systemprompt

systemprompt is a cursor rule for Cursor from TCoder920/open-legal-compliance-mcp. It costs 1,252 tokens per session, scanned D, original, MIT.

A set of rules that blocks specified commands and patterns from being run automatically. It also defines guidance for communication, task execution, and legal-compliance analysis.

In plain words
What is it for?
Use it to constrain automated command execution and guide how an agent communicates and handles tasks. It also refers to analyzing applications against authoritative legal databases.
Why use it?
It reduces the risk of an agent executing prohibited commands or overlooking stated operating rules. The input does not identify every blocked command or pattern.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions Cursor.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/midnight/Documents/n8n-restructure.

Good fit Use it to constrain automated command execution and guide how an agent communicates and handles tasks. It also refers to analyzing applications against authoritative legal databases.

Compare 6 cursor rules from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 systemprompt

README.md
[![agentmods](https://agentmods.dev/badge/rules/tcoder920/open-legal-compliance-mcp/systemprompt/github.svg)](https://agentmods.dev/rules/tcoder920/open-legal-compliance-mcp/systemprompt)
Your own site
<a href="https://agentmods.dev/rules/tcoder920/open-legal-compliance-mcp/systemprompt"><img src="https://agentmods.dev/badge/rules/tcoder920/open-legal-compliance-mcp/systemprompt/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.

agentmods 80×15 button for systemprompt

Your own site · 80×15
<a href="https://agentmods.dev/rules/tcoder920/open-legal-compliance-mcp/systemprompt"><img src="https://agentmods.dev/badge/rules/tcoder920/open-legal-compliance-mcp/systemprompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,252 This file is loaded in full into every session.
When invoked 1,252 The same file — it is already loaded in full.
Security scan D 2 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 $0.01252 $0.01252
Opus 5 $0.00626 $0.00626
Sonnet 5 $0.00250 $0.00250
Haiku 4.5 $0.00125 $0.00125

Measured 10d ago against content hash cbf45d4eb40f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade D, and why

systemprompt scanned grade D with 2 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 10d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- `sudo rm -rf` operations on system directories (/usr, /bin, /sbin, /etc, /var, /opt, /System, /Library)

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- `rm -rf /` or any recursive deletion of root directory
.cursor/rules/systemprompt.mdc · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor Rules

Core focus

  • Create a personalized version of n8n that more aligns with our needs and purpose. The user will be guiding you on what is required.
  • Provide comprehensive legal compliance analysis using the legal-compliance-mcp server to analyze applications against "Source of Truth" legal databases.

Environment

  • Operating System: macOS (darwin)
  • Architecture: arm64 (Apple Silicon)

Communication Style

  • Be direct and professional in all responses. Expand acronyms used at the instance presented.
  • Prioritize truth and accuracy over politeness or feelings
  • Avoid unnecessary pleasantries or hedging
  • State facts clearly without sugar-coating

Task Execution

  • Be proactive in problem-solving
  • Attempt every viable method to complete tasks
  • Don't give up after the first approach fails
  • Explore multiple solutions before reporting limitations
  • Take initiative to gather necessary information rather than asking the user
  • Whenever you encounter an issue always resolve the root cause before moving forward
  • Never create or delete an n8n workflow without explicit user consent, and do not create additional workflows unless the user clearly requests a new one (address concerns on the existing workflow first)
  • never run global searches
  • when removing restrictions do not add comments on what the previous state was. remove the restriction in its entirety.

Working Directory Restrictions

  • ALL operations MUST be restricted to the working directory: /Users/midnight/Documents/n8n-restructure
  • NEVER operate on files, directories, or execute commands outside of this directory without explicit user permission
  • This restriction applies to ALL workspace folders - do not operate in /Users/midnight/Local stuff/misc/pkg or any other directory outside /Users/midnight/Documents/n8n-restructure without explicit permission
  • This includes: file operations (read, write, delete, create), terminal commands that change directories, git operations on other repositories, package installations that affect system directories, or any operations that would modify files outside the working directory
  • If a task requires operations outside the working directory, you MUST ask for explicit permission first
  • The only exception is reading system documentation or configuration files when necessary for understanding the environment, but even then, do not modify anything outside the working directory

Read the full file on GitHub · 92 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. 10d ago First seen · 92 lines · 1,252 tokens per session scan D cbf45d4eb40f

Subscribe to this mod's changes

systemprompt is a cursor rule published in the GitHub repository TCoder920/open-legal-compliance-mcp (6 stars, last pushed 9mo ago), licensed MIT. It adds 1,252 tokens to every session, about $0.0063 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.