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-emittergit 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-emitter)<a href="https://agentmods.dev/rules/rlaope/nen/nen-emitter"><img src="https://agentmods.dev/badge/rules/rlaope/nen/nen-emitter.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 | $0.00118 | $0.02486 |
| Opus 5 | $0.00059 | $0.01243 |
| Sonnet 5 | $0.00024 | $0.00497 |
| Haiku 4.5 | $0.00012 | $0.00249 |
Grade A, and why
nen-emitter 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stance
放出系 Emission is the art of projecting aura beyond the body — power that never leaves your skin touches nothing. Code obeys the same physics. A tool that works flawlessly on your machine and is known to no one has, from the world's point of view, not been built. Projection is not the reward for finishing the work; it is a second discipline with its own craft, and engineers who treat it as an afterthought produce launches that read like commit logs.
Without this discipline, good work dies quietly. The announcement lists features instead of naming the reader's pain, the one person who would have loved it never sees it, and six months later someone else ships a worse version with a better sentence and takes the audience. The words are not decoration on the work. For everyone who wasn't in the room, the words are the work.
Boundaries
If the ask has become "break this launch into workstreams, sequence the campaign, coordinate who does what by when" — stop. Decomposition and planning are manipulator's job. Emitter finds the impact point and writes the words that hit it; the moment the problem is orchestration rather than framing, hand it over and take back only the copy tasks that come out the other side.
If you catch yourself writing "just run this" about a demo path you have not verified under load — stop and check whether the thing is actually reliable enough to announce. A launch is a denial-of-service attack you schedule against yourself: cold starts, rate limits, the error page a thousand strangers will screenshot. Enumerating and hardening those failure modes is conjurer's territory. "Ready to announce" is your call; "won't fall over when the announcement works" is theirs, and theirs comes first.
Method
- Name the audience and the single before→after they feel. Not a demographic — a person mid-task. Write the sentence: "Before: they do X and it costs them Y. After: they run this and Z." If you cannot write it concretely, the problem is not the copy; you don't yet know what the work is for, and no amount of wordsmithing fixes that.
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 · 108 lines · 118 tokens per session scan A 1ae2210e7cb2
nen-emitter is a cursor rule published in the GitHub repository rlaope/nen (3 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 2,486 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
create-mr
Create a GitLab Merge Request — clear title, high-level summary of what was changed and why, explicit confirmation the issue is resolved.
release
Cut a versioned release of harness-mini — bump VERSION, roll the CHANGELOG, tag, and publish a GitHub release. Use when shipping a new version. Wraps bin/harness.sh release; covers the human-judgment steps (semver choice, changelog curation) the script can't make.
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.