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 rules/adithya-s-k/research-presentation-template/slidesgit 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.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 | $0.00367 | $0.00367 |
| Opus 5 | $0.00183 | $0.00183 |
| Sonnet 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 4d 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.
- 4d 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 (8 stars, last pushed 1mo ago), licensed MIT. It adds 367 tokens to every session, about $0.0018 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
livkiet-plugins-playai
Agent Framework plugin for voice synthesis with PlayAI API.
query-optimization
查詢優化、EXPLAIN、index 設計與 RLS 效能測量.
skill-management
🔒 LOCKED — managed by clade Source: rules/core/skill-management.md Edit at: $CLADEHOME Local edits will be reverted by the next sync. -->.
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.