release

release is a skill for Claude Code from aoreshkov/kotlin-lib-mcp. It costs 57 tokens per session (1,163 once invoked), scanned A, original, Apache-2.0.

A release-preparation workflow for the kotlin-lib-mcp project, which provides tools for inspecting Kotlin and Java libraries. It keeps the project version, changelog, checks, and optional Git tag in sync.

In plain words
What is it for?
Use it to choose or apply a version bump, update the changelog, run release checks, and optionally create the matching Git tag.
Why use it?
It prevents a release tag from disagreeing with the versions built into the project, which would stop the release process.

Skill for Claude Code

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

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/aoreshkov/kotlin-lib-mcp/release
Any agent
npx skills add aoreshkov/kotlin-lib-mcp --skill release
Clone the repo
git clone --depth 1 https://github.com/aoreshkov/kotlin-lib-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 release

README.md
[![agentmods](https://agentmods.dev/badge/skills/aoreshkov/kotlin-lib-mcp/release.svg)](https://agentmods.dev/skills/aoreshkov/kotlin-lib-mcp/release)
Your own site
<a href="https://agentmods.dev/skills/aoreshkov/kotlin-lib-mcp/release"><img src="https://agentmods.dev/badge/skills/aoreshkov/kotlin-lib-mcp/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,163 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00057 $0.01163
Opus 5 $0.00028 $0.00581
Sonnet 5 $0.00011 $0.00233
Haiku 4.5 $0.00006 $0.00116

Measured 6d ago against content hash 1284ae70977f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cut a release

The release workflow (.github/workflows/release.yml) is triggered by a v* tag and its first step is a hard version-match guard: if the tag doesn't match the version in both source-of-truth files, the whole release (GitHub release + GHCR image + MCP registry publish) fails. This skill makes the two files agree before the tag is pushed.

The advertised MCP Implementation version is not a third file to bump: it is build-derived from gradle.properties (server/build.gradle.kts bakes project.version into a resource read by ServerVersion) and asserted by ServerVersionTest, so it can never drift and needs no separate guard.

1. Determine the new version

Use $ARGUMENTS if given. Otherwise read the current version from gradle.properties (version=), decide the bump with the user (semver), and confirm. Call the new value <VERSION> (no v prefix inside files; the git tag is v<VERSION>).

2. Bump the version in BOTH guarded files

The tag guard checks these exact patterns (keep the formatting identical):

  1. gradle.properties — the line version=<VERSION> (guard: ^version=<VERSION>$). This is the single source of truth; the runtime MCP version is derived from it (see the note above), so there is no third file to bump.
  2. server.json — the top-level "version": "<VERSION>" (guard: jq .version == <VERSION>). Note: the workflow later also rewrites server.json .version and .packages[0].identifier from the tag, but the guard still requires the committed value to match, so set it here.

Miss either and the release job aborts at the guard step. Grep to confirm both:

grep -n "version=" gradle.properties
grep -n '"version"' server.json

On a MAJOR or MINOR bump, also repin the plugin. plugin/.mcp.json pins the image to the <major>.<minor> tag (ghcr.io/aoreshkov/kotlin-lib-mcp:0.5), which follows patches on its own but not a minor bump. Update that tag and bump plugin/.claude-plugin/plugin.json .version (its own semver, independent of the server's) so installed plugins actually receive the update — the community catalog re-pins from the repo automatically. Patch releases need neither.

Read the full file on GitHub · 93 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. 6d ago First seen · 93 lines · 57 tokens per session scan A 1284ae70977f

Subscribe to this mod's changes

release is a skill published in the GitHub repository aoreshkov/kotlin-lib-mcp (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 1,163 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

to-plan

Use when one ready GitHub issue or an in-chat task needs a repository-aware implementation plan for a later implementation workflow.

chrisbanes/skills · 27 tokens

compose-ui-testing-patterns

Use when writing or reviewing Jetpack Compose UI tests, screenshot tests, previews, semantics assertions, fake image loading, keyboard input, focus assertions, interaction state (hover/pressed/focused), or tests for plain state-driven UI composables.

chrisbanes/skills · 54 tokens

compose-animations

Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.

chrisbanes/skills · 64 tokens

gradle-run

Use when planning to execute Gradle through gradle, ./gradlew, or a custom gradlew wrapper script, or diagnosing a Gradle build, compact workflow ledger, repeated failure fingerprint, check, test, lint, warning, or failure even when no new Gradle run is appropriate.

chrisbanes/skills · 67 tokens

compose-focus-navigation

Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.

chrisbanes/skills · 41 tokens

kotlin-control-flow

Use when writing or reviewing Kotlin branching and control flow: when expressions, guard conditions, sealed type exhaustiveness, smart casts, nullable branching, early returns, or replacing complex if/else chains.

chrisbanes/skills · 44 tokens