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/rlaope/nen/nen-engit clone --depth 1 https://github.com/rlaope/nenWrote 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/rlaope/nen/nen-en)<a href="https://agentmods.dev/rules/rlaope/nen/nen-en"><img src="https://agentmods.dev/badge/rules/rlaope/nen/nen-en.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 | $0.00112 | $0.01979 |
| Opus 5 | $0.00056 | $0.00989 |
| Sonnet 5 | $0.00022 | $0.00396 |
| Haiku 4.5 | $0.00011 | $0.00198 |
Grade A, and why
nen-en 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 4d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stance
円 En is aura extended in a sphere: everything that enters the field is felt, and the feeling is itself the ability. Routing runs on the same law. Reading an incoming request properly — sensing which disciplines the work actually crosses — is not overhead before the real Nen starts; parsing the request and choosing abilities IS using Nen. En is the ability that makes the other abilities reachable.
The stakes are the librarian problem. A pack of disciplines without a sensing layer serves only the user who already knows the taxonomy — they must ask for enhancer by name to get profiling discipline, so the people who most need the routing receive none of it. And the cheap substitute is worse than nothing: keyword routing is a dead sensor. It fires on vocabulary while the actual work walks straight past it — "optimize" summons a profiler to a restructuring request, and the refactor ships unmeasured anyway. The law, stated once and binding always: sibling skill descriptions are scent, not the mechanism — classification happens on what the OUTPUT must be, never on which words appear in the request.
Boundaries
En senses and engages abilities for ONE incoming request. The moment the work needs decomposing into units dispatched across agents with acceptance criteria, stop — that is manipulator, and en's job was complete the moment it engaged manipulator. The field does not run the operation; it detected that an operation was needed.
When the field senses a recurring need that no skill in the table covers, route to hatsu with the occurrence evidence. En never forges: sensing a gap and filling a gap are different abilities, and the second has its own discipline.
En never does the work itself. It is the field, not the fist: it engages enhancer to move the number, transmuter to reshape the code, emitter to land the words, specialist to name the mechanism, conjurer to close the failure modes — and those disciplines act. An en that starts optimizing has stopped sensing.
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.
- 4d ago First seen · 94 lines · 112 tokens per session scan A 7de33b0a835e
nen-en is a cursor rule published in the GitHub repository rlaope/nen (3 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 1,979 once invoked, about $0.0006 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.
Other cursor rules, from other repositories
fix-issue
Implement a fix following the human-thinking loop — understand the root cause, plan the minimal change, implement, verify the problem is actually gone.
mintlify
You are an AI writing assistant specialized in creating exceptional technical documentation using Mintlify components and following industry-leading technical writing practices.
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.
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.