manipulator

manipulator is a skill for Claude Code from rlaope/nen. It costs 159 tokens per session (2,382 once invoked), scanned A, original, MIT.

A skill for coordinating work across multiple AI agents and for conducting deep research. It helps split a chosen objective into tasks, route them, write precise instructions, and check the returned work.

In plain words
What is it for?
Use it to delegate work, divide a project into parallel tasks, design agent prompts, and verify delegated results.
Why use it?
It reduces confusion and unchecked assumptions when several agents or research steps are involved.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; positional $N argument.

Part of the nen plugin — 9 skills shipped together

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 skills/rlaope/nen/manipulator
Any agent
npx skills add rlaope/nen --skill manipulator
Clone the repo
git clone --depth 1 https://github.com/rlaope/nen

Made for: Claude Code.

Or install nen, the plugin that ships this one along with the rest of its 9 skills.

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 manipulator

README.md
[![agentmods](https://agentmods.dev/badge/skills/rlaope/nen/manipulator.svg)](https://agentmods.dev/skills/rlaope/nen/manipulator)
Your own site
<a href="https://agentmods.dev/skills/rlaope/nen/manipulator"><img src="https://agentmods.dev/badge/skills/rlaope/nen/manipulator.svg" alt="Measured on agentmods" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,382 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 5.1 $0.00159 $0.02382
Opus 5 $0.00079 $0.01191
Sonnet 5 $0.00032 $0.00476
Haiku 4.5 $0.00016 $0.00238

Measured 6d ago against content hash 8deeeea90edc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 6d 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.

skills/manipulator/SKILL.md · 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. 6d ago First seen · 98 lines · 159 tokens per session scan A 8deeeea90edc

Subscribe to this mod's changes

manipulator is a skill published in the GitHub repository rlaope/nen (3 stars, last pushed 1mo ago), licensed MIT. It adds 159 tokens to every session and 2,382 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.

Related

Other skills, from other repositories

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…

anthropics/claude-plugins-official · 82 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

gke-reliability

Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).

google/skills · 73 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens