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 agentmods add skills/mattartzanthro/gephi-ai/explore-networknpx skills add MattArtzAnthro/gephi-ai --skill explore-networkgit 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/explore-network)<a href="https://agentmods.dev/skills/mattartzanthro/gephi-ai/explore-network"><img src="https://agentmods.dev/badge/skills/mattartzanthro/gephi-ai/explore-network.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00048 | $0.00718 |
| Opus 5 | $0.00024 | $0.00359 |
| Sonnet 5 | $0.00010 | $0.00144 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
explore-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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore
Run the initial exploration on the graph in the current Gephi workspace. This is the import-and-explore workflow without the import step: open the file in Gephi first (File > Open, or a Data Laboratory import), then run this. No file path is needed.
Tell the user what you're doing at each step — narrate briefly before each tool call.
Steps
-
Health check: Call
gephi_health_check. If it fails, tell the user to start Gephi and stop. -
Confirm there is a graph: Call
gephi_get_project_info. If there is no project or the graph is empty, say so and suggest opening a file in Gephi or using theimport-and-exploreskill with a path; stop. -
The intake question (skip if they already told you): in one friendly question, ask what the nodes and connections are and what they hope to learn. Their answer sets the vocabulary for everything you present, and their expectations become hypotheses to test rather than assumptions.
-
Profile: Call
gephi_profile_graph(one call, the full quantitative picture). Give a short plain-language first reading that combines their description with the numbers, then ask the two or three questions the profile raises (itsflagsare candidates: isolates, fragmentation, hub dominance). -
Let the intake + profile guide what follows — do not run a fixed recipe:
- Isolates or fragmentation: ask before removing anything (their "data problem" may be their finding).
- Their stated interest picks the metric (brokers/gatekeepers -> betweenness; influence/reach -> degree or PageRank; roles -> the similarity layout).
- If they named an attribute they expect to organize the network, test it against the partition baseline before coloring by it; prefer detected communities when their attribute fails, and say so plainly.
- Size and density pick the layout per the layout guide's purpose table.
- Caption clusters in their vocabulary, not in cluster numbers.
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.
- 5d ago First seen · 58 lines · 48 tokens per session scan A bbdda67a1cb5
explore-network is a skill published in the GitHub repository MattArtzAnthro/gephi-ai (21 stars, last pushed 4d ago), licensed Apache-2.0. It adds 48 tokens to every session and 718 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
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.