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/ghaida/intentWrote 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/ghaida/intent/intent-ref-deck-theme)<a href="https://agentmods.dev/rules/ghaida/intent/intent-ref-deck-theme"><img src="https://agentmods.dev/badge/rules/ghaida/intent/intent-ref-deck-theme/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/ghaida/intent/intent-ref-deck-theme"><img src="https://agentmods.dev/badge/rules/ghaida/intent/intent-ref-deck-theme.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 | $0.00006 | $0.01111 |
| Opus 5.5 | $0.00002 | $0.00444 |
| Sonnet 5.5 | $0.00001 | $0.00222 |
| Haiku 4.5 | $0.00001 | $0.00111 |
Grade A, and why
intent-ref-deck-theme 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 7d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/present default theme
Use this theme only when the user supplies no template, brand kit or prior deck. A user template replaces everything visual here; the structural rules in SKILL.md still apply.
Tokens
| Token | Light | Dark | Use |
|---|---|---|---|
| ink | #1a1a2e |
#ececf4 |
titles, body |
| muted | #5b5b72 |
#a0a0b8 |
subtitles, attributions, source credits |
| rule | #b8b8c8 |
#3a3a52 |
hairlines, de-emphasized chart series |
| surface | #f1f1f6 |
#1f1f33 |
placeholder frames, quote panels |
| canvas | #ffffff |
#12121f |
slide background |
| accent | #4338ca |
#7c6ff0 |
the one highlighted series, the ask; nothing decorative |
One sans-serif family throughout (system UI stack in HTML; the template's theme font in .pptx). Weight carries hierarchy: titles bold, everything else regular.
Type sizes
| Live (projected) | Read (sent) | Read, projected (presented and sent) | |
|---|---|---|---|
| Title | 36pt (44pt on title/section slides) | 28pt | 32pt |
| Body / bullets | 24pt, never below 18pt | 14pt | 18pt |
| Small (subtitle, source) | 18pt | 12pt | 14pt |
Layouts
| Layout | Holds | Use for |
|---|---|---|
title |
deck title + subtitle (audience, date) | slide 1 |
claim_visual |
claim title + one visual (screen, diagram, photo, placeholder) | most slides |
claim_chart |
claim title + one chart, highlighted series in accent | data |
claim_bullets |
claim title + up to a few short flat bullets | when there's nothing to show |
quote |
claim title + one quote + attribution | research evidence; the title states the insight |
section |
section claim | turning points in a long deck, not an agenda |
ask |
the ask as the title + what/who/by-when as subtitle | last slide (or the takeaway, if just informing) |
Read decks add a body-text block under the title on every content slide.
Grid
The same frame on every slide makes a deck read as one argument, not a stack of pages. Content that touches the edge reads as cramped, and projectors crop it. The grid is invisible: it decides where things sit and never draws.
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.
- 7d ago First seen · 75 lines · 1,111 tokens per session scan A 5b360bd9eb5e
intent-ref-deck-theme is a cursor rule published in the GitHub repository ghaida/intent (214 stars, last pushed 7d ago), licensed CC0-1.0. It adds 6 tokens to every session and 1,111 once invoked, about $0.0000 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 2026-10-11.
Other cursor rules, from other repositories
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).