teach

teach is a command for coding agents from MattArtzAnthro/gephi-ai. It costs 15 tokens per session (1,145 once invoked), scanned A, original, Apache-2.0.

A teaching workflow for analyzing networks in Gephi, a desktop program that shows relationships between connected items. It narrates each visible step so a viewer can follow how the graph is imported, arranged, and explored.

In plain words
What is it for?
Use it for live lessons, demonstrations, and watch-along sessions in Gephi. It helps explain layouts, groups of connected nodes, important hubs, and changes in the displayed graph.
Why use it?
It makes network analysis easier to understand by connecting each operation with what the viewer should see and why it matters. It prevents large, unexplained operations that are difficult to follow.

Command

Part of the gephi-network-analysis plugin — 1 skill, 11 commands, 4 agents, 1 hook, 1 MCP server 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 commands/mattartzanthro/gephi-ai/teach
Clone the repo
git clone --depth 1 https://github.com/MattArtzAnthro/gephi-ai

Or install gephi-network-analysis, the plugin that ships this one along with the rest of its 1 skill, 11 commands, 4 agents, 1 hook, 1 MCP server.

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 teach

README.md
[![agentmods](https://agentmods.dev/badge/commands/mattartzanthro/gephi-ai/teach.svg)](https://agentmods.dev/commands/mattartzanthro/gephi-ai/teach)
Your own site
<a href="https://agentmods.dev/commands/mattartzanthro/gephi-ai/teach"><img src="https://agentmods.dev/badge/commands/mattartzanthro/gephi-ai/teach.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,145 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 $0.00015 $0.01145
Opus 5 $0.00008 $0.00573
Sonnet 5 $0.00003 $0.00229
Haiku 4.5 $0.00002 $0.00114

Measured 5d ago against content hash 6ef2e164f615, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

teach 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/claude-code/commands/teach.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teaching Mode

Run a network analysis in Gephi Desktop as a narrated, watch-along session: the human is looking at the Gephi window while you work, and your job is to make every step visible and understandable. This mode exists because watching the instrument operate is how people learn what network analysis actually does.

The contract: never do anything the viewer can't follow.

Rules

  1. Narrate first, act second. Before every operation, one or two plain sentences: what you are about to do, what they should watch for, and why it matters ("I'm going to run ForceAtlas 2 now — watch the tangle pull apart into clumps; each clump is a group of nodes more connected to each other than to the rest").

  2. Direct their eyes with gephi_focus_view. After building or importing, fit the whole graph (mode "graph"). Before discussing a cluster, center on its region or hub and select its nodes so they light up. After a layout, re-fit. The viewer should never have to hunt for what you're describing.

  3. Run layouts in visible chunks. Never one 1000-iteration blast — use 200-300 iteration passes (sync true) with narration between: "seeing the big shape now — next pass will tighten the clusters." The settling motion IS the lesson.

  4. Pause for observation. After each visible change, stop and invite them in: "Take a look — what do you notice about the top-right group?" Wait for their answer before continuing. Their observations drive the pace, not your plan.

    Tell them they can point. Early in the session, show them the rectangle-selection tool (dashed-square icon, thin toolbar on the left edge of the canvas): dragging a box around nodes is a way of asking about them, and the selection stays lit while they type. When they use deictic words ("these", "this group", "what did I grab?"), read gephi_get_selection first and answer about the exact nodes they selected — never ask them to type node names.

  5. Explain choices as you make them. Gravity 0 and LinLog aren't incantations — say what each does in one sentence when you set it. Same for the validated palette, sizing by degree, and edge opacity.

Read the full file on GitHub · 88 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 · 88 lines · 15 tokens per session scan A 6ef2e164f615

Subscribe to this mod's changes

teach is a command published in the GitHub repository MattArtzAnthro/gephi-ai (21 stars, last pushed 4d ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,145 once invoked, about $0.0001 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.