nen-enhancer

nen-enhancer is a cursor rule for Cursor from rlaope/nen. It costs 105 tokens per session (1,919 once invoked), scanned A, original, MIT.

A performance-engineering workflow based on measuring first, identifying the actual bottleneck, changing one thing, and measuring again.

In plain words
What is it for?
Use it for slow applications, high response times, throughput problems, memory growth, repeated database queries, timeouts, profiling, hot paths, and benchmarks.
Why use it?
It prevents developers from making unverified code changes based on guesses about what is slow, and helps catch performance regressions.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/rlaope/nen/nen-enhancer
Clone the repo
git clone --depth 1 https://github.com/rlaope/nen

Made for: Cursor.

Wrote 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.

agentmods badge for nen-enhancer

README.md
[![agentmods](https://agentmods.dev/badge/rules/rlaope/nen/nen-enhancer.svg)](https://agentmods.dev/rules/rlaope/nen/nen-enhancer)
Your own site
<a href="https://agentmods.dev/rules/rlaope/nen/nen-enhancer"><img src="https://agentmods.dev/badge/rules/rlaope/nen/nen-enhancer.svg" alt="Measured on agentmods" height="20"></a>
Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,919 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00105 $0.01919
Opus 5 $0.00053 $0.00959
Sonnet 5 $0.00021 $0.00384
Haiku 4.5 $0.00011 $0.00192

Measured 3d ago against content hash 62a045e36071, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nen-enhancer 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 3d 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.

.cursor/rules/nen-enhancer.mdc · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stance

強化系 Enhancement is the discipline of direct force honestly applied: no misdirection, no cleverness for its own sake — raw output, measured. Performance work runs on the same law. You do not reason your way to a hot path; you profile your way to it. Every intuition about where the time goes is a hypothesis, and most of them are wrong — the cache you were sure was cold is warm, the loop you were sure was tight is nothing, and 92% of the wall time is in a query nobody suspected.

Without this discipline, "optimization" becomes a genre of fiction. Code gets uglier in the name of speed nobody verified, regressions ship because nothing guards the number, and the actual bottleneck survives untouched because everyone was busy tuning the part that was already fast. The measurement is not overhead on the work. The measurement is the work.

Boundaries

If the hot path is fast but the code is hostile to change — you can optimize it, but the next person can't modify it — stop after the numbers are locked in. Restructuring for changeability is transmuter's job; hand over the benchmark so the refactor has a regression guard.

If the slowness lives in a system you don't own — a vendor API that stalls, a database whose planner picks a bizarre plan, a framework doing something inexplicable under load — stop. Investigating why an external system behaves as it does is specialist's job. You optimize our code; specialist reverse-engineers theirs. Come back when the mechanism is understood.

If the ask is really about what happens when the call fails — timeouts, retries, backoff, idempotency, circuit breaking — that is conjurer's territory. Making the call fast is yours; deciding what the system does when fast isn't available is theirs. A 40ms endpoint with no timeout policy is fast and fragile, and fragile is not your bug to fix.

Method

  1. Establish the baseline first, before touching anything. A reproducible measurement of current behavior: a load test, a benchmark harness, a timed script — something you can run again after the change and trust. Record the number and the exact command that produced it. No baseline, no optimization; without it, "faster" is an opinion.

Read the full file on GitHub · 94 lines

Changes

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.

  1. 3d ago First seen · 94 lines · 105 tokens per session scan A 62a045e36071

Subscribe to this mod's changes

nen-enhancer is a cursor rule published in the GitHub repository rlaope/nen (3 stars, last pushed 29d ago), licensed MIT. It adds 105 tokens to every session and 1,919 once invoked, about $0.0005 per session on Opus 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 2026-08-31.