I spent 3.8 million tokens finding which service to change

Description and use

In a large monorepo with many microservices, identifying affected services initially required massive token usage due to large graph artifacts. By combining lightweight markdown descriptors with Graphify for deep analysis, token consumption dropped to 61k, making the process practical.

Problem

Determining which microservices in a large monorepo are affected by a new spec is costly and inefficient when relying on a single tool.

Outcome

The two-layer approach cuts token usage from millions to tens of thousands, enabling practical agent-driven routing in large monorepos.

Workflow

• 1. Run Graphify on a single service to generate a structural graph (graph.json).
• 2. Generate a lightweight markdown descriptor per service containing typed frontmatter and links to neighbors.
• 3. For a spec, first query the markdown descriptors to identify candidate services (≈676 tokens per service).
• 4. For each candidate, run Graphify locally on that service to compute precise impact radius (few hundred tokens).
• 5. Aggregate results to determine affected services and detailed changes.
• 6. Use the catalogified data for agent-driven routing and impact analysis.

Evidence

Graphify is superb at the second one. graphify affected "UpdateApiUsageCount" --depth 2 gives you a precise impact radius in a few hundred tokens.

Source

One service entry 2.6 KB, 676 tokens. Ninety of those is 61,000 tokens.

Source