cursorrules

A set of coding rules for SecureTools, a browser-tool project built with plain HTML, CSS, and JavaScript.

In plain words
What is it for?
Use them when modifying SecureTools to avoid frameworks and build tools, keep JavaScript external, use secure randomness, add script integrity checks, and read AGENTS.md first.
Why use it?
They tell the agent which technologies, file locations, security practices, and coding patterns are allowed so changes pass the project's checks.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/midnightmarathon/securetools/cursorrules
Clone the repo
git clone --depth 1 https://github.com/MidnightMarathon/securetools

Made for: Cursor.

Per session 233 This file is loaded in full into every session.
When invoked 233 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00233 $0.00233
Opus 5 $0.00117 $0.00117
Sonnet 5 $0.00047 $0.00047
Haiku 4.5 $0.00023 $0.00023

Measured yesterday against content hash 8d6a79751520, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 13 lines

What it actually says

SecureTools Autopilot Rules

You are an AI assistant working on SecureTools. Follow these rules or the CI will fail.

  1. NO FRAMEWORKS: No React, Vue, Tailwind, etc.
  2. NO BUILD TOOLS: No Webpack, Vite, npm, package.json.
  3. VANILLA ONLY: Only plain HTML, CSS (in /assets/styles.css), and JS (in separate files, loaded with defer).
  4. NO INLINE JS: No <script> blocks in HTML, no onclick, no oninput. Use addEventListener in .js.
  5. RANDOMNESS: Use crypto.getRandomValues(). Never Math.random().
  6. CDN: Check srihash.org and include integrity and crossorigin="anonymous" on all CDN scripts.
  7. SHARED CSS: Do NOT duplicate body, nav, button, or main styles. They inherit from /assets/styles.css.

Read AGENTS.md for the full file map, checklists, and CSS definitions before modifying HTML.

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. yesterday First seen · 13 lines · 233 tokens per session scan A 8d6a79751520

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository MidnightMarathon/securetools (2 stars, last pushed 3mo ago), licensed MIT. It adds 233 tokens to every session, about $0.0012 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.