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.
npx skills add pixel-cellar/Claude-Code-Game-Studios --skill launch-checklistgit clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-StudiosWrote 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.
[](https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/launch-checklist)<a href="https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/launch-checklist"><img src="https://agentmods.dev/badge/skills/pixel-cellar/claude-code-game-studios/launch-checklist/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.
<a href="https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/launch-checklist"><img src="https://agentmods.dev/badge/skills/pixel-cellar/claude-code-game-studios/launch-checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.02334 |
| Opus 5.5 | $0.00000 | $0.00934 |
| Sonnet 5.5 | $0.00000 | $0.00467 |
| Haiku 4.5 | $0.00000 | $0.00233 |
Grade A, and why
launch-checklist 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
---
name: launch-checklist
description: "全面的发布就绪验证，涵盖所有部门：代码、内容、商店、市场、社区、基础设施、法务，以及上线/不上线决策签字。"
argument-hint: "[launch-date or 'dry-run']"
user-invocable: true
allowed-tools: Read, Glob, Grep, Write
---
当此技能被调用时：
> **仅限显式调用**：此技能仅在用户通过 `/launch-checklist` 显式请求时运行。不要基于上下文匹配自动调用。
1. **读取参数**，获取发布日期或 `dry-run` 模式。演练模式（Dry-run）仅生成清单，不创建签字条目。
2. **收集项目上下文**：
- 读取 `CLAUDE.md` 获取技术栈、目标平台和团队结构
- 读取 `production/milestones/` 中最新的里程碑
- 读取 `production/releases/` 中已有的发布清单（如有）
- 读取 `design/live-ops/content-calendar.md` 中的内容日历（如存在）
3. **扫描代码库健康度**：
- 统计 `TODO`、`FIXME`、`HACK` 注释及其位置
- 检查生产代码中是否遗留了 `console.log`、`print()` 或调试输出
- 检查占位资产（搜索 `placeholder`、`temp_`、`WIP_`）
- 检查硬编码的测试/开发值（localhost、测试凭据、调试标志）
4. **生成发布清单**：
```markdown
# 发布清单: [游戏标题]
目标发布: [日期或 DRY RUN]
生成时间: [日期]
---
## 1. 代码就绪
### 构建健康
- [ ] 所有目标平台干净构建通过
- [ ] 零编译器警告
- [ ] 所有单元测试通过
- [ ] 所有集成测试通过
- [ ] 性能基准测试达标
- [ ] 无内存泄漏（已通过长时间浸泡测试验证）
- [ ] 构建体积在平台限制内
- [ ] 构建版本号正确设置并在源代码管理中打标签
### 代码质量
- [ ] TODO 数量: [N]（发布要求为零，或有记录的例外）
- [ ] FIXME 数量: [N]（发布要求为零）
- [ ] HACK 数量: [N]（每项必须有书面说明）
- [ ] 生产代码中无调试输出
- [ ] 无硬编码的开发/测试值
- [ ] 所有功能开关（Feature Flag）已设置为生产值
- [ ] 所有关键路径的错误处理已覆盖
- [ ] 崩溃报告已集成并验证
### 安全
- [ ] 源代码中无暴露的 API 密钥或凭据
- [ ] 存档数据已加密
- [ ] 网络通信已加密（TLS/DTLS）
- [ ] 反作弊措施已启用（如有多人模式）
- [ ] 所有服务器端点已做输入验证（如有多人模式）
- [ ] 隐私政策合规已验证
---
## 2. 内容就绪
### 资产
- [ ] 所有占位美术资产已替换为最终资产
- [ ] 所有占位音频已替换为最终音频
- [ ] 音频混音已完成并经音频总监审批
- [ ] 所有 VFX（视觉特效）已打磨并通过性能验证
- [ ] 无缺失或损坏的资产引用
- [ ] 资产命名规范已执行
### 文本与本地化
- [ ] 所有面向玩家的文本已完成校对
- [ ] 无硬编码字符串（全部已外部化以支持本地化）
- [ ] 所有支持语言的翻译已完成并验证
- [ ] 文本在所有语言中适配 UI（文本适配检查已完成）
- [ ] 所有支持语言的字体覆盖已验证
- [ ] 制作人员名单完整、准确且为最新
### 游戏内容
- [ ] 所有关卡/地图可从头到尾通关
- [ ] 教程流程已完成并通过新玩家测试
- [ ] 所有成就/奖杯已实现并测试
- [ ] 存档/读档在所有游戏状态下正常工作
- [ ] 难度设置已平衡并测试
- [ ] 游戏结尾/制作人员名单序列已完成
---
## 3. 质量保证
### 测试
- [ ] 完整回归测试套件已通过
- [ ] 零 S1（严重）级缺陷未关闭
- [ ] 零 S2（重大）级缺陷未关闭（或有记录的例外）
- [ ] 浸泡测试通过（连续运行 8 小时以上）
- [ ] 多人模式压力测试通过（如适用）
- [ ] 所有关键用户路径在每个平台上已测试
- [ ] 边界情况已测试（存储满、无网络、挂起/恢复）
### 平台认证
- [ ] PC: Steam/Epic/GOG SDK 要求已满足
- [ ] 主机: TRC/TCR/Lotcheck 提交材料已准备
- [ ] 移动端: App Store/Play Store 规范已合规
- [ ] 无障碍: 最低标准已满足（按键重映射、文本缩放、色盲模式）
- [ ] 年龄评级已获取（ESRB、PEGI 及地区性评级）
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.
- 1mo ago First seen · 223 lines · 0 tokens per session scan A 30a1783482c5
launch-checklist is a skill published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (361 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,334 tokens. 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 2026-09-03.
Other skills, from other repositories
launch-checklist
Launch readiness across every department: code, content, store, marketing, community, infrastructure, legal, go/no-go sign-offs.
release-checklist
Pre-release checklist — build verification, certification requirements, store metadata, launch readiness.
day-one-patch
Day-one launch patch — focused fix for known issues found after gold master. Mini-sprint with QA gate and rollback.
milestone-review
Milestone progress review — completeness, quality metrics, risk, go/no-go recommendation. At checkpoints or before a deadline.
team-combat
Orchestrate the combat team — game-designer, gameplay-programmer, ai-programmer, technical-artist, sound-designer, qa-tester — design through implement and validate.
team-live-ops
Orchestrate the live-ops team — live-ops-designer, economy-designer, analytics-engineer, community-manager, writer — for a season or live event.