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/akngs/s4Wrote 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/akngs/s4/best-practices)<a href="https://agentmods.dev/rules/akngs/s4/best-practices"><img src="https://agentmods.dev/badge/rules/akngs/s4/best-practices/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/akngs/s4/best-practices"><img src="https://agentmods.dev/badge/rules/akngs/s4/best-practices.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 | $0.00167 | $0.00167 |
| Opus 5.5 | $0.00067 | $0.00067 |
| Sonnet 5.5 | $0.00033 | $0.00033 |
| Haiku 4.5 | $0.00017 | $0.00017 |
Grade A, and why
best-practices 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.
What it actually says
Always try best to follow the best practices:
- Prefer short and side-effect free functions over long and side-effectful functions.
- Prefer immutable data structures over mutable ones.
- Prefer the simplest possible solution over the most complex one. Never over-engineer.
- Use descriptive yet short names for variables, functions, classes, and modules. Exception: use single letter names for loop variables and parameters of one-liner functions.
- Add documentation to all public functions and classes.
- Write unit tests for all public functions and classes. Tests should be colocated with the code they test.
- Look for opportunities to refactor code to reveal the underlying intent and remove duplication.
- Never use
anytype. - When you import typescript file in this project, do not omit the extension
.ts.
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 · 14 lines · 167 tokens per session scan A eb6ebf685a39
best-practices is a cursor rule published in the GitHub repository akngs/s4 (13 stars, last pushed 10mo ago), licensed MIT. It adds 167 tokens to every session, about $0.0007 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 2026-09-02.
Other cursor rules, from other repositories
swarm-forge-crap
CRAP — complejidad y cobertura las imprime un script, no el modelo.
testing-react
Testing React components — React Testing Library, hooks, context, async, accessibility. Extends core/rules/testing.mdc with React-specific patterns.
dotnet-testing
.NET-specific testing standards for ASP.NET Core applications. Covers test naming, project structure, unit and integration testing patterns, builders, Testcontainers, and WebApplicationFactory. Complements engineering-principles.mdc and dotnet-architecture.mdc.
go
Go development guidelines — error handling, concurrency, interfaces, context propagation, and testing. Applied when working with Go code.
python
Python development guidelines — PEP 8, type hints, error handling, async patterns, packaging, and testing. Applied when working with Python code.
typescript-testing
TypeScript testing guidelines — Vitest/Jest setup, unit testing patterns, mocking strategy, integration testing with Testcontainers, and coverage standards. Applied when working with TypeScript test files.