I've been building https://crit.md to keep that back and forth with agents - GitHub-esque interface and have agents respond to my feedback, iterating until I'm happy.
Admittedly like many others, I use it a lot less for actual plans now, models are indeed getting really good at just getting it.
I wodner what this product space will look like a year from now. Reviews are already dying."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Plan mode is dead"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://www.aymannadeem.com/artificial/intelligence,/developer/tools/2026/09/24/plan-mode-is-dead.html"}},"_tags":["comment","author_tomasztomczyk","story_49840054"],"author":"tomasztomczyk","comment_text":"I also didn't like the chat TUI for back and forth on things, especially on long markdown files where I felt like I needed to copy a line to comment on it. I wonder if LLM companies would rather skip a step and aim for a world where most people one-shot things, which sounds much more impressive.
I've been building https://crit.md to keep that back and forth with agents - GitHub-esque interface and have agents respond to my feedback, iterating until I'm happy.
Admittedly like many others, I use it a lot less for actual plans now, models are indeed getting really good at just getting it.
I wodner what this product space will look like a year from now. Reviews are already dying.","created_at":"2026-09-26T15:25:27Z","created_at_i":1790436327,"objectID":"49857455","parent_id":49854075,"story_id":49840054,"story_title":"Plan mode is dead","story_url":"https://www.aymannadeem.com/artificial/intelligence,/developer/tools/2026/09/24/plan-mode-is-dead.html","updated_at":"2026-09-26T16:55:49Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"tomasz-tomczyk"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crit",".","md"],"value":"Same experience here - I built a similar tool, for reviewing both plans and code - https://crit.md (shameless plug), browser based as opposed to TUI.
Having said that, I don't review the code until going through a few iterations of reviews from Claude. Each round it does find some "obvious" issue, so as long as I'm not close to maxing my subscription for the week I let it run an audit -> validator checks the claims -> fix issues before I get to it."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: adamsreview \u2013 better multi-agent PR reviews for Claude Code"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/adamjgmiller/adamsreview"}},"_tags":["comment","author_tomasz-tomczyk","story_48090276"],"author":"tomasz-tomczyk","comment_text":"Same experience here - I built a similar tool, for reviewing both plans and code - https://crit.md (shameless plug), browser based as opposed to TUI.
Having said that, I don't review the code until going through a few iterations of reviews from Claude. Each round it does find some "obvious" issue, so as long as I'm not close to maxing my subscription for the week I let it run an audit -> validator checks the claims -> fix issues before I get to it.","created_at":"2026-05-11T21:00:40Z","created_at_i":1778533240,"objectID":"48100625","parent_id":48091999,"story_id":48090276,"story_title":"Show HN: adamsreview \u2013 better multi-agent PR reviews for Claude Code","story_url":"https://github.com/adamjgmiller/adamsreview","updated_at":"2026-05-11T21:01:45Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"tomasz-tomczyk"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crit",".","md"],"value":"It's been three months now of building Crit - https://crit.md - local first, open source tool for reviewing markdown and code output from your favourite AI agent.
It's inspired by GitHub PR review workflow, only with quick iterations and local.
It's been great! I found some dedicated users, dogfooding it every day with Claude and starting to get more contributions from the little community. We just got accepted into Homebrew core which was my target.
I'm expanding the team features now as I've got a few users keen to get the sharing service deployed in their private networks!"},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: What are you working on? (May 2026)"}},"_tags":["comment","author_tomasz-tomczyk","story_48085993"],"author":"tomasz-tomczyk","comment_text":"It's been three months now of building Crit - https://crit.md - local first, open source tool for reviewing markdown and code output from your favourite AI agent.
It's inspired by GitHub PR review workflow, only with quick iterations and local.
It's been great! I found some dedicated users, dogfooding it every day with Claude and starting to get more contributions from the little community. We just got accepted into Homebrew core which was my target.
I'm expanding the team features now as I've got a few users keen to get the sharing service deployed in their private networks!","created_at":"2026-05-10T20:37:31Z","created_at_i":1778445451,"objectID":"48087720","parent_id":48085993,"story_id":48085993,"story_title":"Ask HN: What are you working on? (May 2026)","updated_at":"2026-05-10T20:39:26Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"tomasz-tomczyk"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crit",".","md"],"value":"https://crit.md - a CLI tool for reviewing AI coding agent output like a GitHub PR.
I got frustrated with Claude Code and Cursor producing plausible-but-wrong changes with no easy way to annotate and push back, without making a full PR. crit makes the review stage fun again!
Works on both plans as well as code itself. It\u2019s been very rewarding hearing from folks who use it, everyone has been very kind! My most successful side project already :)
GitHub: https://github.com/tomasz-tomczyk/crit"},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: What Are You Working On? (April 2026)"}},"_tags":["comment","author_tomasz-tomczyk","story_47741527"],"author":"tomasz-tomczyk","children":[47746294,47746659],"comment_text":"https://crit.md - a CLI tool for reviewing AI coding agent output like a GitHub PR.
I got frustrated with Claude Code and Cursor producing plausible-but-wrong changes with no easy way to annotate and push back, without making a full PR. crit makes the review stage fun again!
Works on both plans as well as code itself. It\u2019s been very rewarding hearing from folks who use it, everyone has been very kind! My most successful side project already :)
GitHub: https://github.com/tomasz-tomczyk/crit","created_at":"2026-04-13T00:42:37Z","created_at_i":1776040957,"objectID":"47746165","parent_id":47741527,"story_id":47741527,"story_title":"Ask HN: What Are You Working On? (April 2026)","updated_at":"2026-04-25T00:15:46Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"tomasz-tomczyk"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crit",".","md"],"value":"https://crit.md - a CLI tool for reviewing AI coding agent output like a GitHub PR.
I got frustrated with Claude Code and Cursor producing plausible-but-wrong changes with no easy way to annotate and push back, without making a full PR. crit makes the review stage fun again!
Works on both plans as well as code itself. It\u2019s been very rewarding hearing from folks who use it, everyone has been very kind! My most successful side project already :)
GitHub: https://github.com/tomasz-tomczyk/crit"},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: What Are You Working On? (April 2026)"}},"_tags":["comment","author_tomasz-tomczyk","story_47639039"],"author":"tomasz-tomczyk","children":[47641155],"comment_text":"https://crit.md - a CLI tool for reviewing AI coding agent output like a GitHub PR.
I got frustrated with Claude Code and Cursor producing plausible-but-wrong changes with no easy way to annotate and push back, without making a full PR. crit makes the review stage fun again!
Works on both plans as well as code itself. It\u2019s been very rewarding hearing from folks who use it, everyone has been very kind! My most successful side project already :)
GitHub: https://github.com/tomasz-tomczyk/crit","created_at":"2026-04-04T17:15:33Z","created_at_i":1775322933,"objectID":"47641085","parent_id":47639039,"story_id":47639039,"story_title":"Ask HN: What Are You Working On? (April 2026)","updated_at":"2026-04-04T22:44:43Z"}],"hitsPerPage":5,"nbHits":7,"nbPages":2,"page":0,"params":"query=crit.md&hitsPerPage=5&advancedSyntax=true&analyticsTags=backend","processingTimeMS":25,"processingTimingsMS":{"_request":{"roundTrip":14},"fetch":{"query":4,"scanning":19,"total":24},"total":25},"query":"crit.md","serverTimeMS":26}