Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.
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 zts212653/clowder-ai --skill console-devgit clone --depth 1 https://github.com/zts212653/clowder-aiWrote 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/zts212653/clowder-ai/console-dev)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/console-dev"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/console-dev/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/zts212653/clowder-ai/console-dev"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/console-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00114 | $0.01387 |
| Opus 5.5 | $0.00046 | $0.00555 |
| Sonnet 5.5 | $0.00023 | $0.00277 |
| Haiku 4.5 | $0.00011 | $0.00139 |
Grade A, and why
console-dev 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 today.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Console-Dev
Console 前端开发先定入口和状态，再写组件。这个 skill 不替代 tdd / quality-gate，它补齐前端特有的产品路径、设计 token、交互状态和视觉证明。
方向已确认且符合 docs/SOP.md 产品快车道时，下面四项由同一作者随实现自检，不是四轮 A2A 或新审批：第一小时先争取挂上真实入口，自己走关键交互、对照原约定并贴截图，再跑受影响检查；不等 review/full 才首次打开。复用已成立的设计证据，只验证本次变化涉及的状态；用户不承担首轮 QA。
Gate 1: Product Gate
先回答：用户从哪里进入？这个能力属于哪个层级？
| 层级 | 用途 | 门槛 |
|---|---|---|
| L1 Activity Bar | 每天使用的核心入口 | 极慎重，通常需要 operator 决策 |
L2 /settings |
管理/配置 UI | 默认放这里 |
| L3 settings 子 tab | 只读、分析、运维子视图 | 自助选择合适分区 |
| L4 独立 route | 需要专属布局/流程的体验 | 先讨论入口理由 |
涉及状态的 UI 需考虑 loading / empty / partial / full / error、身份权限和 desktop / mobile 中实际相关的状态。 矩阵用于发现独有风险，不要求全组合各跑完整旅程；测试层级与成本按测试规范选择。
Gate 2: Design-System Gate
首启、多步任务或跨界面交接的理解顺序仍不清楚时，按交互叙事核对用户问题、可见结果、真实推进条件与返回位置；已有明确路径的实现/点改不新增设计关卡。
新增或实质改变 UI/UX，先按 feat-lifecycle 的 Design Gate 确认用户任务与体验方向，并使用 ../.cat-cafe-shared-refs/design-in-context-checklist.md：查看同类产品及operator给的参考，保留成立的操作与空间关系，在真实宿主和可信内容态里验证主对象、主动作与状态反馈。需要共创时拿具体稿和推荐及时校准；不能把“使用了 token”当作设计通过。
新代码 token first：颜色、边框、语义状态优先复用现有 CSS variables 和组件 primitive。旧代码迁移可以渐进，但 debt 清单只能减少，不能因为新功能扩大豁免。
Gate 3: Implementation Gate
| 规则 | 处置 |
|---|---|
| 200 行 | 触发拆分审查 |
| 350 行 | 默认必须拆，除非结构理由写清楚 |
| 敏感值 | 展示值和提交值分离；redacted placeholder 不能回写 |
| settings migration | 写清 Source Behavior / Must Preserve Home Behavior / Decision / Proof |
拆分方向优先是视觉独立 sub-component，不是把小工具函数切碎。 行数本身不构成产品 P1，不为这些阈值另写数行 UT。
Gate 4: Verification Gate
必须给证据：
- Golden path 走通
- 以同一用户任务对照参考与实际运行页面；看着对象操作、输入和提交的连续体验成立，不能只凭控件齐全或无横向溢出判通过
- 至少覆盖一个非 happy path 状态
- 改共享 primitive 时抽样兄弟页面
- modal 检查 footer、滚动容器、sticky action、ESC/关闭行为
- 暗色/移动端如果会被影响，必须抽样
- 对照界面错题本，只看本次改动碰到的条目（家里真犯过的反例和自查法；规则正文仍以 DESIGN.md 和在地设计检查单为准）
Common Mistakes
| 错误 | 后果 | 修复 |
|---|---|---|
| 先写组件再找入口 | L1 导航膨胀，后续难回滚 | 先过 Product Gate |
| 把 source PR 整块搬进 settings | 带入 service/auth/chat 红区 | manual-port 到最小 source intent |
| 用 hardcoded 视觉值补样式 | 设计体系继续分叉 | 先查 token / primitive |
| 展示用 redacted 值进入 draft | 覆盖真实 secret | display value 和 submit payload 分层 |
| 只跑类型检查 | UI 状态、滚动、modal 回归漏检 | focused test + 浏览器 proof |
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.
- yesterday Changed 6aea377f1d4d
- 7d ago Changed · +3 lines ecaec6c62ce3
- 14d ago Changed · +2 lines 547d9fe0541e
- 1mo ago Changed · +5 lines 1a8081032ec7
- 1mo ago First seen · 74 lines · 114 tokens per session scan A 5a0d419e9d7d
console-dev is a skill published in the GitHub repository zts212653/clowder-ai (3,471 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 1,387 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.