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/benchflow-ai/agents/stylegit clone --depth 1 https://github.com/benchflow-ai/agentsWhat 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 | $0.00409 | $0.00409 |
| Opus 5 | $0.00204 | $0.00204 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
style 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.
This is a copy
100% identical to style — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Style guide
- Target python 3.10 or higher
- Use python with type annotations. Use
listinstead ofList. - Use
pathlibinstead ofos.path. UsePath.read_text()overwith ...open()constructs. - Use
typerto add interfaces - Keep code comments to a minimum and only highlight particularly logically challenging things
- Do not append to the README unless specifically requested
- Use
jinjafor formatting templates - Use
dataclassfor keeping track config - Do not catch exceptions unless explicitly told to.
- Write concise, short, minimal code.
- In most cases, avoid initializing variables just to pass them to a function. Instead just pass the expression to the function directly.
- Not every exception has to be caught. Exceptions are a good way to show problems to a user.
- This repository rewards minimal code. Try to be as concise as possible.
Here's an example for rule 11:
# bad
a = func()
Class(a)
# good
Class(func())
Test style
- Use
pytest, notunittest. - Do not mock/patch anything that you're not explicitly asked to do
- Avoid writing trivial tests. Every test should test for at least one, preferably multiple points of failure
- Avoid splitting up code in multiple lines like this:
a=func()\n assert a=b. Instead, just doassert func() == b - The first argument to
pytest.mark.parametrizeshould be a tuple (not a string! not a list!), the second argument must be a list (not a tuple!).
Here's an example for rule 4:
# bad
result = func()
assert result == b
# good
assert func() == b
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.
- 2d ago First seen · 52 lines · 409 tokens per session scan A 214a35128161
style is a cursor rule published in the GitHub repository benchflow-ai/agents (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 409 tokens to every session, about $0.0020 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to style, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
engine-internals
Coding Agent engine implementation details (Cursor + Claude Code) — reference when modifying engine.ts or debugging Agent behavior.
testing-conventions
Testing conventions — must reference when modifying src/ code or tests.
architecture-constraints
GolemBot architecture hard constraints — must check before modifying any src/ code.
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.
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.