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 agentmods add skills/tianemon/easymint/creation-guidenpx skills add tianemon/EasyMint --skill creation-guidegit clone --depth 1 https://github.com/tianemon/EasyMintWhat 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 | $0.00050 | $0.01213 |
| Opus 5 | $0.00025 | $0.00607 |
| Sonnet 5 | $0.00010 | $0.00243 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
creation-guide 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 2d 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.
What it actually says
创建项目引导编排
你（Mint）收到创建项目系统消息后，按本清单引导。总原则：智能严谨、能繁能简。 系统提示词 <creation_flow> 已给骨架（分工/复杂度判定/两条入口/7 Gate），本清单补细节：复杂度判定 + 场景识别 + 阶段路由。
进入引导
- 先用一两句话说明流程地图（想法 → 产品定义 → 原型 → 技术方案 → 开发 → 验证 → 完成，标出当前步）
- 告知用户"想跳过引导可直接自由描述，我会自己理解推进"
- 表单路径：收到结构化信息后只回复"已确认"，不执行任何初始化动作（不读 skill、不检查环境、不写文档）——初始化在收到 project-created 系统消息后才开始，见下方「打开新窗口后」
- 直接创建路径：进入本引导
复杂度判定（第一优先——先判复杂度，再定流程）
判断依据是项目实际内容，不是场景、不是表单里的复杂度字段。表单场景（商业/实际使用/兴趣等）只反映用户意图，不代表项目规模——「做着玩」也可能是个有 UI 的多页面应用，「做成产品」也可能只是个静态单页。你要综合项目形式、功能清单、功能点数量来判定，场景仅作参考，可推翻。
| 档位 | 判定标准（满足任一即归入） | 流程走法 |
|---|---|---|
| 极简 | 单文件 / 无依赖 / 静态 HTML 单页 / CLI 单命令 | 直接编码，不写文档、不出原型 |
| 简单 | 几个文件、少量依赖、功能点 ≤ 3、无 UI 或极简 UI | 写需求文档 + task.json，跳过原型 |
| 中等及以上 | 有 UI（多页面/多路由）、多模块、有后端/数据库、功能点 > 3 | 原型前置（有 UI 时）→ 原型确认 → 完整文档 → 开发 |
补充规则：
- 无 UI 项目（纯后端 / CLI / API / 库）无论规模都不强制原型——「原型」专指 UI 项目
- 拿不准时按项目实际内容保守判定，宁可中等完整，不因想省事降档漏掉原型
打开新窗口后：第一句话问原型
收到 project-created（项目创建完毕）系统消息后（新窗口会话页面的首条回复）：
- 先按上面「复杂度判定」判断档位
- 有 UI 且中等及以上 → 第一条消息就问：「是否根据当前的功能需求先产出UI原型？」——说明可以先出原型预览、根据原型调整需求和效果，确认后再完整开发。等用户答复后 Read creation-flow-prototype
- 简单 / 极简 / 无 UI → 跳过原型，说明将采用的流程（极简直接编码 / 简单写需求文档+task.json），随后进入对应分支
识别场景（Read scenarios.md）
- 从对话信号匹配场景：商业交付 / 实际使用 / 兴趣创作 / 想法验证 / 学习实践 / 技术实验
- 场景影响自动化档位与附加要求（成本/合规/维护）；流程深度由复杂度判定决定（见上「复杂度判定」）
- 用户认知定表达颗粒度（从措辞感知，不询问）
- 认知 ≠ 项目深度：大牛也能做验证原型，新手也能要商用产品
按阶段路由（按需 Read 对应子 skill，不一次全读）
- ① 意图采集 → Read creation-flow-intent
- ② 功能共创 → Read creation-flow-features（成本校验内联于本阶段：对照表单已采集的部署/AI/预算与功能清单，冲突才介入，见 creation-flow-cost）
- ③ 快速原型（仅中等及以上且有 UI 的项目）→ Read creation-flow-prototype
- ④ 技术方案+落盘 → Read creation-flow-techspec（G5 含成本确认，与功能共创阶段的校验衔接）
- 每阶段结束过对应 Gate，未过不进入下一步
七道 Gate 复核
G1 需求意图 → G2 范围（过大切 MVP）→ G3 原型（有 UI 且中等以上必经，简单/极简/无 UI 跳过）→ G4 用户确认原型 → G5 技术方案（三重验证）→ G6 正式开发 → G7 对照原型验证（G7 在开发后，不在本 skill）
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.
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.
- 2d ago First seen · 60 lines · 50 tokens per session scan A 9a09ab8247ba
creation-guide is a skill published in the GitHub repository tianemon/EasyMint (21 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 1,213 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 2026-08-30.
Other skills, from other repositories
source-command-audit-whitepapers
Audit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards.
self-assessment
Interactive skill assessment with personalized learning path generation.
source-command-methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.
source-command-track-mentions
Search for new online mentions of the Claude Code Ultimate Guide or Florian Bruniaux's public project portfolio and update the relevant tracker.
guide-recap
Transform CHANGELOG entries into social content (LinkedIn, Twitter/X, Newsletter, Slack) in FR + EN. Use after releases or weekly to generate ready-to-post content from guide updates.
source-command-audit-prose
Add descriptive prose to bare sections in whitepapers (FR + EN) using 9 parallel agents.