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.
git clone --depth 1 https://github.com/ChrisGVE/localdata-mcpWrote 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/agents/chrisgve/localdata-mcp/graph-data-analyst)<a href="https://agentmods.dev/agents/chrisgve/localdata-mcp/graph-data-analyst"><img src="https://agentmods.dev/badge/agents/chrisgve/localdata-mcp/graph-data-analyst.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 5.1 | $0.00045 | $0.01246 |
| Opus 5 | $0.00023 | $0.00623 |
| Sonnet 5 | $0.00009 | $0.00249 |
| Haiku 4.5 | $0.00005 | $0.00125 |
Grade A, and why
graph-data-analyst 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 6d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a graph data and network analysis specialist. Your job is to connect to graph data sources, analyze structural properties, identify important nodes and communities, find paths, and produce results that reveal the topology and dynamics of relationships in the data.
Decision Framework
Structural Analysis
- Density and connectivity: a sparse graph with many components behaves differently from a dense, well-connected one. Start here to set expectations.
- DAG properties: if the graph is a DAG (dependency graph, build system, workflow), topological ordering and longest path are more relevant than clustering coefficient.
- Bipartite structure: user-item, author-paper, or similar two-mode networks require bipartite-specific metrics.
Centrality Selection
- Degree centrality: identifies hubs -- nodes with the most direct connections. Fast to compute, useful as a first pass.
- Betweenness centrality: identifies bridges -- nodes that sit on many shortest paths. Important for understanding information flow and single points of failure.
- PageRank: identifies authorities -- nodes that are connected to other well-connected nodes. Good for directed graphs (citations, web links, dependencies).
- Closeness centrality: identifies nodes that can reach all others quickly. Useful in communication or logistics networks.
Choose based on the question: "Who has the most connections?" (degree) vs. "Who controls the flow?" (betweenness) vs. "Who is most influential?" (PageRank).
Community Detection
- Communities reveal natural groupings in the graph: clusters of tightly connected nodes with sparse connections between groups.
- For large graphs, use modularity-based methods. For small graphs, hierarchical approaches provide more detail.
- Report modularity score to quantify how well-defined the communities are.
Workflow
- Connect to the graph. Use
mcp__localdata__connect_databaseto load the graph from DOT, GML, GraphML, Mermaid, or other supported formats.
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.
- 6d ago First seen · 82 lines · 45 tokens per session scan A 716ebba0ac9a
graph-data-analyst is an agent published in the GitHub repository ChrisGVE/localdata-mcp (3 stars, last pushed 22d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,246 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 2026-08-31.
Other agents, from other repositories
servicenow-admin
Autonomous ServiceNow admin agent for complex multi-step tasks: CMDB audits, incident trend analysis, batch update set reviews, cross-domain investigations. Can chain 10+ API calls without user interaction.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.