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/zxpmail/reqforge/design-brief-buildernpx skills add zxpmail/ReqForge --skill design-brief-buildergit clone --depth 1 https://github.com/zxpmail/ReqForgeWrote 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/zxpmail/reqforge/design-brief-builder)<a href="https://agentmods.dev/skills/zxpmail/reqforge/design-brief-builder"><img src="https://agentmods.dev/badge/skills/zxpmail/reqforge/design-brief-builder.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 | $0.01887 |
| Opus 5 | $0.00000 | $0.00944 |
| Sonnet 5 | $0.00000 | $0.00377 |
| Haiku 4.5 | $0.00000 | $0.00189 |
Grade A, and why
design-brief-builder 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: design-brief-builder description: Used when the user wants to define a design style or visual direction, or says something vague like 'I want a premium/sleek/modern look'. Guides the user through a design interview to clarify visual preferences and outputs Design-Brief.md. After Brief is saved, MUST run Next Step Gate and recommend /design-maker — do not silently end the design phase. version: 1.2.1 updated: 2026-06-21 requires: []
[Task] Through a designer-interviews-client approach, guide the user to define the product's visual direction and output a well-structured Design-Brief.md that can be used both by design tools and by dev-builder for coding.
[Not For] - Generating actual mockups or design files -> use /design-maker instead - Writing code -> use /dev-builder instead - Defining product features -> use /product-spec-builder instead
[Dependency Check] Automatically executed as the first step when the Skill starts:
Required:
- Product-Spec.md → If missing, prompt the user to call /product-spec-builder first
Optional (fallback mode):
- Design tool MCP → If not connected, mark as "manual design mode". The Design Brief is still generated, and the user feeds it to the design tool on their own.
[First Principles]
Brief 前必读 references/first-principles.md
[Shared Discipline]
Karpathy 四原则 → ../_shared/karpathy-discipline.md(Web-First / 不猜)
[Output Style]
→ references/output-style.md(设计师访谈人格)
[File Structure]
design-brief-builder/ ├── SKILL.md ├── commands/design-brief-builder.md ├── templates/design-brief-template.md └── references/ ├── first-principles.md ├── output-style.md ├── workflow.md # 四阶段完整流程(必读) ├── interview-dimension-checklist.md ├── interview-strategies.md ├── sufficiency-judgment.md ├── design-discovery-questionnaire.md ├── visual-direction-presets.md ├── anti-ai-slop-checklist.md └── anti-rationalization.md ../_shared/
[Gotchas]
Open-ended questions instead of choices: Always give concrete options (Linear or Notion? Dark or light?).
Relying on memory for design trends: WebSearch before recommending.
Skipping accessibility: Contrast, hierarchy, touch targets belong in Brief.
Copying without thinking: Adapt reference products; don't clone blindly.
Missing refinement preference: Ask whether the user wants a single delivery or graduated tiers (layout → interaction → edge cases). Gradual refinement catches structural issues early when they're cheap to fix.
No-UI products: If Product-Spec has no UI Layout / API-only / library — do not run full interview or mockup Gate; see references/surface-routing.md.
[Anti-Rationalization Checklist]
→ references/anti-rationalization.md
遇 skipping interview / skipping WebSearch 等场景时读取。
[Output Artifacts]
- Design-Brief.md — Design specification document containing mood direction, color direction, information density, interaction style, etc.
- .forge/design-next-step.json — User's post-Brief choice (mockup / skip / planner-first); required before closing session when not invoking design-maker immediately
[Next Step Gate — HARD-GATE]
Brief 落盘后 MUST 先读 references/surface-routing.md:
- 无 UI(C 类) → 不跑 Gate;design-next-step.json + 推荐 /dev-planner
- 有 UI(A 类) → 执行 references/next-step-gate.md(三选一,推荐 mockup)
- 轻 CLI(B 类) → 简化 Gate,不推荐 design-maker
What ships with it
15 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.
- commands/design-brief-builder.md 726 B
- references/anti-ai-slop-checklist.md 3.1 KB
- references/anti-rationalization.md 1.2 KB
- references/design-discovery-questionnaire.md 1.4 KB
- references/first-principles.md 2.0 KB
- references/interview-dimension-checklist.md 2.7 KB
- references/interview-strategies.md 1.5 KB
- references/next-step-gate.md 4.5 KB
- references/output-style.md 2.0 KB
- references/sufficiency-judgment.md 1017 B
- references/surface-routing.md 3.0 KB
- references/visual-direction-presets.md 2.3 KB
- references/workflow.md 3.2 KB
- skill.json 1021 B
- templates/design-brief-template.md 8.6 KB
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 · 154 lines · 0 tokens per session scan A 32b6ae32bc62
design-brief-builder is a skill published in the GitHub repository zxpmail/ReqForge (18 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,887 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 skills, from other repositories
ui-mockup
Create UI mockups at three fidelity levels — ASCII wireframes for quick iteration, standalone HTML mockups for delivery with requirements, and live prototypes for interaction testing.
anti-slop-design
Category-aware design skill that builds distinctive, production-grade UIs. Brand-vs-product register, color strategy commitment, scene-based theme choice, palettes, font pairings, UX patterns, shadcn/token integration, empty-error-loading copy, secondary slop signals, multimodal design parity from mocks, and a…
3d-web-experiences
Build distinctive, performant, production-grade 3D on the web with Three.js, React Three Fiber, and WebGL. Use when the user asks to "build a 3D scene", "add a 3D hero/landing", "make a product viewer/configurator", mentions three.js / react-three-fiber / r3f / drei / webgl / shaders, or asks to make an existing 3D…
minimax-m3-multimodal-input
How to use MiniMax M3's native multimodal input (image, video) for grounded decisions in coding work. Covers reading attached images/frames, treating them as ground truth for visual claims, screenshot diffing, design parity from mockups, and routing visual evidence through reports and PRs. Load when the user attaches…
design-bootstrap
Bootstrap a design system from a Figma file using MCP tools. Extracts token variables, identifies components, creates the directory structure, and generates scaffolded foundation docs and a component inventory. Use when starting a new project with a Figma design file. Do not use when the design system docs already…
brand-visual-quality
品牌视觉资产生产质量 Owner — 当任务涉及品牌标志、图标、主题变体、微尺寸光学校正、单色母版、主资产谱系或视觉验收证据时使用;要求把几何一致性、变体关系和人工视觉结论绑定到可重放证据,避免只凭文件存在或单次截图宣告完成。.