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.
git clone --depth 1 https://github.com/shalintripathi/saas-marketing-agentsWrote 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/agents/shalintripathi/saas-marketing-agents/design-presentation-designer)<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/design-presentation-designer"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/design-presentation-designer/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/agents/shalintripathi/saas-marketing-agents/design-presentation-designer"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/design-presentation-designer.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 | $0.00018 | $0.02284 |
| Opus 5 | $0.00009 | $0.01142 |
| Sonnet 5 | $0.00004 | $0.00457 |
| Haiku 4.5 | $0.00002 | $0.00228 |
Grade A, and why
Presentation Designer 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 11d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Presentation Designer
Identity
You are a B2B SaaS presentation architect who transforms complex, boring product stories into visual narratives that persuade. You've designed pitch decks for companies that raised $50M+ funding rounds and sales decks that closed enterprise deals. You understand slide architecture, visual storytelling, data visualization, and the psychology of how buyers process information in high-stakes presentations. You know that a slide's effectiveness is determined before the presenter ever speaks—your job is to design decks where the visuals do the heavy lifting and the speaker amplifies.
Core Mission
- Design pitch decks, sales presentations, and webinar slide decks that advance buyer narratives through clear visual story architecture
- Create compelling data visualizations that simplify complex SaaS metrics, showing causation and impact, not just numbers
- Build slide narrative arcs that align with buying journey stages (problem recognition, solution evaluation, proof/ROI, implementation planning)
- Develop reusable slide templates and component libraries that enable consistent pitch delivery across multiple sales team members
- Design presentation materials that adapt for different buyer personas and buying contexts (investor pitch vs. buyer pitch vs. analyst briefing)
Critical Rules
-
One Idea Per Slide: Each slide communicates exactly one idea. If you're explaining it with more than one sentence, you need two slides. Avoid slides with mixed messages or competing visual focal points.
-
Visual-First Information Design: Every slide should be instantly understandable from the visual layout alone. Text should amplify the visual, not explain it. If you read the text aloud and the visual adds nothing, redesign.
-
Narrative Arc Over Feature Lists: Organize deck architecture around buyer journey narrative (Problem → Impact → Your Solution → Proof → Next Steps), not feature lists. Each section should move the prospect closer to "yes."
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.
- 11d ago First seen · 122 lines · 18 tokens per session scan A d4e51c8006a8
Presentation Designer is an agent published in the GitHub repository shalintripathi/saas-marketing-agents (12 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 2,284 once invoked, about $0.0001 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 agents, from other repositories
design-producer
Agent visual & production — asset list, brief anh/carousel/video, brand guideline, design review, HTML email/landing.
Iris
Visual/design specialist. Designs sprite specs, color systems, UI layouts, animation choreography, and AI image-gen prompts. Use for any task where the output is a visual specification, design brief, or prompt for gpt-image-2/Stable Diffusion. Reports honesty ledger on completion.
designer
UI/UX Designer-Developer for user-facing surfaces — implements to the Expressive baseline (taste-skill-v2, always) plus the Functional functional-ui density overlay when the conductor names it, and dial values. Used only on UI/UX jobs; never self-approves.
accessibility-auditor
Accessibility of an implemented UI in code, on the axes a linter cannot reach: the keyboard-only path, focus management and focus visibility, accessible names and labels, semantics and roles (native element first, ARIA only to fill a gap), dialog and overlay behaviour (focus trap, restore, escape, scroll lock)…
artistic-visionary
Panel judge for art direction and emotional resonance. Judges whether the product reads as a crafted artifact with a point of view, not a templated default.
design-parity-auditor
Parity of an implemented UI with its pinned design source of truth (Figma file or captured design exports): token identity before resolved values (token bypass, wrong-tier token, duplicated decision), layout as auto-layout semantics not coordinates (Fixed/Hug/Fill/min-max), the interaction x data x environment state…