Embody: Skill for Claude Code

.claude/skills/pop-networks/SKILL.md

pop-networks is a skill for Claude Code from dylanroscover/Embody. It costs 42 tokens per session (3,399 once invoked), scanned A, original, MIT.

Guidance for building POP networks in TouchDesigner 2025 and later. POPs are GPU-based tools for processing points and geometry, while SOPs are TouchDesigner’s traditional CPU-based geometry tools.

In plain words
What is it for?
Use it for particle systems, point-heavy geometry, GPU displacement, trails, texture lookups, simulations, or converting suitable SOP workflows to POPs.
Why use it?
It helps you choose POPs when many points or particles need parallel GPU processing, while avoiding them when a simpler geometry tool is more appropriate.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is dylanroscover/Embody's own configuration. It tells Claude Code how to work on Embody itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Embody configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dylanroscover/Embody. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dylanroscover/Embody/main/.claude/skills/pop-networks/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dylanroscover/Embody

Made for: Claude Code.

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 pop-networks

README.md
[![agentmods](https://agentmods.dev/badge/skills/dylanroscover/embody/pop-networks/github.svg)](https://agentmods.dev/skills/dylanroscover/embody/pop-networks)
Your own site
<a href="https://agentmods.dev/skills/dylanroscover/embody/pop-networks"><img src="https://agentmods.dev/badge/skills/dylanroscover/embody/pop-networks/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pop-networks

Your own site · 80×15
<a href="https://agentmods.dev/skills/dylanroscover/embody/pop-networks"><img src="https://agentmods.dev/badge/skills/dylanroscover/embody/pop-networks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00042 $0.03399
Opus 5 $0.00021 $0.01699
Sonnet 5 $0.00008 $0.00680
Haiku 4.5 $0.00004 $0.00340

Measured 10d ago against content hash 96ee8c411797, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pop-networks 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 10d 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.

.claude/skills/pop-networks/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

POP Networks

Build GPU-resident point and geometry systems with TouchDesigner POPs. POPs are the 2025+ point-operator family: geometry attributes live on the GPU, many operations run in parallel, and the right chain can replace CPU-heavy SOP or particle workflows.

Use this skill with /create-operator, /visual-aesthetics, performance.md, network-layout.md, and td-python.md. POP correctness is not just a clean network: it is a rendered frame, readable layout, bounded performance, and no operator errors.

POPs vs SOPs

Use POPs when the work is point-heavy, particle-heavy, or naturally parallel:

  • Many points, particles, trails, instancing templates, or live geometry streams.
  • GPU-side displacement, filtering, attributes, neighborhood queries, texture lookups, or simulation loops.
  • Geometry that needs to stay GPU-resident for rendering, instancing, GLSL, or TOP/MAT interop.
  • SOP chains whose main cost is moving or filtering lots of points every frame.

Keep SOPs when they are the honest tool:

  • Booleans, UV unwrap, small static meshes, precise CPU geometry tools, or legacy SOP-only workflows.
  • Tiny one-off static shapes where a SOP is clearer and has no measurable cost.
  • Any workflow that needs a mature CPU operator with no POP equivalent.

Prefer POPs for dynamic scale, not as a religion. Start from the user's goal, expected point count, and render path, then choose the family that keeps the system understandable and fast.

Core Vocabulary

Generators create points or geometry:

  • gridPOP, boxPOP, spherePOP, torusPOP, tubePOP, circlePOP, linePOP, rectanglePOP.
  • randomPOP, sprinklePOP, pointgeneratorPOP, patternPOP, curvePOP.
  • particlePOP creates and manages built-in particles over time.
  • sourcePOP is common in feedback-style particle systems.

Filters and topology ops reshape or route data:

  • transformPOP, mathPOP, mathmixPOP, mathcombinePOP, normalizePOP, limitPOP, rerangePOP, quantizePOP, trigPOP.
  • noisePOP for built-in noise displacement or attribute generation.
  • attributePOP, attributecombinePOP, attributeconvertPOP, normalPOP.
  • mergePOP, switchPOP, selectPOP, deletePOP, groupPOP, sortPOP, copyPOP, blendPOP, nullPOP.
  • primitivePOP, convertPOP, extrudePOP, subdividePOP, facetPOP, polygonizePOP.

Read the full file on GitHub · 210 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. 10d ago First seen · 210 lines · 42 tokens per session scan A 96ee8c411797

Subscribe to this mod's changes

pop-networks is a skill published in the GitHub repository dylanroscover/Embody (170 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 3,399 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

agentcore-investigation

Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.

awslabs/mcp · 52 tokens

amazon aurora dsql

Deprecated compatibility redirect for Aurora DSQL guidance. Use when a request concerns DSQL, Aurora DSQL, distributed SQL, DSQL schemas, migrations, queries, authentication, performance, or application development.

awslabs/mcp · 46 tokens

vibeue

Unreal Engine 5 development using the VibeUE Python API. Use when working in Unreal Engine — blueprints, state trees, materials, actors, landscapes, animation, niagara, widgets, sound, foliage, gameplay tags, enhanced input, skeletons, PCG (procedural content generation), and more. VibeUE is an extension of Unreal's…

kevinpbuckley/VibeUE · 82 tokens

jmcomic

Search, browse, inspect album-specific or site-wide comments, and download manga from JMComic (18comic), obtain the latest Android APK from hect0x7/JMComic-APK, and invoke the upstream jm-view-server jms command for local reading. Use for manga discovery, ranking, comment analysis, downloads, post-processing…

hect0x7/jmcomic-ai · 101 tokens

testing-python

Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage. Covers test design, fixtures, parameterization, mocking, async testing, and CI integration.

AI-Riksarkivet/ra-mcp · 48 tokens

issue_analyse_supervisor

Autonomous issue analysis — supervisor delegates to engineer subagents.

MarcusJellinghaus/mcp-tools-py · 11 tokens