graph-explore

Name: graph-explore
Availability: InStock
Author: romaindecoster

Query the Graphify knowledge graph and summarize architectural context in ≤300 tokens.

1|Updated Mar 27, 2026

Search Tags:#BMAD #graph #knowledge-graph #mcp-tools #graphify #architectural-summary

Ready to run

npx skills add https://github.com/RomainDECOSTER/ironforge --skill graph-explore

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: graph-explore
Source: https://github.com/RomainDECOSTER/ironforge/tree/main/copilot/skills/graph-explore
Command: npx skills add https://github.com/RomainDECOSTER/ironforge --skill graph-explore

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent that queries the Graphify knowledge graph to produce a concise, ≤300-token architectural summary, helping BMAD phases plan efficiently.

Core Features & Use Cases

Queries the Graphify knowledge graph to fetch architectural context for the current codebase.
Synthesizes findings into a structured, ≤300-token summary suitable for BMAD phases (analyze, implement, full-workflow).
Enforces safe operation by routing all MCP tool calls through this subagent instead of direct main-session usage.

Quick Start

Ask a single architectural question and run Graph Explore to get a concise knowledge-graph summary.

Frequently Asked Questions about graph-explore

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract architectural context from a knowledge graph for planning?▼

Extract architectural context by querying the Graphify knowledge graph to summarize modules and dependencies into a concise, structured output. This approach limits tool calls and routes them through a subagent to deliver a ≤300-token summary that directly informs planning phases.

Can I use a subagent to summarize codebase dependencies for BMAD phases?▼

Yes, you can use a subagent to fetch and synthesize codebase dependencies for BMAD phases. The subagent queries the Graphify MCP server tools and returns a ≤300-token architectural summary, ensuring safe operation by preventing direct main-session MCP calls.

What is the best way to get a concise architectural summary for software planning?▼

The best way to get a concise architectural summary is to query a knowledge graph for module and dependency context. By routing MCP tool calls through a subagent, you synthesize findings into a ≤300-token output, keeping the main session clean and focused for planning.

Does Graph Explore require direct MCP server calls in the main session?▼

No, Graph Explore does not require direct MCP server calls in the main session. It enforces safe operation by routing all Graphify MCP tool interactions through the subagent, which then returns the final ≤300-token architectural summary to the main session.

Why limit architectural summaries to 300 tokens during BMAD phase planning?▼

Limiting architectural summaries to 300 tokens during BMAD phase planning ensures the output remains concise and immediately actionable. This constraint forces the subagent to synthesize only essential module, dependency, and structural context from the knowledge graph, preventing context overload.