nen-manipulator

nen-manipulator is a cursor rule for Cursor from rlaope/nen. It costs 155 tokens per session (2,384 once invoked), scanned A, original, MIT.

An orchestration skill for breaking a chosen task into workstreams, assigning them to other agents, and checking their results.

In plain words
What is it for?
It is for decomposition, agent routing, prompt design, parallel work, and verification during multi-agent or deep-research tasks.
Why use it?
It reduces vague delegation and prevents unverified agent output from being treated as finished work.

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-manipulator
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-manipulator

README.md
[![agentmods](https://agentmods.dev/badge/rules/rlaope/nen/nen-manipulator.svg)](https://agentmods.dev/rules/rlaope/nen/nen-manipulator)
Your own site
<a href="https://agentmods.dev/rules/rlaope/nen/nen-manipulator"><img src="https://agentmods.dev/badge/rules/rlaope/nen/nen-manipulator.svg" alt="Measured on agentmods" height="20"></a>
Per session 155 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,384 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 $0.00155 $0.02384
Opus 5 $0.00077 $0.01192
Sonnet 5 $0.00031 $0.00477
Haiku 4.5 $0.00015 $0.00238

Measured 5d ago against content hash 6f38999c21f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nen-manipulator 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 5d 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-manipulator.mdc · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stance

操作系 Manipulation is the discipline of controlling other wills precisely — and precision is the entire game. An orchestrator produces nothing directly; its output is exactly as good as the instructions it wraps around other agents and the verification it applies to what comes back. The subagent you dispatch has no memory of your conversation, no access to your intent, and no shame about returning confident garbage. Whatever you did not write into the dispatch does not exist for that agent.

Without this discipline, delegation becomes theater. Vague prompts go out, plausible prose comes back, "done" is accepted because checking feels like distrust, and the orchestrator ends up laundering unverified work into a final answer with its own credibility stamped on top. The delegation is not the hard part. The contract and the audit are the work.

Boundaries

If the question is still what to pursue — which opportunity matters, how to frame the idea, where the impact point is — stop. That is emitter's job. You decompose and route a goal that has already been chosen; planning the execution of an unchosen goal produces an exquisite breakdown of the wrong thing. Come back when there is a decided objective to distribute.

If the whole task collapses into one deep dive on one external mechanism — why does this library behave this way, what is this undocumented API actually doing — stop pretending it needs orchestration. That is specialist's job, and it should be dispatched as a single unit or simply done. You earn your existence when there are several such units with real routing and integration decisions between them; a coordinator over one worker is pure overhead.

If the routing table itself comes up empty — the same need keeps recurring and no existing skill covers it — stop dispatching. That is hatsu's job: forging the missing ability into a skill of its own. Orchestration distributes work across abilities that exist; it cannot conjure the one that doesn't. Come back when the new skill is forged and trial-fired, and route through it.

Read the full file on GitHub · 98 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. 5d ago First seen · 98 lines · 155 tokens per session scan A 6f38999c21f5

Subscribe to this mod's changes

nen-manipulator is a cursor rule published in the GitHub repository rlaope/nen (3 stars, last pushed 1mo ago), licensed MIT. It adds 155 tokens to every session and 2,384 once invoked, about $0.0008 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.