--- title: "Scott Thurman (@scottthurman89) | Hashnode" description: "Tools that help engineers ship better code, faster. Read the latest articles by Scott Thurman on Hashnode." url: "https://hashnode.com/@scottthurman89" --- @scottthurman89 # Scott Thurman @scottthurman89 · Joined May 2026 Tools that help engineers ship better code, faster. ### [Four .cursorrules files that turn Cursor chat into a focused code reviewer](https://scottthurman.hashnode.dev/four-cursorrules-files-that-turn-cursor-chat-into-a-focused-code-reviewer?utm_source=hashnode&utm_medium=feed) Cursor's chat is great at writing code. It is mediocre at reviewing it. The default behavior is conversational - "looks good, here are some suggestions" - which is the wrong mode for a review. A revie 4 min read · [scottthurman.hashnode.dev](https://scottthurman.hashnode.dev/four-cursorrules-files-that-turn-cursor-chat-into-a-focused-code-reviewer?utm_source=hashnode&utm_medium=feed) [May 12](https://hashnode.com/posts/four-cursorrules-files-that-turn-cursor-chat-into-a-focused-code-reviewer/6a03632a937b84f779ae2c90) ### [prpack v0.2.0: autonomous review mode lands](https://scottthurman.hashnode.dev/prpack-v0-2-0-autonomous-review-mode-lands?utm_source=hashnode&utm_medium=feed) The first version of prpack had one job: pack the right review context and get out of the way. That was deliberate. The failure mode I kept seeing was not "the model is bad at code review." It was "th 4 min read · [scottthurman.hashnode.dev](https://scottthurman.hashnode.dev/prpack-v0-2-0-autonomous-review-mode-lands?utm_source=hashnode&utm_medium=feed) [May 11](https://hashnode.com/posts/prpack-v0-2-0-autonomous-review-mode-lands/6a01776ea63f995f5f876fcf) ### [AI PR review tools in 2026: where prpack fits](https://scottthurman.hashnode.dev/ai-pr-review-tools-in-2026-where-prpack-fits?utm_source=hashnode&utm_medium=feed) AI PR review is not one category anymore. In 2026, the tools split into three buckets. The first bucket is the GitHub or GitLab reviewer bot. It comments on a pull request, tries to catch bugs, and ma 9 min read · [scottthurman.hashnode.dev](https://scottthurman.hashnode.dev/ai-pr-review-tools-in-2026-where-prpack-fits?utm_source=hashnode&utm_medium=feed) [May 11](https://hashnode.com/posts/ai-pr-review-tools-in-2026-where-prpack-fits/6a0171380dc47f5a5d11c863) ### [Add an LLM PR reviewer to your GitHub Actions in 5 minutes (no API key)](https://scottthurman.hashnode.dev/add-an-llm-pr-reviewer-to-your-github-actions-in-5-minutes-no-api-key?utm_source=hashnode&utm_medium=feed) Most "AI code review" GitHub Actions need either a paid platform account, an OpenAI/Anthropic API key sitting in your repo secrets, or both. Both are friction. The first costs ongoing money; the secon 5 min read · [scottthurman.hashnode.dev](https://scottthurman.hashnode.dev/add-an-llm-pr-reviewer-to-your-github-actions-in-5-minutes-no-api-key?utm_source=hashnode&utm_medium=feed) [May 11](https://hashnode.com/posts/add-an-llm-pr-reviewer-to-your-github-actions-in-5-minutes-no-api-key/6a016de20dc47f5a5d0f08f6) ### [A reproducible test: Claude reviews the same PR twice, with and without context](https://scottthurman.hashnode.dev/a-reproducible-test-claude-reviews-the-same-pr-twice-with-and-without-context?utm_source=hashnode&utm_medium=feed) Most of what I read about LLM code review is "we tried it, it works." That's not enough to be useful. I want to know: same model, same PR, two different review contexts - does the output actually chan 5 min read · [scottthurman.hashnode.dev](https://scottthurman.hashnode.dev/a-reproducible-test-claude-reviews-the-same-pr-twice-with-and-without-context?utm_source=hashnode&utm_medium=feed) [May 11](https://hashnode.com/posts/a-reproducible-test-claude-reviews-the-same-pr-twice-with-and-without-context/6a0164b00dc47f5a5d093bd6)