Guides on auto-generated documentation, MCP tools for AI agents, git intelligence, and how repowise compares to other tools.
We ran the same MCP servers and questions on two agent harnesses. Under Claude Code most tools were barely called at all. Here is the measured cause of it.
repowise is developed against an index of itself: every pull request is gated by the same risk and health checks we ship. The setup, measurements, and limits.
We ran the same MCP servers and questions on two agent harnesses. Under Claude Code most tools were barely called at all. Here is the measured cause of it.
The same tool on the same codebase gives 35.6x fewer tokens on one measurement and 15.9% on another. Both are correct, and they measure different things.
A tool that never called its own server measured 43% cheaper than a bare agent. Prompt caching explains it, and it shows why dollar-cost benchmarks mislead.
JetBrains reran two token-saving claims and both collapsed. Here is the eight-part methodology we used to build a benchmark that survives an independent rerun.
We ran a sealed retrieval benchmark against four open source tools, scored last at 0.228, published it, found the bug, fixed it, and reran the sealed half once.
repowise is developed against an index of itself: every pull request is gated by the same risk and health checks we ship. The setup, measurements, and limits.
What CLAUDE.md and AGENTS.md are, what to put in them, best practices, and how to keep them fresh automatically. Learn to give coding agents real repo context.
Code health is a defect-validated measure of how risky code is to change, scored from 49 deterministic markers across three pillars. Reproduce it on your repo.
Living codebase documentation rebuilds on every commit, scores its own freshness, and feeds AI agents. Learn how it works and start with repowise free.
Git intelligence reads your git history to surface hotspots, code ownership, bus factor, and change coupling. Learn how the signals work and where to start.
Prioritize technical debt by impact-per-effort: rank refactoring targets, find dead code, and read coverage as risk. Build your ranked worklist today.
Codebase context for AI agents turns one index into 10 task-shaped MCP tools, cutting real agent-loop output tokens 31.6% on Codex. See how structured context works, try repowise.