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 lync-cyber/CataForge --skill design-grillgit clone --depth 1 https://github.com/lync-cyber/CataForgeWrote 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/lync-cyber/cataforge/design-grill)<a href="https://agentmods.dev/skills/lync-cyber/cataforge/design-grill"><img src="https://agentmods.dev/badge/skills/lync-cyber/cataforge/design-grill/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/lync-cyber/cataforge/design-grill"><img src="https://agentmods.dev/badge/skills/lync-cyber/cataforge/design-grill.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 | $0.00083 | $0.02936 |
| Opus 5 | $0.00042 | $0.01468 |
| Sonnet 5 | $0.00017 | $0.00587 |
| Haiku 4.5 | $0.00008 | $0.00294 |
Grade A, and why
design-grill 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 9d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
设计深度澄清 (design-grill)
启用门
本策略默认关闭，启用与否始终由用户显式决定；自动建议不等于启用，不得仅因「信息不完整」或「需要澄清」自行进入。启用通道按序核实：
- 用户显式要求 — 「开启 Grill」「深挖这个 PRD/架构/UI」「grill me」等，即时启用。
- 项目偏好 — 项目指令文件 §全局约定
深度澄清(Grill)为always时，阶段 skill 进入发散澄清前直接启用；为never时不询问，仅保留通道 1。 - 阶段入口一次询问 — 无项目偏好记录且执行模式非 agile-prototype 时，阶段 skill 进入发散澄清前必须用一次选择题询问：本阶段开启 / 本阶段跳过 / 本项目一律开启 / 本项目不再询问；后两项由 orchestrator 写入 §全局约定
深度澄清(Grill): always|never。询问是协议动作，用户选择「开启」才构成显式同意。
未获显式同意时立即返回原阶段，以 research user-interview 做普通澄清。
scope 取 prd | arch | ui，限当前阶段或用户指定范围；Grill 是阶段内策略，不改变 phase、执行模式或长期项目偏好。完成或退出后把总结交回 req-analysis、arc-design 或 ui-design，恢复原阶段流程。
运行纪律
启用即进入深挖模式：沿决策依赖树逐分支穷尽追问，直到每个分支被解决（用户确认、明确委托推荐或显式跳过）且用户确认共同理解。事实与决策分离——能从环境核实的事实自查不问，需要拍板的决策无论大小都归用户，不得以「影响小」「有合理默认」为由静默替用户决定。退出与暂停的决定权在用户；本策略不自行宣布收敛、不主动劝退。
能力边界
- 能做: 对 PRD、Architecture、UI 设计构建决策依赖树，核验本地事实，给出有依据的推荐，逐分支收敛并输出阶段可消费的可追溯总结
- 不做: 代替阶段 Skill 产出完整 PRD、Arch 或 UI-SPEC，代替用户作最终业务或审美决定，或创建平行的长期决策事实源
- 不做: 未启用时改变正常阶段流程，或把未获同意的普通澄清升级为持续访谈
输入规范
- scope 与需深度澄清的范围
- 当前会话已确认的用户意图与选择
- 当前执行模式、阶段状态，以及已有阶段文档、research-note、代码、配置和设计资产
输出规范
- 会话内工作台账: 决策依赖、事实来源、推荐、用户反馈、假设、未决项与受影响分支
- 每个阶段的一次连续 Grill 会话最多维护一份 research-note，作为过程证据；不按问题创建文件
- 完成、暂停或停止时输出共同理解总结，供当前阶段 authoring 写入终态权威文档
执行流程
Step 1: 模式与上游边界
standard: PRD、Arch、UI 可分别运行并保持独立台账；仅 Arch 可筛选 ADR 候选；UI 在 Design-Tool Capability Gate 通过后才可读取 Penpotagile-lite: 只收敛能落入 lite 产物边界的问题；planning 中先prd后arch，UI 仅在显式启用 UI 阶段时运行；Arch-lite 不创建 ADR，UI-SPEC-lite 不扩张为完整页面、路由或响应式规格。核心决定无法在 lite 边界表达时建议切换 standard，不自动切换agile-prototype: 不自动建议 Grill，阶段入口也不询问；用户显式要求时只对 brief 中的产品、技术或 UI 意图做受限澄清。发现复杂架构、多页面、长期演进或高风险决策时建议升级模式，不自动创建完整阶段文档或 ADR- 问题越过当前 scope 时停止该分支：产品功能、业务流程、权限或交互语义交回 PRD；API、数据、系统能力或实现边界交回 Arch
Step 2: 建立本地事实包
按本地事实优先顺序查明问题，能确定的内容不得再询问用户：
- 当前会话中用户已明确表达的事实和选择
- 项目指令文件、framework 配置、当前执行模式和阶段状态
cataforge context read返回的 PRD、Arch、UI-SPEC 与 research 内容- 现有代码、依赖清单、配置、API、数据结构、样式 Token 和设计资产
design_tool=penpot且 Capability Gate 已通过时，经 penpot-bridgeread获取结构、样式、Token 实值；必要时export_shape做视觉 grounding- 已有 research-note
- 必要的官方外部资料；技术版本与生命周期委托 tech-eval 核实
- 仍无法核实的推断，显式标为
[ASSUMPTION]
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.
- 9d ago First seen · 161 lines · 83 tokens per session scan A 7cd8facfb8ab
design-grill is a skill published in the GitHub repository lync-cyber/CataForge (129 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 2,936 once invoked, about $0.0004 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 2026-08-30.
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 $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.