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/ccdawn/codex-skills/briefbound-frontend-engineeringnpx skills add CCDawn/codex-skills --skill briefbound-frontend-engineeringgit clone --depth 1 https://github.com/CCDawn/codex-skillsWrote 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/ccdawn/codex-skills/briefbound-frontend-engineering)<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-frontend-engineering"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-frontend-engineering.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 5.1 | $0.00062 | $0.01397 |
| Opus 5 | $0.00031 | $0.00698 |
| Sonnet 5 | $0.00012 | $0.00279 |
| Haiku 4.5 | $0.00006 | $0.00140 |
Grade A, and why
briefbound-frontend-engineering 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 6d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Briefbound Frontend Engineering
目标
把已对齐的界面契约实现为符合项目约定、状态完整且可在浏览器验证的前端代码。优先复用现有组件、token 和数据契约,不重新发明视觉方向。
Briefbound task contract
- Context Boundary: 已对齐的用户结果、目标页面或组件、
APPROVED/PREVIEW_SKIPPED证据、现有设计系统与相邻实现、技术栈、数据契约和可运行环境。 - Output Contract: 最小生产实现、关键状态覆盖、响应式与无障碍处理,以及与声明相称的运行时证据。
- Allowed Action: 在 Briefbound Router 授权 surface 内修改前端组件、样式和必要测试;不改变无关后端协议、品牌方向或全局设计系统。
- Success Evidence: 目标测试、类型或构建检查,以及真实浏览器中的主路径、关键状态、目标视口和 console 检查。
- Stop Condition: 命中
PREVIEW_REQUIRED但缺少用户APPROVED、界面结果仍有高影响歧义、需要新的产品/视觉方向、数据契约不可用、修改越过授权边界,或运行环境阻止关键验收。 - Route Out: 产品或交互分叉转
briefbound-ui-design;跨消费者 token、主题或共享组件治理转briefbound-design-system;复杂外部组件决策转briefbound-feature-reuse-research;验证后的真实残留转briefbound-development-cleanup;阻塞回briefbound-router。
统一调用契约
- 只处理 Briefbound task contract 范围;不匹配时回
briefbound-router或最具体 owner。 - 用户可见内容默认中文,只报告关键实现、证据和剩余风险;代码、命令、路径、错误原文、API/协议、skill 名和枚举保留原样;Route Out 仅以 Briefbound task contract 为准,末行写
下一步建议: <一个具体动作>。
实施边界
- 只在进入时已有用户
APPROVED,或有依据的PREVIEW_SKIPPED,或收到包含该证据的独立 handoff 时主责。设计 owner 正在同一上下文执行“设计并实现”时不叠加本 skill。 FAST_PATH:既有模式下的明确小修,记录PREVIEW_SKIPPED依据后直接实现;COMPACT_FLOW必须消费已批准预览/设计。- 出现跨页面信息架构、品牌方向或设计系统治理时停止扩张,转对应 owner。
预览证据闸门
- 新页面或未确认的布局、交互、视觉、响应式、跨组件结果:
PREVIEW_REQUIRED,转设计 owner 生成隔离网页。 - 明确小修或既有模式机械改动:记录
PREVIEW_SKIPPED;用户已明确批准具体预览或设计稿:记录APPROVED对象与边界。 - 截图、测试、UI Review 或一般“继续实现”不能替代对具体预览的用户批准;实现偏离时重新预览。
条件操作指南
先用依赖、样式入口和组件配置确认技术栈:
- 使用 Tailwind CSS:实施前读取 references/tailwind.md。
- 使用 shadcn/ui 或存在
components.json:实施前读取 references/shadcn.md;两者命中则都读取。 - 指南不新增 owner、依赖、迁移权限或预览豁免。版本、项目定制或 CLI 冲突以项目事实和官方当前文档为准;解决方案若改变依赖、主题、组件 API、兼容性或批准结果,停止受影响写入并与用户讨论。
生产实现
- 读取 owning component、相邻页面、组件库、token、数据流和相关测试,确认项目真实模式。
- 选择满足契约的最小结构;组件只在形成稳定复用边界或显著降低复杂度时拆分。
- 覆盖主路径及相关的 loading、empty、error、disabled、success、权限和长内容状态,不凭空增加无关状态。
- 使用语义元素和原生控件,保证标签、键盘路径、焦点、非颜色提示和必要 ARIA;保留现有无障碍基线。
- 使用现有响应式策略和 token,稳定固定格式元素的尺寸,检查换行、溢出、窄屏降级和动态内容。
- 保持服务端/客户端边界、请求缓存、状态所有权和渲染成本符合当前框架约定;性能优化必须针对可观察问题。
What ships with it
3 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.
- 6d ago First seen · 67 lines · 62 tokens per session scan A be9b963471bc
briefbound-frontend-engineering is a skill published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 24d ago), licensed MIT. It adds 62 tokens to every session and 1,397 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 2026-08-31.
Other skills, from other repositories
domestic-stack
写 uniapp / 微信小程序 / SpringBoot 代码时使用。贴合国内主流技术栈的实战规范。.
frontend-best-practices
写 React/Vue 前端代码时使用。组件、状态、性能、可访问性的实战规范。.
personal-page-polish
Polish an existing single-file personal page after the user asks for a clearer, more readable design while preserving its content and no-build setup.
pm-fe-assistant
面向产品经理(非开发人员)的前端改动协作助手。当用户是 PM、设计师、运营等非技术角色, 通过自然语言描述想要修改的前端界面(文案、样式、按钮、页面布局等)时触发此技能。 助手会用通俗语言沟通、绝不展示代码、绝不进行任何 Git 分支操作,并按"理解需求 → 告知方案 → 执行修改 → 汇报结果"的流程协作。 典型触发场景:用户说"把按钮改成蓝色"、"修改登录页文案"、"调整一下首页布局"等界面改动需求,且语气明显是非技术人员。.
fe-performance
前端性能优化技能包,涵盖懒加载与代码分割、图片优化(WebP化)、Service Worker 缓存、首屏性能优化、Core Web Vitals 治理、Bundle 分析与瘦身。 当需要优化前端加载速度、减小包体积、改善用户体验指标、配置缓存策略、或进行性能诊断时触发此技能。 支持 Angular、Vue、React、原生 JS、Node.js 技术栈。.
fe-architecture
前端架构演进技能包,涵盖框架大版本升级、微前端架构、TypeScript 迁移、CSS 架构迁移。 当需要升级框架版本(Vue2→3、React Class→Hooks、Angular 升级)、引入微前端、迁移到 TypeScript、或重构 CSS 架构时触发此技能。 支持 Angular、Vue、React、原生 JS、Node.js 技术栈。.