kobato: Skill for Claude Code

.agents/skills/release/SKILL.md

release is a skill for Claude Code from syhily/kobato. It costs 46 tokens per session (1,150 once invoked), scanned A, original, MIT.

A command-led workflow for publishing a Kobato project release, including version changes, branches, tags, and a GitHub release.

In plain words
What is it for?
Use it when releasing a specified version and preparing the next development version.
Why use it?
It organizes the many release steps and checks that the project is on the right branch with no uncommitted changes.

Skill for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is syhily/kobato's own configuration. It tells Claude Code how to work on kobato 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 kobato configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/release.ts bump $version.

Reuse

Borrowing it

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

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/syhily/kobato/release"><img src="https://agentmods.dev/badge/skills/syhily/kobato/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,150 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 $0.00046 $0.01150
Opus 5.5 $0.00018 $0.00460
Sonnet 5.5 $0.00009 $0.00230
Haiku 4.5 $0.00005 $0.00115

Measured 2mo ago against content hash cb2e9dff4fc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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.

.agents/skills/release/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release

Execute a Kobato release. The user provides two arguments:

  1. $version — the version to release (e.g. 6.3.0).
  2. $next_version — the next development version on develop (e.g. 6.4.0-dev).

The entire release lifecycle runs automatically: analyze commits, draft notes, bump version, push to develop, fast-forward merge to main, tag and create the GitHub release, switch back to develop, prepare the next cycle, and push.

Step 0: Validate arguments

Both $version and $next_version must be present and match X.Y.Z or X.Y.Z-prerelease (e.g. 6.3.0, 6.3.0-beta.1, 6.4.0-dev). If either is missing or malformed, stop and ask the user for the correct value.

Step 1: Validate preconditions

  • Run git branch --show-current — must be on develop.
  • Run git status --porcelain — working tree must be clean. If dirty, stop and tell the user to commit or stash.
  • Run node scripts/release.ts since-last — note the last released tag.

Step 2: Analyze commits

Run git log <last-tag>..HEAD --format="%h %s" to get all commits since the last release.

If there are zero commits, tell the user there's nothing to release and stop.

Step 3: Study the release notes style

Run gh release view <last-tag> to read the most recent release notes body. This is your primary style reference.

Also read the second-most-recent release for additional context: run gh release view <tag-before-that>.

Internalize these style rules:

  • Title: ## Kobato X.Y.Z (h2, with "Kobato" prefix)
  • Lead paragraph: 1–2 sentences summarizing the release themes, with bolded feature names inline
  • Sections: Use ### headers with emoji prefixes — ### ✨ New Features, ### 🛡️ Security Hardening, ### 🏗️ Architecture & Refactoring, ### 🔧 Build & Dependencies, ### 🐛 Fixes. Only include sections that have entries. Add extra sections (e.g., ### 🎨 UI Redesign, ### 🎵 Music Player) if a thematic grouping makes sense.
  • Sub-headers: **Bold Title Case** to group related items within a section.
  • Bullets: Each change is a single - bullet, concise and technical. Describe what changed and often why. Use sentence case.
  • Language: English. Technical, precise, no first person.
  • Emojis: Only as section header prefixes, never inline.
  • Footer: **Full Changelog**: [prev...current](https://github.com/syhily/kobato/compare/PREV...CURRENT) — a clickable markdown link

Read the full file on GitHub · 94 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. 2mo ago First seen · 94 lines · 46 tokens per session scan A cb2e9dff4fc5

Subscribe to this mod's changes

release is a skill published in the GitHub repository syhily/kobato (114 stars, last pushed 7d ago), licensed MIT. It adds 46 tokens to every session and 1,150 once invoked, about $0.0002 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 2026-08-30.