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.
git clone --depth 1 https://github.com/phuctm97/modelfetchWrote 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/phuctm97/modelfetch/nx-rules)<a href="https://agentmods.dev/rules/phuctm97/modelfetch/nx-rules"><img src="https://agentmods.dev/badge/rules/phuctm97/modelfetch/nx-rules/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/phuctm97/modelfetch/nx-rules"><img src="https://agentmods.dev/badge/rules/phuctm97/modelfetch/nx-rules.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00668 | $0.00668 |
| Opus 5.5 | $0.00267 | $0.00267 |
| Sonnet 5.5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
nx-rules 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 1mo 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.
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.
// This file is automatically generated by Nx Console
You are in an nx workspace using Nx 21.4.1 and pnpm as the package manager.
You have access to the Nx MCP server and the tools it provides. Use them. Follow these guidelines in order to best help the user:
General Guidelines
- When answering questions, use the nx_workspace tool first to gain an understanding of the workspace architecture
- For questions around nx configuration, best practices or if you're unsure, use the nx_docs tool to get relevant, up-to-date docs!! Always use this instead of assuming things about nx configuration
- If the user needs help with an Nx configuration or project graph error, use the 'nx_workspace' tool to get any errors
- To help answer questions about the workspace structure or simply help with demonstrating how tasks depend on each other, use the 'nx_visualize_graph' tool
Generation Guidelines
If the user wants to generate something, use the following flow:
- learn about the nx workspace and any specifics the user needs by using the 'nx_workspace' tool and the 'nx_project_details' tool if applicable
- get the available generators using the 'nx_generators' tool
- decide which generator to use. If no generators seem relevant, check the 'nx_available_plugins' tool to see if the user could install a plugin to help them
- get generator details using the 'nx_generator_schema' tool
- you may use the 'nx_docs' tool to learn more about a specific generator or technology if you're unsure
- decide which options to provide in order to best complete the user's request. Don't make any assumptions and keep the options minimalistic
- open the generator UI using the 'nx_open_generate_ui' tool
- wait for the user to finish the generator
- read the generator log file using the 'nx_read_generator_log' tool
- use the information provided in the log file to answer the user's question or continue with what they were doing
Running Tasks Guidelines
If the user wants help with tasks or commands (which include keywords like "test", "build", "lint", or other similar actions), use the following flow:
- Use the 'nx_current_running_tasks_details' tool to get the list of tasks (this can include tasks that were completed, stopped or failed).
- If there are any tasks, ask the user if they would like help with a specific task then use the 'nx_current_running_task_output' tool to get the terminal output for that task/command
- Use the terminal output from 'nx_current_running_task_output' to see what's wrong and help the user fix their problem. Use the appropriate tools if necessary
- If the user would like to rerun the task or command, always use
nx run <taskId>to rerun in the terminal. This will ensure that the task will run in the nx context and will be run the same way it originally executed - If the task was marked as "continuous" do not offer to rerun the task. This task is already running and the user can see the output in the terminal. You can use 'nx_current_running_task_output' to get the output of the task to verify the output.
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.
- 1mo ago First seen · 43 lines · 668 tokens per session scan A 632e4679a587
nx-rules is a cursor rule published in the GitHub repository phuctm97/modelfetch (145 stars, last pushed 10mo ago), licensed MIT. It adds 668 tokens to every session, about $0.0027 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).