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/inboxpraveen/Minimize-Cursor-CostWrote 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/inboxpraveen/minimize-cursor-cost/html-css)<a href="https://agentmods.dev/rules/inboxpraveen/minimize-cursor-cost/html-css"><img src="https://agentmods.dev/badge/rules/inboxpraveen/minimize-cursor-cost/html-css/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/inboxpraveen/minimize-cursor-cost/html-css"><img src="https://agentmods.dev/badge/rules/inboxpraveen/minimize-cursor-cost/html-css.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 | $0.00000 | $0.00385 |
| Opus 5.5 | $0.00000 | $0.00154 |
| Sonnet 5.5 | $0.00000 | $0.00077 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
html-css 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 1mo 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
HTML / CSS Rules
Output
- Show only the affected element / selector.
- Don't reprint surrounding markup unless needed for selector context.
- Don't reformat indentation in unrelated lines.
CSS
- Match existing methodology: BEM / utility-first (Tailwind) / CSS Modules / plain.
- Don't introduce a new methodology mid-file.
- Don't add CSS custom properties (vars) if the file doesn't use them.
- Don't add vendor prefixes — assume autoprefixer or modern browsers unless told otherwise.
Tailwind
- Match existing class ordering style.
- Don't introduce arbitrary values (
w-[123px]) when a scale value works. - Don't add
@applyrules unless the codebase uses them. - Don't add new custom theme entries to
tailwind.config.*unless asked.
SCSS / Sass
- Don't add nested selectors deeper than the existing file.
- Don't introduce mixins for one-off use.
- Match existing module/import style (
@usevs@import).
Accessibility
- Preserve existing ARIA attributes — don't strip them.
- Don't add ARIA attributes that duplicate semantic HTML (e.g.,
role="button"on<button>). - Match existing alt-text style (don't suddenly add
alt=""to all images).
Never
- Don't change the design system colors / spacing scale.
- Don't introduce CSS-in-JS to a CSS-file project (or vice versa).
- Don't add
!importantto fix specificity — fix the selector. - Don't restructure HTML semantics (
<div>→<section>) unless the task is a11y.
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.
- 1mo ago First seen · 41 lines · 0 tokens per session scan A 985700341676
html-css is a cursor rule published in the GitHub repository inboxpraveen/Minimize-Cursor-Cost (10 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 385 tokens. 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
performance
Frontend performance optimization rules. Apply when optimizing UI or bundle.
accessibility
Accessibility (a11y) rules for frontend components. Apply when editing UI or markup.
40-styling
CSS modules colocated with components, kebab-case filenames. See rules/core/styling.md.
tailwind-v4-anti-patterns
Tailwind CSS v4 anti-pattern detection. Prevents the most common AI-generated mistakes: version mixing, deprecated config patterns, and removed utilities.
tailwind-v4-config
Tailwind CSS v4 configuration rules for CSS and build tool files. Covers @theme, @source, @import, PostCSS, and Vite plugin setup.
tailwind-v4-core
Core Tailwind CSS v4 rules. Enforces correct v4 syntax and prevents common v3 fallbacks. Attach to all conversations involving Tailwind CSS.