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.
npx skills add MattArtzAnthro/gephi-ai --skill teach-with-gephigit clone --depth 1 https://github.com/MattArtzAnthro/gephi-aiWrote 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.
[](https://agentmods.dev/skills/mattartzanthro/gephi-ai/teach-with-gephi)<a href="https://agentmods.dev/skills/mattartzanthro/gephi-ai/teach-with-gephi"><img src="https://agentmods.dev/badge/skills/mattartzanthro/gephi-ai/teach-with-gephi/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.
<a href="https://agentmods.dev/skills/mattartzanthro/gephi-ai/teach-with-gephi"><img src="https://agentmods.dev/badge/skills/mattartzanthro/gephi-ai/teach-with-gephi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.01150 |
| Opus 5 | $0.00024 | $0.00575 |
| Sonnet 5 | $0.00010 | $0.00230 |
| Haiku 4.5 | $0.00005 | $0.00115 |
Grade A, and why
teach-with-gephi 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 87 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
-
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").
-
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. -
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.
-
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_selectionfirst and answer about the exact nodes they selected — never ask them to type node names. -
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.
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.
- 11d ago First seen · 87 lines · 49 tokens per session scan A 93f8e1361150
teach-with-gephi is a skill published in the GitHub repository MattArtzAnthro/gephi-ai (22 stars, last pushed 9d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,150 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.
Other skills, from other repositories
manim-explainer-animation
Provider-independent production workflow for creating Manim-based explainer animations. Use when an agent must plan, code, render, QA, or hand off precise math, science, data, diagram, algorithm, or concept animations with Manim, including storyboard, scene architecture, formulas, coordinate systems, voiceover timing…
proof-writer
A rigorous proof-writing workflow for theorems, lemmas, propositions, and corollaries in machine-learning and AI theory. It can also explain when a claim cannot be proved under its stated assumptions.
agent-challenges
Agent skill for challenges - invoke with $agent-challenges.
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
earth2studio-create-datasource
Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.