Show HN: Tracking AI Code with Git AI
Show HN (score: 6)Description
Think 'git blame' but for AI code. There's a lot about how it works in the post, but wanted to share how it's been impacting me + my team:
- I find I review AI code very differently than human code. Being able to see the prompts my colleagues used, what the AI wrote, and where they stepped in to override has been extraordinarily helpful. This is still very manual today, but hope to build more UI around it soon.
- “Why is this here?” — more than once I’ve giving my coding agent access to the past prompts that generated code I’m looking at, which lets the Agent know what my colleague was thinking when they made the change. Engineers talk to AI all day now…their prompts are sort of like a log of thoughts :)
- I pay a lot of attention to the lines generated for every 1 accepted ratio. If it gets up over 4 or 5 it means I’m well outside the AI’s distribution or prompting poorly — either way, it’s a good cause for reflection and I’ve learned a lot about collaborating with LLMs.
This has been really fun to build, especially because some amazing contributors who were working on similar projects came together and directed their efforts towards Git AI shine. We hope you like it.
More from Show
Show HN: Control Claude permissions using a cloud-based decision table UI
Show HN: Control Claude permissions using a cloud-based decision table UI We’ve been building visual rule engines (clear interfaces + API endpoints that help map input data to a large number of outcomes) for a while and had the fun idea lately to see what happens when we use our decision table UI with Claude’s PreToolUse hook.<p>The result is a surprisingly useful policy/gating layer– these tables let your team:<p>- Write multi-factor, exception-friendly policies (e.g. deny rm -rf / when --force; allow cleanup only in node_modules; ask on network calls like curl/wget; block kubectl delete or SQL DROP, each with a clear reason)<p>- Roll out policy changes instantly (mid-run, flip a risky operation from allow → ask; the next attempt across devs and agents is gated immediately– no git pull, agent restart, or coordination)<p>- Adopt lightweight governance that is somewhat agent agnostic and survives churn (MCP/skills/etc)- just add columns/rules as new tools and metadata show up<p>- Get a quick central utility to understand which tools are being used, which tools get blocked most often, and why
Show HN: Claude Code Scheduler
Show HN: Claude Code Scheduler I found myself frequently wanting to schedule tasks in Claude Code (both one-time and recurring) so I built a CC plugin to help with that.<p>To install: /plugin marketplace add jshchnz/claude-code-scheduler /plugin install scheduler@claude-code-scheduler<p>Then just tell Claude what you want (some examples):<p>Every Wednesday at 3am find dead code: unused functions, unreachable branches, commented-out code, and unused imports. List by file with line numbers.<p>Schedule a code review every weekday at 9am. Review commits from the last 24 hours, check for bugs, security issues, error handling gaps, and code that needs comments. Summarize with file:line references.
Show HN: Webctl – Browser automation for agents based on CLI instead of MCP
Show HN: Webctl – Browser automation for agents based on CLI instead of MCP
Show HN: Tsonic – A TypeScript to native code compiler via CLR and NativeAOT
Show HN: Tsonic – A TypeScript to native code compiler via CLR and NativeAOT
No other tools from this source yet.