cursorrules

A set of writing rules for Markdown files, which are plain-text documents that use simple symbols for headings, links, lists, and code. It defines standards for README files and other Markdown content.

In plain words
What is it for?
Use it when editing README files or other .md files to guide headings, paragraphs, code examples, links, images, and lists.
Why use it?
It keeps documentation consistent, easy to scan, and aligned with the project's required structure and formatting.

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/deslicer/mcp-for-splunk/cursorrules
Clone the repo
git clone --depth 1 https://github.com/deslicer/mcp-for-splunk

Made for: Cursor.

Per session 756 This file is loaded in full into every session.
When invoked 756 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 $0.00756 $0.00756
Opus 5 $0.00378 $0.00378
Sonnet 5 $0.00151 $0.00151
Haiku 4.5 $0.00076 $0.00076

Measured 2d ago against content hash ec95f1a08e41, 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 2d 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.

.cursorrules · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor Rules for MCP Server for Splunk

README and Markdown Standards

When editing any *.md file, apply these standards:

README Writing Guidelines

  • Follow the guide in docs/readme-guide.md for all README files
  • Use the 3-Layer Principle: Hook (10s) → Quick Start (2m) → Navigation (30s)
  • Target audience first: Define personas and technical level before writing
  • Maximum 1200 words for main READMEs, focus on navigation to detailed docs

Markdown Formatting Rules

# H1: Document title only (one per file)
## H2: Major sections
### H3: Subsections (use sparingly, avoid H4+)

**Bold**: Important terms, actions, key concepts
*Italic*: Emphasis, file names, variables
`Code`: Commands, file paths, configuration values

Content Standards

  • Paragraphs: Maximum 3-4 sentences
  • Code blocks: Always include language for syntax highlighting
  • Links: Use descriptive text, prefer relative paths for internal links
  • Images: Include alt text, optimize for <500KB, use repo-relative paths
  • Lists: Use parallel structure, start with action verbs when possible

Code Example Requirements

  • Test all code examples before including
  • Include expected output when helpful
  • Show command context (directory, prerequisites)
  • Comment complex commands
  • Use realistic examples, not foo/bar placeholders

README Structure Enforcement

For main README files, ensure these sections exist:

  1. Hero Section: Title, badges, value proposition, key features
  2. Quick Start: Prerequisites, installation, first success
  3. Documentation Hub: Links to detailed guides
  4. Community/Support: Issues, discussions, help channels

Writing Style Rules

  • Use active voice: "Run the command" not "The command should be run"
  • Be specific: "Takes 2 minutes" not "Quick setup"
  • Show outcomes: "You'll see X" not "The system will do Y"
  • Use direct address: "You" instead of "users" or "developers"
  • Avoid jargon without explanation

Quality Checks

Before saving any .md file:

  • All links work and point to correct locations
  • Code examples are tested and current
  • Images load and have alt text
  • Headings follow logical hierarchy
  • Content serves the target audience
  • Length appropriate for document type

Read the full file on GitHub · 86 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. 2d ago First seen · 86 lines · 756 tokens per session scan A ec95f1a08e41

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository deslicer/mcp-for-splunk (27 stars, last pushed 8d ago), licensed Apache-2.0. It adds 756 tokens to every session, about $0.0038 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 2026-08-30.