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.
npx agentmods add rules/raysalem/real_estate_sd_web_scraper/workflowgit clone --depth 1 https://github.com/raysalem/real_estate_sd_web_scraperWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00572 |
| Opus 5 | $0.00000 | $0.00286 |
| Sonnet 5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
workflow 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standard Operating Procedures (SOP)
1. Prompt Validation
Before acting, evaluate the prompt against these criteria:
- Is it complete and unambiguous?
- Do I have the necessary context (codebase access, credentials)?
- Are the tools/libraries requested available in this environment?
- Action: If any criteria fail, you MUST ask the user for clarification before proceeding.
2. Planning Phase
Planning is the most critical stage. Spend the necessary time here to avoid implementation errors.
- Research: Read the existing code for semantic meaning. Do not rely on file names alone.
- Verify & Plan: Development and Testing must be planned together. A feature without a verification plan is incomplete.
- Create/Update
docs/plan.md: Use the template below. This is a HARD REQUIREMENT before writing any implementation code.
Planning Template (docs/plan.md)
- Task: Summary of the request.
- Verification: Specific scripts, commands, or data checks to prove it works.
- Roadmap: Step-by-step technical approach.
- Impact Analysis: Identify which existing features might be affected.
- Notes: Record challenges or deviations encountered during execution.
3. Implementation & Verification Cycle
- Implement: Follow the approved
docs/plan.md. - Regression Testing: You MUST run existing tests or perform manual checks on related features to ensure Existing Feature Integrity. No feature should break to accommodate a new one.
- Verify: Run the verification steps defined in the plan.
- Document: Update
docs/features.md,docs/todo.md, andREADME.mdas needed.
4. Judicial Review (Final Validation)
Before declaring a task complete, you MUST perform a "Judicial Review." Switch perspective to act as an external auditor/judge with no attachment to the recent code changes.
The Judge's Checklist:
- Prompt Fidelity: Did we actually solve the user's primary goal, or did we drift into "slop"?
- Regression Check: Is there ANY evidence (logical or via tests) that existing functionality was broken? (Zero-tolerance for regressions).
- The "Best Path" Test: Is this the most elegant and maintainable solution, or is it a "brown zone" hack?
- Slop Reduction: Are there any redundant comments, unused imports, or boilerplate leftovers?
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.
- yesterday First seen · 43 lines · 572 tokens per session scan A 581e958da962
workflow 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 572 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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.