A release procedure for publishing a new FloatSoda version. It covers the preparation before tagging and the checks needed for the automated build, test, package, and NuGet publishing workflow.

In plain words
What is it for?
Use it to confirm the release scope, update the version and changelog, run verification and documentation checks, create the tag and release, and monitor NuGet publication.
Why use it?
It reduces errors caused by release steps being remembered differently each time, such as missing GitHub Releases or incorrect changelog comparison links. It also keeps the release aligned with the project's documented policy.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is sumx21t-3310/FloatSoda's own configuration. It tells Claude Code and Codex how to work on FloatSoda 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 FloatSoda configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sumx21t-3310/FloatSoda. 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/sumx21t-3310/FloatSoda/main/.agents/skills/floatsoda-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sumx21t-3310/FloatSoda

Made for: Claude Code, Codex.

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 floatsoda-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/sumx21t-3310/floatsoda/floatsoda-release/github.svg)](https://agentmods.dev/skills/sumx21t-3310/floatsoda/floatsoda-release)
Your own site
<a href="https://agentmods.dev/skills/sumx21t-3310/floatsoda/floatsoda-release"><img src="https://agentmods.dev/badge/skills/sumx21t-3310/floatsoda/floatsoda-release/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 floatsoda-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/sumx21t-3310/floatsoda/floatsoda-release"><img src="https://agentmods.dev/badge/skills/sumx21t-3310/floatsoda/floatsoda-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 268 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,107 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00268 $0.03107
Opus 5 $0.00134 $0.01554
Sonnet 5 $0.00054 $0.00621
Haiku 4.5 $0.00027 $0.00311

Measured yesterday against content hash 551677be6634, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

floatsoda-release 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 yesterday.

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.

.agents/skills/floatsoda-release/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FloatSoda リリース

このスキルが存在する理由

リリースパイプラインは半分しか自動化されていない。.github/workflows/release.yml が引き継ぐのは git push origin vX.Y.Z からで、build → test → pack → NuGet を処理する。その タグより前のすべてと、タグの後の GitHub Release は人間の儀式 — そして儀式は風化する。この リポジトリでの実証: v0.2.0 / v0.3.0 / v0.3.1 はタグが打たれ NuGet に公開されたが、 GitHub Release は一度も作成されず、CHANGELOG の compare リンクは v0.3.0...main を指した まま、[0.3.1] のリンク行は丸ごと欠けていた。それらの手順が記憶に依存しないようにするのが このスキル。

唯一の正典

RELEASING.mdポリシーの正典で、このスキルはその執行者。

  • 毎回の実行の最初に RELEASING.md を読み、記憶ではなくそこに書いてあることに従う。
  • このスキルと RELEASING.md が食い違ったら RELEASING.md が勝つ — そして食い違いを口に出す。 スキルが直されるように。
  • ポリシーの例外をここに書き込まない。 ゲートの動かし方を変えるとオーナーが決めたら(たとえば ジュニアコーダーゲートを Phase 完了まで先送りする、など)、その変更は RELEASING.md に属する。 このスキルに「ただし当面は代わりに X する」という分岐を持たせてはならない。

ハードストップ — オーナーの明示的な承認が要るもの

このワークフローの他のすべては可逆。これらはそうではない。

  1. git push origin vX.Y.Z — Trusted Publishing 経由で NuGet に公開される。公開された バージョンは差し替えられず、deprecate / unlist しかできない。
  2. gh release create — 公開の、外向きの操作。

準備を整え、diff と計画を提示して、止まる。前の手順が「明らかに」示唆していたからといって、 タグを push しない。

ワークフロー

タスクツールで追跡すること — リリースは手順が多く、1つ抜けるのが既定の失敗モードになる。

0. 事前確認

  • 作業ツリーがクリーン(git status --porcelain が空)で main にいて、origin/main と同期 している。リリースをフィーチャーブランチから切ってはならない。
  • リリースコミットで CI がグリーン(gh run list --branch main --limit 5)。
  • gh auth status が通る(手順1、7、8 で必要)。

1. リリーススコープを確定する

git describe --tags --abbrev=0

そのタグから HEAD までを diff する(git log --oneline <prev>..HEAD、PR 単位の視点には --merges)。3方向でクロスチェックし、不一致は黙って直さず報告する:

  • コミット vs [Unreleased] — CHANGELOG エントリの無い利用者可視の変更、またはコミットの 無いエントリ。
  • マイルストーンgh api repos/sumx21t-3310/FloatSoda/milestones で Phase 一覧を取り、 gh issue list --milestone "<title>" --state closed でこのリリースが実際に閉じる Issue を見る。 上のコミットで修正されたのにまだ開いている Issue が、報告すべき発見。
  • public API サーフェス — この範囲に public API の追加・変更はあるか? あるなら docs/ が それに合わせて更新済みかを確認する(CONTRIBUTING は新しい public API に docs 先行を要求する)。 手順5のジュニアゲートが読むのはまさにそのページだから。

Read the full file on GitHub · 156 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. yesterday Changed · +5 lines · +82 tokens per session 551677be6634
  2. 12d ago First seen · 151 lines · 186 tokens per session scan A e32ef87cf3b4

Subscribe to this mod's changes

floatsoda-release is a skill published in the GitHub repository sumx21t-3310/FloatSoda (11 stars, last pushed 2d ago), licensed MIT. It adds 268 tokens to every session and 3,107 once invoked, about $0.0013 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.

Related

Other skills, from other repositories

safe-github-push

A workflow for safely pushing Git repositories that contain large assets or binary files to GitHub. It checks repository changes and file sizes before planning commits and pushes.

moorestech/moorestech · 114 tokens

sentry

Use when adding error tracking, performance monitoring, and release health to .NET applications — ASP.NET Core, MAUI, WPF, Blazor, EF Core integration. Sentry .NET SDK: cross-platform error and performance monitoring with source map support, breadcrumbs, and alerting.

znlgis/opengis-skills · 60 tokens

improve-test-coverage

Iteratively write .NET unit tests to improve code coverage toward 80% line and branch targets. USE FOR: autonomously running tests, finding gaps, writing targeted tests, and repeating until 80% coverage or plateau. Calls all 7 dotnet-coverage-mcp MCP tools: GetSourceFiles, RunTestsWithCoverage, GetCoverageSummary…

Hyeonu-Cha/dotnet-coverage-mcp · 139 tokens

analyze-coverage-gaps

Identify uncovered branches and coverage changes for a specific .NET method. USE FOR: finding exactly which branch conditions are untested in a method, comparing current coverage against the previous baseline to see what improved. Calls GetUncoveredBranches and GetCoverageDiff via dotnet-coverage-mcp MCP tools. DO NOT…

Hyeonu-Cha/dotnet-coverage-mcp · 90 tokens

run-coverage

Run .NET tests with code coverage and display a summary. USE FOR: generating a coverage report for a test project, getting baseline line/branch coverage per class and method, checking current coverage percentages. Calls RunTestsWithCoverage then GetCoverageSummary via dotnet-coverage-mcp MCP tools. Requires…

Hyeonu-Cha/dotnet-coverage-mcp · 100 tokens

maintain-discatsharp

Review, modify, test, document, or release the DisCatSharp repository. Use for DisCatSharp source changes, API additions and migrations, Discord payload models, serialization, command synchronization, Gateway dispatch, REST behavior, analyzer work, multi-target testing, DocFX generation, release notes, and repository…

Aiko-IT-Systems/DisCatSharp · 69 tokens