Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add YoungjaeDev/my-claude-plugins/plugin install 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/youngjaedev/my-claude-plugins/deck-new)<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/deck-new"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/deck-new/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-new"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/deck-new.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 | $0.00159 | $0.01200 |
| Opus 5.5 | $0.00064 | $0.00480 |
| Sonnet 5.5 | $0.00032 | $0.00240 |
| Haiku 4.5 | $0.00016 | $0.00120 |
Grade B, and why
deck-new scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
found=$(find "$HOME/.claude/plugins/cache" "${CODEX_PLUGIN_CACHE:-$HOME/.codex/plugins/cache}" \ How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deck-new
Overview
Creates deck/ from the plugin template (neutral shell.html, a sample sections/00-cover.html, outline.md, motions/basic.js, fonts, vendor/gsap.min.js, brand assets, an empty assets/logos/sources.json, deck/.gitignore) and writes the three rule copies into .claude/rules/, each stamped with the plugin version. The deck owns every copied file afterwards. Build, check, render and deploy tools stay in the plugin and are never copied.
When to use
- The user explicitly asks for a new house-format deck in the current repository.
- Not when
deck/exists: the scaffold refuses. Usedeck-syncfor rule updates anddeck-authorfor writing slides. - Not for a generic talk or a PPTX conversion: that is
frontend-slides.
Procedure
Interaction gate: Claude uses AskUserQuestion; Codex uses request_user_input when exposed, otherwise asks in plain text and waits.
-
Confirm the target. Show
pwdand ask the user to confirm it is the repository root that should holddeck/. -
Resolve the plugin root and scaffold. Shell state does not persist between tool calls, so keep the resolver and the command in one call.
PLUGIN_ROOT="${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}" [ -z "$PLUGIN_ROOT" ] && [ -f plugins/deck/scripts/kit.py ] && PLUGIN_ROOT=plugins/deck if [ -z "$PLUGIN_ROOT" ]; then # find, not a glob: zsh aborts on an unmatched glob and does not split an unquoted list. found=$(find "$HOME/.claude/plugins/cache" "${CODEX_PLUGIN_CACHE:-$HOME/.codex/plugins/cache}" \ -mindepth 3 -maxdepth 3 -type d -path '*/deck/*' 2>/dev/null | awk -F/ '{print $NF "\t" $(0)}') if sort -V </dev/null >/dev/null 2>&1; then PLUGIN_ROOT=$(printf '%s\n' "$found" | sort -V | tail -1 | cut -f2-) else PLUGIN_ROOT=$(printf '%s\n' "$found" | sort -t. -k1,1n -k2,2n -k3,3n | tail -1 | cut -f2-) fi fi [ -f "$PLUGIN_ROOT/scripts/kit.py" ] || { echo "deck plugin scripts not found; export PLUGIN_ROOT=<path to plugins/deck>"; exit 1; } PY=$(command -v python3 || command -v python) "$PY" "$PLUGIN_ROOT/scripts/kit.py" new .
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.
- today Changed 4f3354680b4e
- 13d ago First seen · 62 lines · 159 tokens per session scan B eb2d630c9a4b
deck-new is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 159 tokens to every session and 1,200 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.
Other skills, from other repositories
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image layout — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
waitlist-page
A simple waitlist page for collecting email addresses from people interested in a new product or early-access release.