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/06ketan/slideshotWrote 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/rules/06ketan/slideshot/slideshot-mcp)<a href="https://agentmods.dev/rules/06ketan/slideshot/slideshot-mcp"><img src="https://agentmods.dev/badge/rules/06ketan/slideshot/slideshot-mcp/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/rules/06ketan/slideshot/slideshot-mcp"><img src="https://agentmods.dev/badge/rules/06ketan/slideshot/slideshot-mcp.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 | $0.01691 | $0.01691 |
| Opus 5 | $0.00846 | $0.00846 |
| Sonnet 5 | $0.00338 | $0.00338 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
slideshot-mcp 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 9d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slideshot MCP v4.4.0 — Tool Usage Guide
6 Tools
| Tool | When to use |
|---|---|
discover_themes |
MANDATORY first for slide creation workflow. Returns themes, orientation presets, token modes, format options, and persisted user preferences. |
list_themes |
Idempotent theme catalog read with no discovery gates. Use when you just need the theme list. |
create_slides |
Create slides. Use mode=default unless user explicitly chose token_saver. |
edit_slides |
Partial edits to existing HTML — replace_slide, patch_css, patch_class, swap_token. Use this instead of regenerating the whole deck for small iterations (saves tokens). |
render_slides |
Render HTML to PDF/WebP/PNG/PPTX. Accepts html string or htmlPath. Supports width, height, selector, scale, webpQuality, orientation, pptxMode, pptxFilename, slideRange. Can be called directly with an existing htmlPath (bypasses gates). |
health_check |
Diagnose Puppeteer/Chromium issues. |
Two Workflows
A. Full slide-creation workflow (no existing HTML)
1. discover_themes → present ALL native selector prompts to the user
── theme, topic, orientation, token mode (recommend Default), format
── DO NOT render themes as markdown list — use selectors only
── DO NOT ask how many slides — AI decides based on topic
── WAIT for user answers
2. Show DATA OUTLINE — bullet list of proposed slides (no tool call)
── Present the outlineConfirm selector: "Looks good, continue" / "I want to make changes"
── WAIT for user to pick or type response. Loop until approved.
3. create_slides(mode, theme, orientation, html/slides) → htmlPath
── Use mode=default unless user explicitly chose token_saver
── STOP: Show htmlPath as code preview artifact
── Ask user to confirm. DO NOT call render_slides in this turn.
4. User confirms → render_slides(htmlPath, formats, scale, pptxMode...) → files on disk
B. Direct render (user has existing HTML file)
1. render_slides(htmlPath=<path to existing file>, formats, width, height, scale...) → files on disk
── No discover_themes or create_slides needed
── Gates are bypassed when htmlPath points to an existing file
── Also accepts html string directly instead of htmlPath
── Supports all render params: selector, width, height, scale, webpQuality, orientation, pptxMode, pptxFilename, slideRange
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.
- 9d ago First seen · 134 lines · 1,691 tokens per session scan A a393b758b347
slideshot-mcp is a cursor rule published in the GitHub repository 06ketan/slideshot (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,691 tokens to every session, about $0.0085 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 cursor rules, from other repositories
pro-deck-builder
Create polished HTML slide decks and PDF-ready documents for consulting deliverables. Uses the RRBC design system with warm light mode, dark mode cover pages, Lora/Inter/Roboto Mono typography, and data visualization palette. Trigger on 'deck', 'slides', 'presentation', 'pitch deck', 'keynote', 'report', or 'PDF'.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.