Review pull requests by what the code does, not only the diff
Built Perspica, a semantic diff that explains what changes do and the concepts behind them for AI-era code review.
Source
sshah03 on Hacker News · 2026-09-30 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-15.
What they did
Built Perspica, a semantic diff that explains what changes do and the concepts behind them for AI-era code review.
Result (as claimed)
Open-sourced semantic review aid after heavy coding-agent use.
Tools they used
Cost: Claude Code: free plan, paid from $17/mo; OpenAI Codex: free plan, paid from $8/mo. Checked 2026-10-14.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Claude Code, OpenAI Codex. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Review pull requests by what the code does, not only the diff What the original author did: Built Perspica, a semantic diff that explains what changes do and the concepts behind them for AI-era code review. Reported result (as claimed by the author): Open-sourced semantic review aid after heavy coding-agent use. Source: https://news.ycombinator.com/item?id=49914005 Tools they used: Claude Code, OpenAI Codex Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Review pull requests by what the code does, not only the diff What the original author did: Built Perspica, a semantic diff that explains what changes do and the concepts behind them for AI-era code review. Reported result (as claimed by the author): Open-sourced semantic review aid after heavy coding-agent use. Source: https://news.ycombinator.com/item?id=49914005 Tools they used: Claude Code, OpenAI Codex Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Review pull requests by what the code does, not only the diff What the original author did: Built Perspica, a semantic diff that explains what changes do and the concepts behind them for AI-era code review. Reported result (as claimed by the author): Open-sourced semantic review aid after heavy coding-agent use. Source: https://news.ycombinator.com/item?id=49914005 Tools they used: Claude Code, OpenAI Codex Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Related use cases
Wake up to pull requests your agents finished overnight
Uses Firstmate so one agent in Claude Code orchestrates other coding agents overnight.
Chat with Claude Code and OpenClaw from the Mac menu bar
Built Littleguys, a WhatsApp-style Mac menu bar app for Claude Code, Codex and OpenClaw agents.
Cut Claude Code spend with a planner plus cheap worker models
Built Agent Orchestra so a main model plans and checks while cheaper models do read and search work.
Manage Claude Code, Codex and Grok agents from one workspace
Built Offrun to run Claude Code, Codex, AGY and Grok Build side by side and see who needs attention and what usage remains.