gephi-ai AGENTS.md

gephi-ai AGENTS.md is an instructions file for Codex, OpenCode from MattArtzAnthro/gephi-ai. It costs 819 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for an AI coding agent working with Gephi, a desktop application for visualising and analysing networks such as relationships between people or websites. They describe a local MCP server that lets the agent control a running Gephi installation and provide network-analysis guidance.

In plain words
What is it for?
Building, analysing, arranging, styling, and exporting network graphs through Gephi. They also explain how to register the local server with supported coding-agent tools.
Why use it?
They give the agent a defined sequence for checking that Gephi and its plugin are available before doing network work. This reduces setup mistakes and helps it follow the repository’s working practices.

Instructions file for CodexOpenCode

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 instructions/mattartzanthro/gephi-ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/MattArtzAnthro/gephi-ai

Made for: Codex, OpenCode.

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 gephi-ai AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mattartzanthro/gephi-ai/agents-md.svg)](https://agentmods.dev/instructions/mattartzanthro/gephi-ai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mattartzanthro/gephi-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/mattartzanthro/gephi-ai/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 819 This file is loaded in full into every session.
When invoked 819 The same file — it is already loaded in full.
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 $0.00819 $0.00819
Opus 5 $0.00409 $0.00409
Sonnet 5 $0.00164 $0.00164
Haiku 4.5 $0.00082 $0.00082

Measured 5d ago against content hash f0a137811719, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gephi-ai AGENTS.md 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

AGENTS.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gephi AI — Instructions for AI Coding Agents

This repository ships an MCP server (gephi-ai on PyPI) that controls a running Gephi Desktop through a local HTTP API provided by the Gephi AI plugin (gephi-ai-<version>.nbm), plus a portable skill that teaches network-analysis practice. The server exposes 113 tools whose names start with gephi_ (Claude Code shows them as mcp__gephi-mcp__gephi_*).

When a user asks to build, analyze, lay out, style, or export a network, follow this chain:

  1. MCP tools present (tool names start with gephi_): use them. Call gephi_health_check first. It confirms that Gephi Desktop is running with the plugin installed, reports the plugin and server versions, and says whether an update is available. If it fails, tell the user to start Gephi (with the plugin installed from the Releases page) and stop; nothing else works without it.

  2. Your agent supports MCP but the server is not registered: the user can add it with one command. The launcher is the same everywhere; only the registration syntax differs.

    claude mcp add gephi-mcp -- uvx gephi-ai
    codex mcp add gephi-mcp -- uvx gephi-ai
    gemini mcp add -s user gephi-mcp uvx gephi-ai
    

    uvx fetches the current gephi-ai release from PyPI on first run and caches it. Any other MCP client: point it at uvx gephi-ai over stdio.

  3. No MCP at all: there is no fallback. The server talks to Gephi Desktop on 127.0.0.1:8080, so it has to run on the machine where Gephi runs. Say so, and point the user at the README's Install section.

The skill

plugins/claude-code/skills/gephi/ is a self-contained skill folder (SKILL.md plus references/): tool reference, layout guide, statistics guide, filtering, claim verification, text networks, and how to read a network map. It is written for any agent that reads the portable skill format. Install it by copying the folder into your agent's skills directory (~/.codex/skills/, ~/.cursor/skills/, ~/.copilot/skills/, or .agents/skills/ in a project); Claude Code users get it through the plugin, together with slash commands and subagents that only Claude Code can run.

Read the full file on GitHub · 65 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 · 65 lines · 819 tokens per session scan A f0a137811719

Subscribe to this mod's changes

gephi-ai AGENTS.md is an instructions file published in the GitHub repository MattArtzAnthro/gephi-ai (21 stars, last pushed 4d ago), licensed Apache-2.0. It adds 819 tokens to every session, about $0.0041 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.