visualize-network

visualize-network is a skill for Claude Code, Codex from MattArtzAnthro/gephi-ai. It costs 56 tokens per session (725 once invoked), scanned A, original, Apache-2.0.

A workflow for arranging and styling a graph in Gephi, a desktop tool for exploring networks of connected items.

In plain words
What is it for?
Use it to lay out publication-ready network diagrams, size nodes by connections, color communities, quieten edges, and fix items that are hidden or hard to read.
Why use it?
It turns a cluttered graph into a readable map by checking the data, choosing a layout, highlighting groups, and reviewing the result visually.

Skill for Claude CodeCodex

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/mattartzanthro/gephi-ai/visualize-network
Any agent
npx skills add MattArtzAnthro/gephi-ai --skill visualize-network
Clone the repo
git clone --depth 1 https://github.com/MattArtzAnthro/gephi-ai

Made for: Claude Code, Codex.

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 visualize-network

README.md
[![agentmods](https://agentmods.dev/badge/skills/mattartzanthro/gephi-ai/visualize-network.svg)](https://agentmods.dev/skills/mattartzanthro/gephi-ai/visualize-network)
Your own site
<a href="https://agentmods.dev/skills/mattartzanthro/gephi-ai/visualize-network"><img src="https://agentmods.dev/badge/skills/mattartzanthro/gephi-ai/visualize-network.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 725 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 $0.00056 $0.00725
Opus 5 $0.00028 $0.00362
Sonnet 5 $0.00011 $0.00145
Haiku 4.5 $0.00006 $0.00072

Measured 5d ago against content hash 22095c94e54a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visualize-network 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.

plugins/gephi-network-analysis/skills/visualize-network/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visualize a Network

Style and lay out the live graph in place. The goal is a map where real structure is visible, hubs are legible, edges are informative but quiet, and nothing is accidentally invisible.

Read ../gephi/references/layout-guide.md for layout selection and its symptom-to-fix table. Read ../gephi/references/reading-network-maps.md for the caption and interpretation discipline.

Iterative Loop

  1. Health and baseline. Call gephi_health_check, then gephi_get_graph_stats and gephi_visual_qa. Stop if Gephi is unavailable or the graph is empty. Use a requested partition column; otherwise prefer modularity_class, a clearly categorical column, or computed communities.
  2. Data-truth gate. Run gephi_visual_qa with the partition column. If its verdict is none, do not color by that attribute. Compute communities with gephi_compute_modularity and use modularity_class, or proceed without community color.
  3. Style. Compute degree if needed. Apply the validated eight-color partition palette with gray beyond eight communities, size nodes by degree, and set preview defaults from the gephi skill. Use subdued source-colored edges for most networks and neutral gray for dense text networks.
  4. Layout. Run the layout selected by the layout guide. For ForceAtlas 2, use synchronous execution, LinLog, size-appropriate scaling, and measured weight handling. Finish with Noverlap.
  5. Inspect. Run gephi_visual_qa, export a small diagnostic PNG, and inspect it. Check overview separation and close-up node legibility.
  6. Adjust one variable. Diagnose the symptom, change exactly one layout or preview parameter, rerun a short pass, and measure again. Repeat up to three times or until the QA warnings are resolved and both zoom levels read well.
  7. Label and export. Add cluster captions only when they have evidence-based names. Use extent.suggested_export for the canvas, scale up for publication, and export to the requested destination. Offer gephi_view_graph when the host supports MCP Apps.

Read the full file on GitHub · 60 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 · 60 lines · 56 tokens per session scan A 22095c94e54a

Subscribe to this mod's changes

visualize-network is a skill published in the GitHub repository MattArtzAnthro/gephi-ai (21 stars, last pushed 3d ago), licensed Apache-2.0. It adds 56 tokens to every session and 725 once invoked, about $0.0003 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.