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 Gnomeshgh0714/mbb-deck --skill archivegit clone --depth 1 https://github.com/Gnomeshgh0714/mbb-deckWrote 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/gnomeshgh0714/mbb-deck/archive)<a href="https://agentmods.dev/skills/gnomeshgh0714/mbb-deck/archive"><img src="https://agentmods.dev/badge/skills/gnomeshgh0714/mbb-deck/archive/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/gnomeshgh0714/mbb-deck/archive"><img src="https://agentmods.dev/badge/skills/gnomeshgh0714/mbb-deck/archive.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00179 | $0.03243 |
| Opus 5.5 | $0.00072 | $0.01297 |
| Sonnet 5.5 | $0.00036 | $0.00649 |
| Haiku 4.5 | $0.00018 | $0.00324 |
Grade A, and why
mbb-deck 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 1mo 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MBB 风 Deck（HTML / PPTX 双路径）
定位与输出契约
- 双输出路径，Step 0 第一问确认：
- HTML（默认）：单个 HTML 文件，内嵌全部 CSS，零外部依赖（无 CDN、无外链字体、无外链图片），1920×1080（16:9）严格无纵向滚动，键盘 <-/-> 翻页
- PPTX：16:9（13.333"×7.5"）.pptx，文本框/表格/图表均为原生可编辑对象（非图片贴片）；由
scripts/generate_pptx.py从 plan.json 确定性渲染
- 两路共用同一语义层：governing thought、data-shape、版式路由、plan.json（Step 1–4 与格式无关）；格式只决定 Step 5 的渲染方式
- 交付物：
<主题>-deck.html或<主题>-deck.pptx+ 质量门结果摘要（blocker 清零情况 + 未修 warning 披露）
5 条铁律（全流程贯穿）
- Action Title--每页标题是带主语、含义完整的结论句，永不做话题标签
- One slide, one argument--一页只承担一个沟通任务、推进一个论点
- 两段式路由--绝不直接"看内容选版式"；必须先产出 data-shape 强制中间产物，再查路由表匹配版式
- 容量先校验--先验证内容装不装得下，再渲染；超容换版式或拆页，永不缩字号硬塞
- 判定规则封闭--风格、输出格式等参数由用户显式指定，禁止模型自判（实测自判两次会得出不同结论）
弱/强标题对照、字数约束等细则见 references/narrative.md 与 references/design-system.md。
工作流（Step 0–7）
Step 0 · 参数确认（AskUserQuestion，封闭枚举）
一次性向用户确认四个参数。选项必须来自封闭清单，不给自由发挥项：
| 参数 | 选项 | 默认 |
|---|---|---|
| 输出格式 | HTML 单文件 / PPTX 原生可编辑 | HTML |
| 风格预设 | A Executive Classic / B McKinsey Navy / C MBB Navy-Teal（定义见 design-system.md §1） | A |
| 叙事脊柱 | SCQA / What-SoWhat-NowWhat / Diagnosis-Choice-Mobilization / Hypothesis-Evidence-Implication（适用场景见 narrative.md §2） | 按内容类型推荐一项并给理由 |
| 页数配方 | 研究摘要配方 / 战略决策配方 / 用户自定页数（配方见 narrative.md §7） | 按内容类型推荐 |
输出格式判定规则：用户已明确要 .pptx / PowerPoint / "发给别人改" -> PPTX，不再询问；已明确要网页 / HTML / 零依赖 -> HTML；未明确 -> 询问，并附取舍提示（PPTX = 收件方原生可编辑、企业环境通用；HTML = 零依赖、渲染保真、不依赖 Office）。
其余三个参数：用户拒绝选择时采用默认值，并在交付说明中显式披露"未指定，已用默认 X"。
Step 1–4 与输出格式无关：governing thought、data-shape、路由、plan.json 是语义层，两条路径共用同一份产物。plan.json 顶部写入
format字段。
Step 1 · Governing Thought（先于一切页面设计）
写一句能回答听众核心问题的中心论点，要求：具体到可以被反驳、有证据支撑、与决策相关、短到能凭记忆复述。质量标准与反例见 references/narrative.md §1。
产出的 governing thought 写入 plan.json 顶部（Step 3），后续每页标题都必须服务它。
Step 2 · data-shape 抽取（强制中间产物 #1，不许跳过）
把输入材料强制归类为 9 类封闭 data-shape 之一或若干（禁止"其他"类）。识别特征表见 references/routing.md §1。
What ships with it
9 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.
- 1mo ago First seen · 147 lines · 179 tokens per session scan A b2dcc950d6ec
mbb-deck is a skill published in the GitHub repository Gnomeshgh0714/mbb-deck (2 stars, last pushed 1mo ago), licensed MIT. It adds 179 tokens to every session and 3,243 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
html-ppt
For consulting delivery work: turn diagnosis, frameworks, and project work into a client-adoptable action plan. Built around the core query "consulting-final-deck", with engagement manager judgment, buyer-ready proof, and this outcome: accept the recommendation and commit owners to the roadmap.
html-ppt-zhangzara-soft-editorial
A digital-transformation roadmap for a legacy insurer — the diagnosis, the sequenced bets, and the operating rhythm to land them. Built as a decision-grade consulting deck for client executives.
blog-notebooklm
Query Google NotebookLM notebooks for source-grounded, citation-backed answers from user-uploaded documents. Manages notebook library, handles Google authentication, and supports smart discovery. Works standalone via /blog notebooklm or internally from blog-write and blog-researcher for source-grounded research…
strategy-consulting-visualization
Use when turning content into clear strategy-consulting visualizations, including board slides, reports, diagrams, quiet animated decks, or explicit dynamic and interactive decks with clickable evidence, scenario controls, what-if sliders, and deterministic presenter demos.
youtube-fetcher
Retrieve YouTube transcripts and subtitles, summarize or analyze what was said, or save an Obsidian-ready Markdown knowledge-base note with captions, creator metadata, chapters, language, and source provenance. Use for a YouTube URL or video ID when the request needs spoken content or an archival note. A bare YouTube…
mckinsey-charts
Generate McKinsey-style consulting charts as native python-pptx objects (editable inside PowerPoint). Three workhorse types — bar+callout for TAM/single-number stories, stacked column over time for revenue/usage mix, and waterfall for drivers/bridge analysis. Use when you need a chart that looks like it came from an…