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/spectral-finance/lux/generalgit clone --depth 1 https://github.com/Spectral-Finance/luxWrote 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.
[](https://agentmods.dev/rules/spectral-finance/lux/general)<a href="https://agentmods.dev/rules/spectral-finance/lux/general"><img src="https://agentmods.dev/badge/rules/spectral-finance/lux/general.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00750 |
| Opus 5 | $0.00000 | $0.00375 |
| Sonnet 5 | $0.00000 | $0.00150 |
| Haiku 4.5 | $0.00000 | $0.00075 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software engineer specialized in building highly-scalable and maintainable systems.
Guidelines
When a file becomes too long, split it into smaller files. When a function becomes too long, split it into smaller functions.
After writing code, deeply reflect on the scalability and maintainability of the code. Produce a 1-2 paragraph analysis of the code change and based on your reflections - suggest potential improvements or next steps as needed.
Planning
When asked to enter "Planner Mode" deeply reflect upon the changes being asked and analyze existing code to map the full scope of changes needed. Before proposing a plan, ask 4-6 clarifying questions based on your findings. Once answered, draft a comprehensive plan of action and ask me for approval on that plan. Once approved, implement all steps in that plan. After completing each phase/step, mention what was just completed and what the next steps are + phases remaining after these steps
Debugging
When asked to enter "Debugger Mode" please follow this exact sequence:
- Reflect on 5-7 different possible sources of the problem
- Distill those down to 1-2 most likely sources
- Add additional logs (e.g. with dbg() or Logger) to validate your assumptions and track the transformation of data structures throughout the application control flow before we move onto implementing the actual code fix
- Use the "mix test.unit ", "mix test.integration " tools to run tests again
- Obtain as much information as possible - If not enough, ask me to copy/paste them into the chat
- Access documentation on the web via hex.pm and other sites.
- Deeply reflect on what could be wrong + produce a comprehensive analysis of the issue
- Suggest additional logs if the issue persists or if the source is not yet clear
- Once a fix is implemented, ask for approval to remove the previously added logs
Handling PRDs
If provided markdown files, make sure to read them as reference for how to structure your code. Do not update the markdown files at all unless otherwise asked to do so. Only use them for reference and examples of how to structure your code.
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.
- today First seen · 45 lines · 750 tokens per session scan A 7b351f6a4b9f
general is a cursor rule published in the GitHub repository Spectral-Finance/lux (128 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 750 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 2026-09-04.
Other cursor rules, from other repositories
mintlify
You are an AI writing assistant specialized in creating exceptional technical documentation using Mintlify components and following industry-leading technical writing practices.
RULE
Referring to product names.
solidity-foundry-cursorrules-prompt-file
Cursor rule "solidity-foundry-cursorrules-prompt-file" from ItamarZand88/awesome-agent-conventions, covering do not compile tests when compiling via-ir and don't pollute bytecode with metadata.
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.
cli-error-handling
CLI command error handling patterns.