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 skills/m-binimran/design-pack/presentation-decknpx skills add m-binimran/design-pack --skill presentation-deckgit clone --depth 1 https://github.com/m-binimran/design-packWrote 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/m-binimran/design-pack/presentation-deck)<a href="https://agentmods.dev/skills/m-binimran/design-pack/presentation-deck"><img src="https://agentmods.dev/badge/skills/m-binimran/design-pack/presentation-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 | $0.00041 | $0.00275 |
| Opus 5 | $0.00020 | $0.00138 |
| Sonnet 5 | $0.00008 | $0.00055 |
| Haiku 4.5 | $0.00004 | $0.00028 |
Grade A, and why
presentation-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 3d 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.
What it actually says
presentation-deck
A deck that looks designed, not defaulted: one system, applied consistently.
Process
- Outline first: narrative arc, one idea per slide, the key takeaway per slide.
- Layout system: a small set of slide templates (title, section, content, big-number, image-full, quote) with a consistent grid, type scale, and colour from the brand kit.
- Build via the Canva connector (branded template) or as structured slides; place real content, not lorem.
- Visuals: charts as part of the system; imagery via stock/generation (licensed); minimal text per slide.
- Polish: alignment, consistent spacing, contrast (the
contrast-guardhook), readable from the back row.
Output
- The deck (confirmed from the connector) following the layout system, with speaker-note suggestions and licensing recorded.
Guardrails
- Consistent system across slides; on-brand; legible; not a wall of bullet text.
- Confirm the connector built it; record asset licenses.
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.
- 3d ago First seen · 25 lines · 41 tokens per session scan A b027cdf4e40c
presentation-deck is a skill published in the GitHub repository m-binimran/design-pack (3 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 275 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
llamaindex
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM…
prepare-mcp-integration
Prepare MCP/vendor integrations through cited research, a content PR, exact-revision human approval, and one governed Paperclip connector PR per approved connection. Use for new integration research and delivery; not for ad hoc connector coding that bypasses the playbooks.
agent-builder
Draft new agents and attach scheduled automations to them. Depth-1 cap; drafts only — a human must publish via the UI.
swarmclaw
AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.
llamaindex
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM…
fair-housing-overlay
Foundational compliance skill. Enforces Fair Housing, TCPA, MLS-data-quality, and always-positive rules across every other skill in this repo. Load this skill alongside any other for compliance-first output. Use when ANY content is being generated for an audience the agent doesn't directly control (social, MLS, email…