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 commands/roeibh/marp-deck-architect/create-marp-deckgit clone --depth 1 https://github.com/roeibh/marp-deck-architectWrote 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/commands/roeibh/marp-deck-architect/create-marp-deck)<a href="https://agentmods.dev/commands/roeibh/marp-deck-architect/create-marp-deck"><img src="https://agentmods.dev/badge/commands/roeibh/marp-deck-architect/create-marp-deck.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 | $0.06345 |
| Opus 5 | $0.00000 | $0.03173 |
| Sonnet 5 | $0.00000 | $0.01269 |
| Haiku 4.5 | $0.00000 | $0.00634 |
Grade A, and why
create-marp-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 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Marp Slide Deck
Create or edit a presentation using Marp. The archetype system shapes everything: visual theme, content density, tone, layout choices, and narrative structure.
Arguments
$ARGUMENTS- Topic, file path to existing deck, or outline
Mode Detection
- Empty or topic: New deck → Phase 1
- Path to
.mdfile: Read it, ask what to change, preserve existing archetype - Contains "restyle": Read deck, strip
<style>, apply new archetype
The Archetype System
Every deck is built for an archetype - aesthetic + intent + audience. The archetype changes how you WRITE, not just how it LOOKS.
| Archetype | Who | Goal | Aesthetic |
|---|---|---|---|
| Builder | Engineers, hackers | Explain systems clearly | Dark, monospace, terminal-adjacent |
| Operator | Execs, PMs, consultants | Drive decisions | Clean, structured, McKinsey calm |
| Seller | Founders, sales | Persuade, close | Bold, punchy, YC pitch energy |
| Creator | Speakers, designers | Be memorable | Expressive, gradients, visual-first |
| Educator | Trainers, enablement | Teach clearly | Warm, friendly, progressive disclosure |
Phase 1: Interview
Round 1 (ask all at once):
- Goal: What should the audience walk away with?
- Audience: Who's in the room?
- Key points: Main ideas, even rough
- Existing material: Notes, docs, files?
Read any files/URLs thoroughly before Round 2.
Round 2 (after Round 1):
- Archetype: Recommend one based on answers. Describe all four if unsure. If none fit, trigger custom flow (see below).
- Narrative arc: Suggest the archetype's default framework
- Data & visuals: Code, diagrams (Mermaid), screenshots?
- Constraints: Slide count, duration, branding?
- Speaker notes: Generate per slide?
Summarize and confirm.
Custom Archetype Flow (when none of the four fit)
If the user rejects all archetypes, build a custom one by asking:
- Vibe in 3 words: "Describe the feeling in 3 words" (e.g., "warm, playful, minimal")
- Color direction: Specific colors, a brand reference ("like Stripe" / "Notion vibes" / "cyberpunk"), or a mood ("earthy and warm")
- Density: Dense/packed, medium, or spacious/airy?
- Visual references: Any presentations, websites, or brands to emulate?
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 · 329 lines · 0 tokens per session scan A 56c16df5be24
create-marp-deck is a command published in the GitHub repository roeibh/marp-deck-architect (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,345 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 commands, from other repositories
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
enum-udp
UDP scan + service follow-up — top ports first, full sweep only when justified.
claude-recall
Update project context using the local LLM (Qwen2.5 0.5B).
review
Submit a story for verification (In Progress → In Review, no PR yet).