general

General rules for an AI coding agent covering concise work, documentation review, specialized project rules, security, communication, verification, and final review. They establish a working method for making and checking repository changes.

In plain words
What is it for?
Use them as baseline instructions for coding tasks in a repository. They guide how the agent starts work, changes files, communicates risks, and verifies the result.
Why use it?
They reduce unnecessary edits and help prevent unsupported assumptions, exposed secrets, and unverified work. They also require the agent to consult the project’s docs and rules before implementation.

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/raysalem/real_estate_sd_web_scraper/general
Clone the repo
git clone --depth 1 https://github.com/raysalem/real_estate_sd_web_scraper

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 332 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00332
Opus 5 $0.00000 $0.00166
Sonnet 5 $0.00000 $0.00066
Haiku 4.5 $0.00000 $0.00033

Measured 2d ago against content hash de2e5987e34c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

general 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.

.cursor/rules/general.mdc · 22 lines

What it actually says

General Guidelines

1. Primary Mandates

  • MINIMIZE SLOP: Produce clean, concise, robust, and functional code. No boilerplate, redundant comments, or hallucinated features. Go straight to the point.
  • SURGICAL UPDATES: Make the smallest change necessary to achieve the goal without compromising architectural integrity.
  • DOCS-FIRST MINDSET: Every session must begin by reviewing the docs/ folder and README.md. These are the "System of Record."

2. Core Behavior

  • Adherence to Rules: You MUST follow the specialized rules in .cursor/rules/ (Workflow, Maintenance, Python, etc.) for all implementations.
  • Judicial Review: Every task is subject to a mandatory final "Judicial Review" to ensure prompt fidelity and zero regressions.
  • Security & Integrity: Never hardcode secrets. Always protect system integrity and source control history.

3. Communication

  • Brevity: Be direct and professional. Avoid conversational filler.
  • Proactiveness: Identify risks and suggest improvements (adding to docs/todo.md) rather than just executing blindly.
  • Verification: Never consider a task "Done" until behavioral correctness is verified and structural integrity is confirmed.
    • MANDATORY: Tests must always include explicit assertions and/or checkers (fuzzy matching is acceptable when needed). Tests that simply print() without programmatic validation are strictly prohibited.
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 · 22 lines · 332 tokens per session scan A de2e5987e34c

Subscribe to this mod's changes

general is a cursor rule published in the GitHub repository raysalem/real_estate_sd_web_scraper (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 332 tokens. 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.