graphify-usagelisted

# Graphify Usage Query the knowledge graph effectively, interpret results accurately, and stay within token budgets. ## Overview The graphify MCP server exposes the codebase as a pre-built knowledge graph stored in `graphify-out/graph.json`. The graph encodes structural relationships between concepts, modules, and files extracted by the graphify pipeline. This skill governs when, how, and with what discipline agents should query it. **Owner**: Riko (Explorer Agent) — Riko is the primary graph query agent and owns interpretation of results. **Consumers**: Senku (Planner Agent), Lawliet (Reviewer Agent) — both may consult the graph during planning and review, but Riko is the preferred query agent for deep exploration. **Out of scope**: Loid (Executor) and Alphonse (Verifier) do NOT have graph access by design. Loid performs file writes and needs test output, not structural queries; Alphonse runs verification commands that cannot rely on graph freshness. This enforces the one-writer invariant: only agents that need structural context hold graph tool permissions. All 7 tools are accessed via the MCP prefix `mcp__plugin_agent-flow_graphify__*`. See [references/tool-reference.md](references/tool-reference.md) for full signatures. --- ## When to Query the Graph vs. Grep Use the graph when you need structural relationships. Use grep when you need literal text matches. | Trigger condition | Preferred approach | |---|---| | "What modules import X?" / dependency mapping | Graph