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/adithya-s-k/research-presentation-templateWrote 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/adithya-s-k/research-presentation-template/slides)<a href="https://agentmods.dev/rules/adithya-s-k/research-presentation-template/slides"><img src="https://agentmods.dev/badge/rules/adithya-s-k/research-presentation-template/slides/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/adithya-s-k/research-presentation-template/slides"><img src="https://agentmods.dev/badge/rules/adithya-s-k/research-presentation-template/slides.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 | $0.00367 | $0.00367 |
| Opus 5.5 | $0.00147 | $0.00147 |
| Sonnet 5.5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
slides 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 2mo 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
Read CLAUDE.md at the repo root — it is the full authoring guide and applies
here verbatim. The short version:
- One idea per slide. If it needs a paragraph, split it. The dev-only
OverflowGuardbadge means redesign, not smaller type. - Type floors: body ≥ 22px, bullets ~34px, slide titles ~46px, big claims 54–92px.
- Title / authors / venue / links / theme live in
presentation.config.json— never hard-coded in a slide. - Colours come from
useTheme()tokens (T.bg,T.white,T.text,T.textMuted,T.textDim,T.accent,T.accent2,glow.*). No raw hex in slides — it breaks the other themes and light mode. - A content slide is
SlideShell+ absolutely-positioned content starting aroundtop: 210, withleft/right: 96. UseStagger+Risefor entrances. - Add a slide: new
src/slides/NN_Name.tsx, then one line insrc/slides/index.ts. Never hard-code the section number; setbare: truefor title/divider/closing slides. - Deck UI that overlays the stage must be tagged
data-chromeso the PPTX/PDF export can hide it.
Done means: npx tsc --noEmit clean, renders in dark and light, no overflow badge.
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.
- 2mo ago First seen · 27 lines · 367 tokens per session scan A 4f4d9a053057
slides is a cursor rule published in the GitHub repository adithya-s-k/research-presentation-template (9 stars, last pushed 3mo ago), licensed MIT. It adds 367 tokens to every session, about $0.0015 per session on Opus 5.5. 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
astro-strapi-starter
Astro x Strapi starter — layout, content collections, block renderer vs StrapiBlocks, types.
project
Project-wide instructions and conventions.
new_project
You are an expert Product Owner focused on helping users define new software projects through collaborative vision creation.
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.