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 commands/shangyankeji/super-dev/super-dev-seeaigit clone --depth 1 https://github.com/shangyankeji/super-devWrote 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/commands/shangyankeji/super-dev/super-dev-seeai)<a href="https://agentmods.dev/commands/shangyankeji/super-dev/super-dev-seeai"><img src="https://agentmods.dev/badge/commands/shangyankeji/super-dev/super-dev-seeai.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01700 |
| Opus 5 | $0.00000 | $0.00850 |
| Sonnet 5 | $0.00000 | $0.00340 |
| Haiku 4.5 | $0.00000 | $0.00170 |
Grade A, and why
super-dev-seeai 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 5d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/super-dev-seeai (claude-code)
在当前项目触发 Super Dev SEEAI 赛事极速版。
输入
- 需求描述:
$ARGUMENTS - 如果未提供参数，先要求用户补全需求后再执行。
SEEAI 定位
- 面向比赛或超短时间盒交付，例如精美官网、小游戏、展示型工具或单功能 demo。
- 保留 research / 三文档 / docs confirm / spec，但全部压缩成比赛快版。
- Spec 确认后直接进入前后端一体化快速开发，不再拆 preview confirm。
- 若宿主会更新
.super-dev/workflow-state.json，必须显式写入flow_variant = seeai，确保恢复和继续提示仍然回到 SEEAI 模式。
半小时时间盒
- 0-4 分钟：fast research，锁定评审场景、竞品风格和作品 wow 点。
- 4-8 分钟：输出 compact research / PRD / architecture / UIUX。
- 8-10 分钟：等用户确认文档和方向，不展开长讨论。
- 10-12 分钟：生成 compact Spec / tasks，只保留最小可交付路径。
- 12-27 分钟：一体化 full-stack sprint，先把主展示面做成，再补最小必要后端/数据层。
- 27-30 分钟：polish、demo 路径检查、讲解词和亮点总结。
首轮输出模板
作品类型：官网类 / 小游戏类 / 工具类，三选一。评委 wow 点：本次作品最值得被记住的一个亮点。P0 主路径：半小时内必须真实跑通的一条演示路径。主动放弃项：本轮明确不做的部分，避免范围失控。关键假设：只有在用户没说清时才写，最多 1 到 2 条。- 如果需求不缺关键输入，不要长时间澄清，直接进入 fast research。
范围裁剪规则
- P0：必须完成一个可演示主路径，首页/主玩法/主工具流程必须能跑。
- P1：补一个明显 wow 点，例如强主视觉、动画、排行榜、分享页、彩蛋交互。
- P2：只有在剩余时间充足时才加扩展能力，例如真数据库、登录、复杂后台。
比赛短文档模板
research.md：题目理解、评委 wow 点、参考风格、主动放弃项。prd.md：P0 主路径、P1 wow 点、P2 可选项、非目标。architecture.md：页面/玩法主循环、技术栈、最小后端、降级方案。uiux.md：视觉关键词、主 KV、页面骨架、关键动效。spec：只保留一个 sprint 清单，按P0 -> P1 -> polish排序。
推荐标题骨架
research.md：# 题目理解# 参考风格# Wow 点# 主动放弃项prd.md：# 作品目标# P0 主路径# P1 Wow 点# P2 可选项# 非目标architecture.md：# 主循环# 技术栈# 数据流# 最小后端# 降级方案uiux.md：# 视觉方向# 首屏/主界面# 关键交互# 动效重点# 设计 Tokenspec：# Sprint Checklist下只列P0、P1、Polish
作品类型决策
-
官网类题：优先主视觉、品牌叙事、首屏信息密度和滚动节奏。 默认技术栈：React/Vite 或 Next.js + Tailwind + Framer Motion。 默认 sprint：Hero/首屏 -> 亮点区/叙事 -> CTA/滚动动效 -> 最终 polish。
-
小游戏类题：优先核心玩法循环、反馈感、积分/胜负和再次游玩闭环。 默认技术栈：HTML Canvas + Vanilla JS；复杂玩法再上 Phaser。 默认 sprint：主循环可玩 -> 积分/胜负反馈 -> 特效/音效 -> 复玩和 polish。
-
工具类题：优先一个高价值主流程、输入输出清晰、结果页直观。
默认技术栈：React + Vite + Tailwind；必要时补最小 Express/Fastify 后端。 默认 sprint：输入页/主流程 -> 结果页 -> 分享/导出等演示加分项 -> 最终 polish。
题型识别提示
- 提到品牌、官网、落地页、活动宣传、首屏，默认按官网类处理。
- 提到玩法、得分、胜负、闯关、点击反馈，默认按小游戏类处理。
- 提到生成、分析、查询、输入输出、结果页、效率提升，默认按工具类处理。
- 如果需求跨多类，先选最容易让评委记住的那一类做主轴。
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.
- 5d ago First seen · 99 lines · 0 tokens per session scan A e2a72e1242cf
super-dev-seeai is a command published in the GitHub repository shangyankeji/super-dev (274 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,700 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 2026-08-30.
Other commands, from other repositories
learn
Learn Claude Code best practices and capture lessons into persistent memory.
list
Display all learnings stored in the pro-workflow database.
cost-tracker
Track session costs, understand token spend, and get optimization tips.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
prd
Create, audit, or derive a Product Requirements Document. Use "derive" for satellite repos in multi-repo projects.
setup
Initialize Coco in the current project. Creates .coco/ directory, config, git hooks, and permissions. Use "reset" to force reconfiguration, or "migrate" to reconcile an existing config against the current defaults.