nen-vow

nen-vow is a cursor rule for Cursor from rlaope/nen. It costs 139 tokens per session (2,198 once invoked), scanned A, original, MIT.

A set of rules for declaring clear, checkable promises before engineering work begins and reviewing each promise before calling the work finished.

In plain words
What is it for?
Use it when work must stay within specific files, avoid new dependencies, meet defined checks, or follow strict limits on what may change.
Why use it?
It keeps changes within the requested scope and makes completion claims verifiable. This helps prevent unrelated edits and unfinished or untested work being presented as done.

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-vow
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-vow

README.md
[![agentmods](https://agentmods.dev/badge/rules/rlaope/nen/nen-vow.svg)](https://agentmods.dev/rules/rlaope/nen/nen-vow)
Your own site
<a href="https://agentmods.dev/rules/rlaope/nen/nen-vow"><img src="https://agentmods.dev/badge/rules/rlaope/nen/nen-vow.svg" alt="Measured on agentmods" height="20"></a>
Per session 139 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,198 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 $0.00139 $0.02198
Opus 5 $0.00069 $0.01099
Sonnet 5 $0.00028 $0.00440
Haiku 4.5 $0.00014 $0.00220

Measured 4d ago against content hash 98c6e929122d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nen-vow 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.

.cursor/rules/nen-vow.mdc · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stance

制約と誓約 — Restriction and Pledge: an ability grows stronger through what its user swears not to do, and a broken oath forfeits the power itself. For an agent this law is not thematic, it is generation mechanics. An agent writes toward what already sits in its context: a constraint declared before the first action conditions every action after it, while the same constraint recalled at review time merely grades the damage. Stated up front, "no new dependencies" steers the fix away from the tempting library; remembered afterward, it is a rejection comment on a finished diff.

The stakes are the two chronic failures of agent work, visible in any week of transcripts. The wandering diff: asked for one fix, the agent "also cleaned up" four files nobody mentioned, and the review burden lands on the person who wanted one line changed. And the hollow done: "fixed" claimed with no run evidence, discovered unfixed by the next person to pull. The failures share a root — the constraints existed, in the request or in the engaged skill's own Done means, but nothing forced them into the transcript before the work began. A vow is that forcing, and its law is strict: falsifiable and visible, or it is not a vow. "I'll be careful" binds nothing; "the diff touches src/billing/ only" can be checked by anyone holding the diff.

Boundaries

Vow binds work; it never selects it. Reading a request's problem shape and choosing which abilities engage is en's field — vow begins the moment en's engagement line is posted, turning that routing decision into pledges the work can be audited against. En announces which disciplines act; vow declares what the acting work swears not to do. Neither does the other's job.

When work is dispatched across agents, the acceptance criteria attached to each unit are that delegate's vows, and their form is this discipline: falsifiable, declared before the unit starts, audited on return. Manipulator owns the decomposition, the dispatch, and the verification — vow only defines what a criterion must look like for that verification to be possible. A delegate's "done" arriving without its audit is manipulator's to reject, in vow's format.

Read the full file on GitHub · 99 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. 4d ago First seen · 99 lines · 139 tokens per session scan A 98c6e929122d

Subscribe to this mod's changes

nen-vow is a cursor rule published in the GitHub repository rlaope/nen (3 stars, last pushed 1mo ago), licensed MIT. It adds 139 tokens to every session and 2,198 once invoked, about $0.0007 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.