000-cursor-rules-loader

000-cursor-rules-loader is a cursor rule for Cursor from Stramp/Lost-Mines-Phandelver. It costs 1,414 tokens per session, scanned A, original, MIT.

A startup rule for Cursor that checks for project rules and loads every Markdown rule file before other work begins.

In plain words
What is it for?
Use it in a Cursor project with a .cursor/rules folder to require an initial rules check and establish which instructions take priority.
Why use it?
It is intended to make the agent follow the project's instructions consistently, including a special response limit when only read-only tools are available.

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/stramp/lost-mines-phandelver/000-cursor-rules-loader
Clone the repo
git clone --depth 1 https://github.com/Stramp/Lost-Mines-Phandelver

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 000-cursor-rules-loader

README.md
[![agentmods](https://agentmods.dev/badge/rules/stramp/lost-mines-phandelver/000-cursor-rules-loader.svg)](https://agentmods.dev/rules/stramp/lost-mines-phandelver/000-cursor-rules-loader)
Your own site
<a href="https://agentmods.dev/rules/stramp/lost-mines-phandelver/000-cursor-rules-loader"><img src="https://agentmods.dev/badge/rules/stramp/lost-mines-phandelver/000-cursor-rules-loader.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,414 This file is loaded in full into every session.
When invoked 1,414 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 $0.01414 $0.01414
Opus 5 $0.00707 $0.00707
Sonnet 5 $0.00283 $0.00283
Haiku 4.5 $0.00141 $0.00141

Measured 3d ago against content hash 9447a99156cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

000-cursor-rules-loader 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.

.cursor/rules/000-cursor-rules-loader.mdc · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🚨 INITIALIZATION RULE - MANDATORY RULES LOADING 🚨

🎯 MAXIMUM PRIORITY (0) - APPLY BEFORE ALL OTHERS 🎯

This rule has MAXIMUM PRIORITY (priority: 0) and MUST be applied BEFORE any other rule.

⚠️ CRITICAL INSTRUCTION - EXECUTE FIRST ⚠️

🚨 MANDATORY FIRST CHECK - BEFORE ANYTHING ELSE 🚨

BEFORE reading rules, BEFORE responding, ALWAYS check:

  1. Am I in ASK Mode?

    • Check available tools: if only read-only tools → ASK Mode
    • If ASK Mode → Response MUST be ONE sentence maximum, NO code, brief
    • If Agent Mode → Can proceed normally
  2. If in ASK Mode and response is longer than one sentence → STOP and rewrite

ALWAYS, ALWAYS, ALWAYS start each chat session by doing the following:

1. Verify Rules Existence

BEFORE responding to ANYTHING, you MUST:

  1. 🚨 FIRST: Check if in ASK Mode (read-only tools = ASK Mode)

    • If ASK Mode → Response MUST be ONE sentence, brief, NO code
    • If Agent Mode → Can proceed normally
  2. Verify that the .cursor/rules/ folder exists

  3. List ALL .mdc files in the .cursor/rules/ folder

  4. Read and apply ALL found rules

2. Mandatory Confirmation

ALWAYS start your first response with:

✅ RULES LOADED: [number] rules found and applied in .cursor/rules/

If you CANNOT read the rules, you MUST:

⚠️ WARNING: Could not read rules from .cursor/rules/
Please verify that the folder exists and that .mdc files are present.

3. Rules Priority Order

ALWAYS apply rules in this priority order:

  1. PRIORITY 0 (MAXIMUM):

    • 000-cursor-rules-loader.mdc - This rule (loader)
  2. PRIORITY 1 (CRITICAL):

    • ask-mode-behavior.mdc - ASK Mode behavior (ONE sentence, NO code)
    • clean-code-mandatory.mdc - Clean Code MANDATORY
    • execution-guard.mdc - Integrity protection
  3. PRIORITY 2 (CRITICAL):

    • project-architecture.mdc - Project architecture
  4. PRIORITY 3 (HIGH):

    • teaching-role.mdc - Expert/teacher posture

Read the full file on GitHub · 158 lines

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 · 158 lines · 1,414 tokens per session scan A 9447a99156cd

Subscribe to this mod's changes

000-cursor-rules-loader is a cursor rule published in the GitHub repository Stramp/Lost-Mines-Phandelver (2 stars, last pushed 9mo ago), licensed MIT. It adds 1,414 tokens to every session, about $0.0071 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.