CURSOR

Agent commands are available with @ prefix (e.g., @architect, @developer). Each command.

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/mslavov/shelly-forge/cursor
Clone the repo
git clone --depth 1 https://github.com/mslavov/shelly-forge

Made for: Cursor.

Per session 343 This file is loaded in full into every session.
When invoked 343 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00343 $0.00343
Opus 5 $0.00171 $0.00171
Sonnet 5 $0.00069 $0.00069
Haiku 4.5 $0.00034 $0.00034

Measured today against content hash 7575ade33f49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CURSOR 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 today.

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/CURSOR.mdc · 40 lines

What it actually says

Documentation Usage Guidelines

CRITICAL: Framework-First Reading Order

📚 MANDATORY READING ORDER:

  1. FIRST: Read rules in @rules/ - Framework rules and development guidelines
  2. SECOND: Read @INDEX.md - Documentation navigation hub
  3. THIRD: Read your agent definition in @definitions/ (if applicable)
  4. THEN: Consult project-specific documentation as needed

Pre-Task Protocol

  1. Verify you've read the framework rules - All files in @rules/ and @INDEX.md are mandatory
  2. Review relevant documentation - Use @INDEX.md to find specific docs
  3. Check the Quick Task Lookup - Find the right documents for your task type
  4. Read @system-overview.md for system understanding when needed
  5. Consult product documents from docs/product as needed
  6. Reference technical docs from docs/tech as needed

Post-Task Protocol

  1. Update the single authoritative source for any changed information
  2. Update cross-references if new relationships are created
  3. Move completed tasks from @tasks/in-progress/ to @tasks/done/
  4. Update @INDEX.md if new documents are created

Agent Commands

Agent commands are available with @ prefix (e.g., @architect, @developer). Each command:

  • Provides a brief role description
  • Links to full documentation using Cursor's @ notation
  • Assumes this CURSOR.mdc file has been read

See available commands in .cursor/rules/*.mdc

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. today First seen · 40 lines · 343 tokens per session scan A 7575ade33f49

Subscribe to this mod's changes

CURSOR is a cursor rule published in the GitHub repository mslavov/shelly-forge (20 stars, last pushed 1y ago), licensed MIT. It adds 343 tokens to every session, about $0.0017 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 2026-09-01.