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 YoungjaeDev/my-claude-plugins --skill deck-askgit clone --depth 1 https://github.com/YoungjaeDev/my-claude-pluginsWrote 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/youngjaedev/my-claude-plugins/deck-ask)<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/deck-ask"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/deck-ask/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/youngjaedev/my-claude-plugins/deck-ask"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/deck-ask.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 | $0.00183 | $0.01038 |
| Opus 5.5 | $0.00073 | $0.00415 |
| Sonnet 5.5 | $0.00037 | $0.00208 |
| Haiku 4.5 | $0.00018 | $0.00104 |
Grade A, and why
deck-ask 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 12d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deck-ask
Suggest the next deck skill. Look, then answer in a few lines; the user or that skill acts.
How to answer
-
Read only what tells the stage, cheapest first: does
deck/exist, thedeck/outline.mdheader and slide table,git status --short deck/, and the lastdeck-checkoutput if it is in the conversation. Do not run builds or scripts. -
Answer in this shape, in the user's language:
지금: <one line on where the deck stands> 추천: /<plugin:skill> — <one reason tied to what you saw> 대안: /<plugin:skill> — <when to pick it instead> (only if a real alternative exists) -
Stop. Do not start the suggested skill unless the user says so.
House deck or not
- House deck: RALPHDEV lecture in a repo,
deck/shell.html+deck/sections/, Vercel. Use the table. - One-off generic talk, pitch, or PPTX conversion without the house shell: suggest
frontend-slides. - Both loaded in a house deck:
deck-authorand.claude/rules/deck-authoring.mdwin where they overridefrontend-slides.
Situation → suggestion
| What you see | Suggest | Why |
|---|---|---|
| The request was dictated by voice and reads garbled | docs:vp |
fix terms before choosing |
No deck/ yet, house format wanted |
deck-new |
scaffold + stamped rule copies |
| Thesis, audience or section list unsettled | docs:interview-methodology |
decide before outlining; answers go to the outline header |
| Outline exists but needs stress-testing | grilling |
Matt skill; change deck/outline.md first |
| Outline names tools or concept slides without assets | deck-assets |
official logos, icon sheets, mascot cuts; confirms counts before spending quota |
| One image unrelated to the deck | codex-image |
never for a brand logo |
| Slides to write or change | deck-author |
outline first, then only the asked slides |
| Sections, shell, motions or assets changed since the last check | deck-check |
build, copy check, rule drift, render, look at PNGs |
deck-check said rules: stale/missing/unstamped or vendor: differs |
deck-sync |
never touches deck-local.md |
deck-check said rules: edited |
move deck-only lines to .claude/rules/deck-local.md |
deck-sync --force only with the user's yes |
| User wants to look at the deck or fix wording by eye | dev-server edit mode (deck-check step 5) |
text only; boxes cannot be moved yet |
| User reviewed locally and asked to deploy | deck-deploy |
only on that request |
| A rule should change for every deck | edit the plugin's templates/rules/, then deck-sync per deck |
one deck only: deck-local.md |
| A deck skill itself should change | docs:skill-forge |
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.
- 12d ago Changed 993fb01edb00
- 13d ago First seen · 64 lines · 183 tokens per session scan A 0fc6a00c1369
deck-ask is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 183 tokens to every session and 1,038 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 2026-10-06.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…