{"slug": "stop-using-6-chrome-tabs-for-code-reviews-do-it-in-your-terminal", "title": "Stop Using 6 Chrome Tabs for Code Reviews—Do It in Your Terminal", "summary": "A developer shares a terminal-based code review workflow that pipes git diffs through Anthropic's Claude API for instant structural feedback, catching issues like SQL injection and performance problems in seconds. The approach replaces browser-based tools with a bash command, optionally incorporating project context from architecture docs for more relevant reviews. The developer recommends either existing CLI tools or a custom DIY setup, emphasizing consistency and speed over manual review.", "body_md": "You know that moment when you're reviewing a PR and you need to:\n\nYeah. Let's fix that.\n\nBrowser-based code review tools are slow for one simple reason: they're not built for developers who think in terminal commands. You're constantly switching context—reaching for the mouse, squinting at small diffs, waiting for pages to load.\n\nWhat if your code review tool was just... bash?\n\nThere's a trick that changed how I review code. Instead of opening GitHub, I pipe the diff through Claude (or any LLM) and get instant feedback with actual reasoning.\n\nHere's the real command I use:\n\n```\ngit diff origin/main..HEAD | curl https://api.anthropic.com/v1/messages \\\\\n  -H \"x-api-key: $ANTHROPIC_API_KEY\" \\\\\n  -H \"content-type: application/json\" \\\\\n  -d @- | jq '.content[0].text'\n```\n\nDrop that in a function, add some formatting, and you get **structural feedback in seconds** instead of 10 minutes of alt-tabbing.\n\nWhen I used this on a recent refactor, it caught:\n\nTook Claude 3 seconds. I would've spent 15 minutes finding two of those.\n\nLet's say your coworker just pushed this and asked you to review:\n\n```\nfunction fetchUserData(userId) {\n  return db.query(`SELECT * FROM users WHERE id = ${userId}`)\n    .then(data => JSON.stringify(data))\n    .catch(err => err.message)\n}\n```\n\nRunning it through the pipeline:\n\n```\nCritical issue: SQL injection vulnerability - userId is interpolated directly\nPerformance issue: Serializing with JSON.stringify adds latency\nError handling: catching errors as strings means you lose stack traces\nBetter approach: Use parameterized queries, let DB handle serialization\n```\n\nYou can also ask it to **explain the fix**, not just flag problems. Takes 30 seconds for output that would take you 5 minutes to manually review.\n\nNot hyperbole. I timed it.\n\nSometimes. The LLM doesn't know your specific codebase patterns without telling it. So add context:\n\n```\ncat ARCHITECTURE.md | cat - <(git diff origin/main) | send_to_claude\n```\n\nNow it understands your patterns first. Way better reviews.\n\n**Option 1: Use existing tools**\n\n**Option 2: DIY (2 hours of work)**\n\n`review`\n\nand call it with `review HEAD~5`\n\nI went with DIY because my team has specific standards I wanted Claude to enforce.\n\nIt's not that the AI is smarter than you. It's that it's **consistent and fast**. You're not tired after reviewing your 50th PR that day. You're not missing obvious stuff because you've been context-switching for 6 hours.\n\nAnd the feedback is usually *just detailed enough* without being overwhelming. Better than some humans I've worked with, not gonna lie.\n\nThe next level is **semantic analysis**—not just \"this looks wrong\" but \"this contradicts the pattern you established in module-x\". That's hard without buil them in, actually works.\n\nFor now, if you're drowning in PRs, try piping one through Claude. Spend 10 minutes setting it up. You'll save that back in a single review.\n\n**Want to stay sharp on AI tools and productivity tricks?** [Check out LearnAI Weekly](https://learnairesource.com/newsletter)—real strategies from people actually using this stuff, not hype.", "url": "https://wpnews.pro/news/stop-using-6-chrome-tabs-for-code-reviews-do-it-in-your-terminal", "canonical_source": "https://dev.to/learnairesource/stop-using-6-chrome-tabs-for-code-reviews-do-it-in-your-terminal-4n0n", "published_at": "2026-07-13 15:00:31+00:00", "updated_at": "2026-07-13 15:18:02.625529+00:00", "lang": "en", "topics": ["developer-tools", "large-language-models", "ai-tools"], "entities": ["Claude", "Anthropic", "GitHub", "LearnAI Weekly"], "alternates": {"html": "https://wpnews.pro/news/stop-using-6-chrome-tabs-for-code-reviews-do-it-in-your-terminal", "markdown": "https://wpnews.pro/news/stop-using-6-chrome-tabs-for-code-reviews-do-it-in-your-terminal.md", "text": "https://wpnews.pro/news/stop-using-6-chrome-tabs-for-code-reviews-do-it-in-your-terminal.txt", "jsonld": "https://wpnews.pro/news/stop-using-6-chrome-tabs-for-code-reviews-do-it-in-your-terminal.jsonld"}}