project-stage-detect

project-stage-detect is a skill for Claude Code from pixel-cellar/Claude-Code-Game-Studios. It costs 30 tokens per session (1,768 once invoked), scanned A, original, MIT.

A project-stage detector that scans design documents, source code, production plans, prototypes, architecture records, and tests to estimate where a game project is in development.

In plain words
What is it for?
Use it when taking over a project, joining a codebase, checking milestone readiness, or deciding which development step should come next.
Why use it?
It answers “where are we now?” from the files already present and points out missing documents or development artifacts.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it when taking over a project, joining a codebase, checking milestone readiness, or deciding which development step should come next.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pixel-cellar/claude-code-game-studios/project-stage-detect
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.

Any agent
npx skills add pixel-cellar/Claude-Code-Game-Studios --skill project-stage-detect
Clone the repo
git clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-Studios

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 project-stage-detect

README.md
[![agentmods](https://agentmods.dev/badge/skills/pixel-cellar/claude-code-game-studios/project-stage-detect/github.svg)](https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/project-stage-detect)
Your own site
<a href="https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/project-stage-detect"><img src="https://agentmods.dev/badge/skills/pixel-cellar/claude-code-game-studios/project-stage-detect/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 project-stage-detect

Your own site · 80×15
<a href="https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/project-stage-detect"><img src="https://agentmods.dev/badge/skills/pixel-cellar/claude-code-game-studios/project-stage-detect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,768 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.01768
Opus 5.5 $0.00012 $0.00707
Sonnet 5.5 $0.00006 $0.00354
Haiku 4.5 $0.00003 $0.00177

Measured 1mo ago against content hash 8d64a4ba26d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-stage-detect 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.

.claude/skills/project-stage-detect/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

项目阶段检测

本技能扫描你的项目以确定其当前开发阶段、工件的完整性以及需要关注的缺失项。特别适用于以下场景:

  • 接手一个现有项目
  • 入职一个代码库
  • 里程碑前检查缺失项
  • 了解 "我们现在在哪里?"

工作流

1. 扫描关键目录

分析项目结构和内容:

设计文档(design/):

  • 统计 design/gdd/*.md 中的 GDD 文件数
  • 检查 game-concept.md、game-pillars.md、systems-index.md
  • 如果 systems-index.md 存在,统计总系统数与已设计系统数
  • 分析完整性(概述、详细设计、边缘情况等)
  • 统计 design/narrative/ 中的叙事文档数
  • 统计 design/levels/ 中的关卡设计数

源代码(src/):

  • 统计源文件数(与语言无关)
  • 识别主要系统(包含 5 个以上文件的目录)
  • 检查 core/、gameplay/、ai/、networking/、ui/ 目录
  • 估算代码行数(大致规模)

生产工件(production/):

  • 检查是否有活跃的 Sprint 计划
  • 查找里程碑定义
  • 查找路线图文档

原型(prototypes/):

  • 统计原型目录数
  • 检查是否有 README(已文档化 vs 未文档化)
  • 评估原型是已归档还是活跃的

架构文档(docs/architecture/):

  • 统计 ADR (Architecture Decision Record,架构决策记录) 数量
  • 检查是否有概述/索引文档

测试(tests/):

  • 统计测试文件数
  • 估算测试覆盖率(粗略启发式)

2. 分类项目阶段

根据扫描的工件确定阶段。先检查 production/stage.txt — 如果存在,使用其值(来自 /gate-check 的显式覆盖)。否则, 使用以下启发式规则自动检测(从最高阶段向前检查):

阶段 指标
概念 无游戏概念文档,处于头脑风暴阶段
系统设计 游戏概念存在,系统索引缺失或不完整
技术搭建 系统索引存在,引擎未配置
预制作 引擎已配置,src/ 不到 10 个源文件
制作 src/ 有 10 个以上源文件,活跃开发中
打磨 仅限显式设置(由 /gate-check 制作 -> 打磨关卡设置)
发布 仅限显式设置(由 /gate-check 打磨 -> 发布关卡设置)

3. 协作式缺失项识别

不要只是列出缺失的文件。而是提出澄清问题:

  • "我看到战斗代码(src/gameplay/combat/)但没有 design/gdd/combat-system.md。这是先做的原型,还是应该进行逆向文档化?"
  • "你有 15 个 ADR 但没有架构概述。需要我创建一个来帮助新贡献者吗?"
  • "production/ 中没有 Sprint 计划。你在其他地方跟踪工作吗(Jira、Trello 等)?"
  • "我发现有游戏概念但没有系统索引。你是否已经将概念拆解为各个独立系统,还是需要我运行 /map-systems?"
  • "原型目录有 3 个项目没有 README。这些是实验,还是需要文档化?"

4. 生成阶段报告

使用模板:.claude/docs/templates/project-stage-report.md

报告结构:

# 项目阶段分析

**日期**:[日期]
**阶段**:[概念/系统设计/技术搭建/预制作/制作/打磨/发布]

## 完整性概览
- 设计:[X%]([N] 个文档,[缺失项])
- 代码:[X%]([N] 个文件,[系统])
- 架构:[X%]([N] 个 ADR,[缺失项])
- 生产管理:[X%]([状态])
- 测试:[X%]([覆盖率估算])

## 识别的缺失项
1. [缺失项描述 + 澄清问题]
2. [缺失项描述 + 澄清问题]

## 推荐后续步骤
[根据阶段和角色按优先级排列的列表]

5. 角色过滤的推荐(可选)

如果用户提供了角色参数(例如 /project-stage-detect programmer):

程序员:

  • 专注于架构文档、测试覆盖率、缺失的 ADR
  • 代码与文档的差距

Read the full file on GitHub · 192 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. 1mo ago First seen · 192 lines · 30 tokens per session scan A 8d64a4ba26d0

Subscribe to this mod's changes

project-stage-detect is a skill published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (361 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 1,768 once invoked, about $0.0001 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 2026-09-03.