Codebase intelligence, explained
Guides on auto-generated documentation, MCP tools for AI agents, git intelligence, and how repowise compares to other tools.
All posts
How the repowise PR Bot Comments Only When It Matters
pr bot silent default is the only sane default for review automation. A GitHub PR bot should stay out of the way on green changes, then speak only when it…
Use git history to catch stale ADRs before they mislead agents
Use git history to flag stale decisions in an architecture decision records workflow. Catch drift early with a 500-commit view before agents follow old code.
AI Code Review Tools Fail When They Ignore Ownership
AI code review tools catch lint, but miss ownership. See how local history and nearby changes cut bad reviews and surface the right reviewer.
Codebase intelligence is becoming the missing layer for agents
Why the codebase intelligence category is replacing raw file access: git history, ownership, and memory cut bad changes and speed agent work.
What Model Context Protocol actually sends to Claude Code
See how model context protocol sends structured repo data to Claude Code, with a wire-level example and 7 tools to inspect.
Audit a Flask monolith before acquisition with graph, history, wiki, ADRs
Run a pre-acquisition code audit on a Flask monolith with graph, git history, wiki freshness, and ADRs. Find surprises before week two.
Codebase RAG Breaks on Git History, Not Embeddings
Why the codebase rag landscape fails after the first lookup: 4 indexing layers, 7 agent tools, and a cleaner path to ownership and change context.
Why vector-only retrieval misses co-change clusters in monorepos
Co-change analysis git shows which files move together, who owns them, and what breaks next. See why vector-only retrieval misses refactor signals.
Audit a legacy monolith before acquisition with graph, history, wiki, ADRs
Audit legacy code with graph, history, wiki, and ADRs to answer ownership, risk, and rewrite questions before a deal. See 4 layers in one review.
Our git co-change model failed on a monorepo refactor
Why co-change analysis git overfit a monorepo refactor, and the guardrails we added after 500 commits of history pointed at the wrong coupling.
Generate a CLAUDE.md from your repo’s ADRs and wiki
Generate claude.md from ADRs and wiki into a day-one agent brief: 1 file, clear rules, and links to the decisions that matter most.
Developer productivity metrics that survive AI coding agents
Developer productivity metrics should track reruns, tool calls, context churn, and time-to-first-correct-edit. Use 4 signals to replace vanity counts.