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 CCDawn/codex-skills --skill briefbound-visual-designgit 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-visual-design)<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-visual-design"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-visual-design.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 | $0.00069 | $0.01647 |
| Opus 5 | $0.00034 | $0.00823 |
| Sonnet 5 | $0.00014 | $0.00329 |
| Haiku 4.5 | $0.00007 | $0.00165 |
Grade A, and why
briefbound-visual-design 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Briefbound Visual Design
目标
把产品目的、受众和内容转成有辨识度且可实施的视觉语言。主动推断合适方向并给出推荐,不让用户先掌握设计术语;视觉强度服务任务,不以“独特”为理由牺牲可读性、性能或产品效率。
Briefbound task contract
- Context Boundary: 产品/品牌、受众、使用场景、内容与资产、目标 surface、现有视觉基线、技术和无障碍约束。
- Output Contract: 一个推荐视觉方向;命中预览闸门时先交付隔离预览 URL、代表截图、覆盖状态和用户批准状态。
- Allowed Action: 分析现有产品和资产、形成视觉契约;
PREVIEW_REQUIRED时只写隔离预览,收到用户APPROVED后才调整正式视觉实现;不改变无关信息架构、业务行为或全局设计系统。 - Success Evidence: 预览阶段为可访问网页、桌面/移动截图、关键内容和降级边界;正式阶段为关键 surface 的真实渲染、目标视口、内容压力、无障碍和性能检查。
- Stop Condition:
WAITING_USER_REVIEW、用户要求REVISE/ABANDON、品牌资产或产品定位存在高影响冲突、所需素材不可获得,或实施越过授权范围。 - Route Out: 信息架构或交互模型成为主要未知量时转
briefbound-ui-design;只交付视觉方案或需要独立实施 handoff 时转briefbound-frontend-engineering;系统 token/主题治理转briefbound-design-system;现有结果审查转briefbound-ui-review;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;默认输出一个有依据的推荐方向,而不是风格名称堆砌。低影响细节由 agent 自行决策。
- 用户可见内容默认中文,只说明会改变实现的视觉决策、证据和取舍;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>。
语境判断
- SaaS、CRM、后台、编辑器和运营工具:优先扫描、比较、密度、稳定层级和重复操作效率,辨识度来自精确而非装饰。
- 品牌、产品、作品集、活动和展示页面:品牌或对象必须成为首屏信号,可用图像、字体、构图和节奏建立记忆点。
- 游戏和创意体验:可以更具表现力,但交互反馈、可读性和性能仍是硬边界。
- 已有产品:先读取品牌资产、相邻页面、token 和组件;除非用户明确要求重塑,不引入不兼容的平行视觉语言。
用户只说“更好看、现代一点、有高级感”时,结合产品类型和现有证据直接推荐;只有方向会显著改变布局、素材、品牌感知或成本时才给少量备选。
单 owner 贯穿
用户要求视觉设计并实现时,本 owner 贯穿隔离预览、用户批准后的正式落地和浏览器验收,不再加载 UI Design 或 Frontend Engineering。WAITING_USER_REVIEW 是必须暂停的自然闸门。普通响应式和无障碍约束作为实现边界;只有核心信息架构/交互或跨消费者契约需要重定时才切换 owner。
预览批准闸门
品牌表达、字体、色彩、构图、图像、图标或动效方向尚未获用户确认时标记 PREVIEW_REQUIRED;明确小修、既有语言机械应用或已有批准证据可标记 PREVIEW_SKIPPED。
- 优先在项目已有 preview/example surface 或任务级临时目录中复用真实组件和内容结构,不先修改正式 route、生产组件、共享 token 或真实写接口。
- 提供可访问的本地网页、主要桌面/移动截图、真实代表文案、关键状态、资源/动效降级和模拟边界;应用不可运行时才降级为独立 HTML/CSS/JS。
- 交付后进入
WAITING_USER_REVIEW,只接受用户APPROVED / REVISE <反馈> / ABANDON状态变化。UI Review 的通过建议不能代替用户批准。 REVISE只改预览;APPROVED后连续实施已确认方向;ABANDON不写正式 surface。
视觉契约
- 概念:用一句可执行原则说明视觉如何支持产品,而不是只给风格标签。
- 字体:定义 display/body/mono 的角色、层级、字重、行高和长文本行为;字体选择兼顾语言覆盖、加载和许可。
- 色彩:定义背景、surface、文本、边框、accent 和状态语义;保证对比度且不只靠颜色传达状态。
- 构图:根据内容优先级选择网格、密度、留白、对齐和节奏;避免默认 hero、均匀卡片阵列和无内容依据的装饰。
- 图像与图标:优先展示真实产品、对象、地点、人物或状态;图标来自项目已有库,核心图片必须可检查而非纯氛围填充。
- 动效:只设计能解释层级、状态变化、空间关系或品牌时刻的运动;明确 reduced-motion 和低性能降级。
- 细节:圆角、阴影、边框和背景效果形成有限体系;按语境判断,不建立脱离产品的永久禁用清单。
What ships with it
1 file 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 · 69 lines · 69 tokens per session scan A 1db1614179c7
briefbound-visual-design is a skill published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 24d ago), licensed MIT. It adds 69 tokens to every session and 1,647 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
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
A front-end change assistant for product managers, designers, and other non-developers. Front-end work changes what users see and interact with in a web interface.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
ss-studio
Turn a product brief and optional references into three distinct creative directions, a human-selected StyleSeed interaction plan, generated image/video asset jobs, a working UI prototype, and a verified prototype-first showcase reel. Use for client concepts, app interaction exploration, trendy but coherent UI…