Starcat: Skill for Claude Code

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

starcat-release is a skill for Claude Code, Codex from starcat-app/Starcat. It costs 100 tokens per session (2,288 once invoked), scanned A, original, MIT.

A project-specific procedure for releasing the Starcat macOS app through its App Store and direct-download channels.

In plain words
What is it for?
It helps prepare App Store archives, build direct-download DMGs, manage Sparkle updates, deploy the website and changelog, and handle notarization and tags.
Why use it?
It helps choose the correct release path and follow the repository's rules for packaging, signing, updates, deployment, and related release tasks.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present. Also seen: mentions AGENTS.md.

This is starcat-app/Starcat's own configuration. It tells Claude Code and Codex how to work on Starcat 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 Starcat configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is STARCAT_NOTARIZE=1 ./scripts/release-direct.sh X.Y.Z.

Reuse

Borrowing it

Nothing to install: this file belongs to starcat-app/Starcat. 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/starcat-app/Starcat/main/.claude/skills/starcat-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/starcat-app/Starcat

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 starcat-release

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/starcat-app/starcat/starcat-release"><img src="https://agentmods.dev/badge/skills/starcat-app/starcat/starcat-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,288 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 $0.00100 $0.02288
Opus 5 $0.00050 $0.01144
Sonnet 5 $0.00020 $0.00458
Haiku 4.5 $0.00010 $0.00229

Measured 9d ago against content hash fd6214ec8c07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

starcat-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.

.claude/skills/starcat-release/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Starcat 发版

使用这个 skill 选择并执行正确的 Starcat 双渠道发版路径。正式入口是 App Store archive 与 Direct 公开发布两条;不要把 legacy 内测 DMG 流程或通用 macOS 发版流程 当成本仓库的权威正式流程。

硬性规则

  • 始终用中文回复,并遵守仓库 AGENTS.md:先给方案并征求 dong4j 明确确认,再修改文件或运行有副作用的发版命令。
  • 除非用户在当前对话中明确说“开干 / 执行 / 发布 / GO / 动手”,否则不要运行真实发布、部署、上传、git taggit pushrsyncssh、notarization 或 appcast 写入命令。
  • 排查时先使用只读命令:git statusgit taggit ls-remote--help、读取文件,以及脚本 dry-run 模式。
  • 不要为了发版手动修改 project.yml 里的版本号字段。Starcat 的版本来自 git tag 和构建脚本。
  • Starcat 已发布正式版;修改发版代码时保留线上用户、已发布 tag 和历史产物,不覆盖或复用既有版本。代码层废弃路径仍应一次性收口,不堆叠永久双轨。
  • 保留无关未提交文件。工作区不干净时,先判断这些改动是否与发版任务相关,再提出下一步。

入口选择

先判断用户要走哪条路径:

用户意图 使用入口 原因
App Store 发布准备、archive、Validate、上传 App Store Connect scripts/package-appstore.sh / make package-appstore 构建并校验 Starcat archive;上传继续由 Xcode Organizer / Transporter 完成
Direct 公开发布、Sparkle 更新、starcat.ink 部署、上传 DMG/appcast scripts/release-direct.sh <X.Y.Z> Direct 渠道完整编排入口;发布后还要同步 Homebrew Cask
只在本地构建 Direct 包 scripts/package-direct.sh <X.Y.Z> 构建 StarcatDirect DMG,可选 notarization/appcast
历史 ad-hoc 内测 tag + DMG 流程 scripts/release-store.sh vX.Y.Z legacy 入口;默认禁用,必须显式设置 STARCAT_ALLOW_LEGACY_RELEASE=1

如果用户只说“发版”但没有说明渠道,先确认是 App Store、Direct,还是双渠道。 如果用户提到 starcat.ink、Sparkle、appcast、notarization 或上传 DMG,可以推断为 Direct;提到 App Store Connect、Organizer、TestFlight 或审核则走 App Store。 两条路径都仍需先给方案并确认再执行。

标准工作流

  1. 需要细节时先读 references/release-map.md
  2. 用只读命令检查当前状态:
    • git status --short
    • git branch --show-current
    • git tag --sort=-creatordate | head
    • Direct 发版可补充:scripts/release-direct.sh --help
  3. 说明选择的入口、前提假设、副作用和验证标准。
  4. 除非用户当前轮已经明确授权执行,否则先等确认。
  5. 真实发布前优先 dry-run:
    • Direct:STARCAT_RELEASE_DRY_RUN=1 ./scripts/release-direct.sh <X.Y.Z>
    • App Store 没有发布 dry-run;先完成只读门禁,获授权后运行 make package-appstore,该命令只生成 archive、不上传
  6. 执行已确认的命令后,验证产物和 URL,并报告精确路径。

App Store 发布

App Store archive 使用 scripts/package-appstore.sh,日常入口:

make package-appstore
make open-appstore-archive

Read the full file on GitHub · 184 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 184 lines · 100 tokens per session scan A fd6214ec8c07

Subscribe to this mod's changes

starcat-release is a skill published in the GitHub repository starcat-app/Starcat (154 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 2,288 once invoked, about $0.0005 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.