A release workflow for the claude-ultimate-hud plugin. It builds the project, updates version information and documentation, then commits, pushes, creates a GitHub release, and cleans local caches.

Use it to publish a new plugin version with a version number and release description. It updates package and marketplace metadata, README content, and the changelog.

It gathers the repeated release steps into one ordered process. It also stops when the build fails or when the working directory has no changes.

release — Skill for Claude Code by hadamyeedady12-dev

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/hadamyeedady12-dev/claude-ultimate-hud

agentmods

npx agentmods add skills/hadamyeedady12-dev/claude-ultimate-hud/release

Made for: Claude Code.

Or install claude-ultimate-hud, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hadamyeedady12-dev/claude-ultimate-hud/release/github.svg)](https://agentmods.dev/skills/hadamyeedady12-dev/claude-ultimate-hud/release)

Your own site

<a href="https://agentmods.dev/skills/hadamyeedady12-dev/claude-ultimate-hud/release"><img src="https://agentmods.dev/badge/skills/hadamyeedady12-dev/claude-ultimate-hud/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hadamyeedady12-dev/claude-ultimate-hud/release"><img src="https://agentmods.dev/badge/skills/hadamyeedady12-dev/claude-ultimate-hud/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,575 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.

Model	Per session	Once invoked
Fable 5.1	$0.00026	$0.01575
Opus 5	$0.00013	$0.00788
Sonnet 5	$0.00005	$0.00315
Haiku 4.5	$0.00003	$0.00158

Measured 9d ago against content hash 39686d12c5aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

skills/release/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-ultimate-hud Release Workflow

새 버전을 릴리즈하는 전체 워크플로우를 자동 실행합니다.

Arguments

$0: 새 버전 번호 (예: 1.6.0). 생략 시 사용자에게 질문합니다.
$1~: 릴리즈 한줄 설명 (예: API stability & git extensions). 생략 시 자동 생성합니다.

Pre-check

작업 디렉토리가 claude-ultimate-hud 플러그인 루트인지 확인합니다.
- 아니면 cd ~/.claude/plugins/claude-ultimate-hud 또는 마켓플레이스 캐시 경로로 이동합니다.
git status로 현재 상태를 확인합니다.
변경 사항이 없으면 사용자에게 알리고 중단합니다.

Step 1: Gather Info

버전이 $0으로 제공되지 않으면 AskUserQuestion으로 물어봅니다:

header: "Version"
question: "새 버전 번호를 입력하세요 (현재: {현재 package.json 버전})"

릴리즈 설명이 없으면 git diff HEAD --stat과 변경된 소스 파일을 분석해서 한줄 제목과 changelog를 자동 생성합니다.

Step 2: Build

bun run build

빌드 실패 시 중단합니다.

Step 3: Version Bump

아래 3개 파일에서 버전을 $0으로 업데이트합니다:

package.json: "version": "{OLD}" → "version": "{NEW}"
.claude-plugin/plugin.json: metadata.version
.claude-plugin/marketplace.json: metadata.version

Step 4: Update README

4-1. README.md (한국어)

## 기능 섹션 아래, 기존 최신 버전 항목 위에 새 버전 feature highlight를 추가합니다:

### v{VERSION} - {한줄 설명}
- 주요 변경 사항 목록 (git diff에서 추출)

## 출력 예시 섹션의 코드 블록을 새 기능이 반영된 예시로 업데이트합니다 (변경 필요시에만).

## 변경 이력 섹션 맨 위에 상세 changelog를 추가합니다:

### v{VERSION}
- 변경 항목들 (구체적, 기술적)

4-2. README.en.md (English)

동일한 구조로 영문 README도 업데이트합니다. 한국어 changelog를 영어로 번역하여 추가합니다.

Changelog 작성 규칙

git diff HEAD 또는 커밋된 변경 사항을 분석하여 changelog를 생성합니다.
각 항목은 적절한 이모지 prefix를 사용합니다:
- 🔒 보안/안정성, 🌿 Git, 📊 데이터/표시, 🔥 성능
- 📝 코드 변경, 🔍 디버그/추적, 📋 기능, 📏 UI
- ⚙️ 설정, 📦 빌드/파일, 🛡️ 검증, ❄️ 캐시
변경 유형별로 그룹핑합니다 (API, Git, UI, Config 등).
짧고 구체적으로 작성합니다 — "개선" 같은 모호한 표현 금지.

Step 5: Rebuild dist

README/metadata 변경 후 dist가 변경되었을 수 있으므로 리빌드합니다:

bun run build

Step 6: Commit

커밋 1 — 소스 변경 (이미 unstaged인 경우):

feat: upgrade to v{VERSION} — {한줄 설명}

{상세 변경 사항 요약}

Co-Authored-By: Claude Opus 4.6 <[email protected]>

커밋 2 — README/메타데이터:

docs: add v{VERSION} changelog, update marketplace and plugin metadata

Co-Authored-By: Claude Opus 4.6 <[email protected]>

Read the full file on GitHub · 186 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.

9d ago First seen · 186 lines · 26 tokens per session scan A 39686d12c5aa

Subscribe to this mod's changes

release is a skill published in the GitHub repository hadamyeedady12-dev/claude-ultimate-hud (48 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,575 once invoked, about $0.0001 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.

Claude Code Git and workflow Releases developer-tools hud statusline tmux

session-end

Use when branch work is finished and the user asks to close the session out — "/session-end", "encerra a sessão", "fecha essa branch", "vamos encerrar aqui", "abre o PR e faz o merge", "leva até o merge e limpa a branch", "finaliza e limpa o worktree". Also OFFER it (do not auto-run it) when the user signals closure…

will-pagane/claude-superdev-harness · 0 tokens

release