toc

toc is a cursor rule for Cursor from duongductrong/antigravity-kit. It costs 418 tokens per session, scanned A, original, MIT.

A routing guide that maps different kinds of software requests to specialized skills and concise coding rules. It helps decide which guidance applies before work begins.

In plain words
What is it for?
Use it to choose guidance for frontend, backend, design, research, problem solving, Git, and coding style tasks.
Why use it?
It prevents unrelated instructions from being applied to a task and makes responses more consistent.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to choose guidance for frontend, backend, design, research, problem solving, Git, and coding style tasks.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/duongductrong/antigravity-kit/toc
Install

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.

Clone the repo
git clone --depth 1 https://github.com/duongductrong/antigravity-kit

Made for: Cursor.

Wrote 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.

agentmods badge for toc

README.md
[![agentmods](https://agentmods.dev/badge/rules/duongductrong/antigravity-kit/toc.svg)](https://agentmods.dev/rules/duongductrong/antigravity-kit/toc)
Your own site
<a href="https://agentmods.dev/rules/duongductrong/antigravity-kit/toc"><img src="https://agentmods.dev/badge/rules/duongductrong/antigravity-kit/toc.svg" alt="Measured on agentmods" height="20"></a>
Per session 418 This file is loaded in full into every session.
When invoked 418 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00418 $0.00418
Opus 5 $0.00209 $0.00209
Sonnet 5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 3d ago against content hash 3418668e2bbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

toc 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • toc — 100% identical, 0 lines differ
.cursor/rules/toc.mdc · 29 lines

What it actually says

You have multiple specialized rules organized into Skills (comprehensive guides with references) and Rules (concise best practices).

Skills

  • Aesthetic - Visual design principles, storytelling, and micro-interactions for distinctive interfaces
  • Backend Development - API design, architecture, authentication, security, and DevOps patterns
  • Frontend Design - Create distinctive, production-grade interfaces with bold aesthetics (avoid generic AI slop)
  • Frontend Development - React/TypeScript patterns: Suspense, lazy loading, TanStack Query/Router, MUI v7, file organization
  • UI Styling - shadcn/ui components, Tailwind CSS utilities, theming, accessibility, and canvas-based visual design
  • Sequential Thinking - Structured problem-solving with revision, branching, and hypothesis verification
  • Problem Solving - Techniques for complexity spirals, innovation blocks, meta-patterns, and scale testing
  • Research - Systematic research methodology for technical solutions with report generation

Rules

  • Git - Git commit and branching conventions
  • Coding Style - Coding style and best practices

Routing Guidelines

  1. For each user request, first infer which domains are relevant.
  2. Select 0–3 rules/skills that best match the request, prefer the SINGLE most specific one when possible.
  3. If both security and performance apply, prioritize security.mdc first, then performance.mdc.
  4. If no rule clearly matches, ignore all rules and answer normally.
Changes

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.

  1. 3d ago First seen · 29 lines · 418 tokens per session scan A 3418668e2bbe

Subscribe to this mod's changes

toc is a cursor rule published in the GitHub repository duongductrong/antigravity-kit (51 stars, last pushed 6mo ago), licensed MIT. It adds 418 tokens to every session, about $0.0021 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 2026-09-03.