Clawpatch 0.1.0 maps codebases into semantic feature slices that include entrypoints, owned files, tests, and trust boundaries. The CLI invokes the Codex provider to review each slice and stores findings with severity, confidence, evidence, and fix recommendations. Supported commands cover init for project detection across Node.js, TypeScript, Go, Rust, and SwiftPM, plus map, review, fix, and report functions. The release follows experiments that ran roughly 100 Codex agents to scan commits and PRs.
🩹 clawpatch 0.1.0 is live:
Clawpatch maps codebases into semantic feature slices, reviews them for bugs and quality issues, and records explicit fix attempts with validation.
You'll be surprised how much this will find. npm install -g clawpatch https://clawpatch.ai
Users expressed excitement for AI tools like Clawpatch and OpenClaw using Codex agents to automate code reviews and uncover hidden bugs due to efficiency and helpful features, while others objected to high costs and build issues.
No Digg Deeper questions have been answered for this story yet.
People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question:
How would we build software in the future if tokens don't matter?
We constant run ~100 codex in the cloud, reviewing every PR, every issue. If a fix on main lands, @clawsweeper will eventually find that 6 month old issue and close it with an exact reference.
We run codex on every commit to review for security issues (as it's far too easy to miss).
We run codex to de-duplicate issues and find clusters and send reports for the most pressing issues.
We have agents that can recreate complex setups, spin up ephemeral http://crabbox.sh machines, log into e.g. Telegram, make a video and post before/after fix on the PR.
There's codex that watch new issues and - if it fits our documented vision well, automatically create a PR of it. (that then another codex reviews)
We have codex running that scans comments for spam and blocks people.
We have codex instances running that verify performance benchmarks and report regressions into Discord.
We have agents that listen on our meetings and proactively start work, e.g. create PRs when we discuss new features while we discuss them.
We build http://clawpatch.ai to split all our projects into functional units to review and find bugs and regresssions.
We do the same split for security with Vercel's deepsec and Codex Security to find regressions and vulnerabilities.
All that automation allows us to run this project extremely lean.
Try https://clawpatch.ai on one of your repos and let codex work its magic. It's amazing at uncovering bugs you didn't know you had.
this is wild
People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question:
How would we build software in the future if tokens don't matter?
We constant run ~100 codex in the cloud, reviewing every PR, every issue. If a fix on main lands, @clawsweeper will eventually find that 6 month old issue and close it with an exact reference.
We run codex on every commit to review for security issues (as it's far too easy to miss).
We run codex to de-duplicate issues and find clusters and send reports for the most pressing issues.
We have agents that can recreate complex setups, spin up ephemeral http://crabbox.sh machines, log into e.g. Telegram, make a video and post before/after fix on the PR.
There's codex that watch new issues and - if it fits our documented vision well, automatically create a PR of it. (that then another codex reviews)
We have codex running that scans comments for spam and blocks people.
We have codex instances running that verify performance benchmarks and report regressions into Discord.
We have agents that listen on our meetings and proactively start work, e.g. create PRs when we discuss new features while we discuss them.
We build http://clawpatch.ai to split all our projects into functional units to review and find bugs and regresssions.
We do the same split for security with Vercel's deepsec and Codex Security to find regressions and vulnerabilities.
All that automation allows us to run this project extremely lean.
run codex on every commit
People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question:
How would we build software in the future if tokens don't matter?
We constant run ~100 codex in the cloud, reviewing every PR, every issue. If a fix on main lands, @clawsweeper will eventually find that 6 month old issue and close it with an exact reference.
We run codex on every commit to review for security issues (as it's far too easy to miss).
We run codex to de-duplicate issues and find clusters and send reports for the most pressing issues.
We have agents that can recreate complex setups, spin up ephemeral http://crabbox.sh machines, log into e.g. Telegram, make a video and post before/after fix on the PR.
There's codex that watch new issues and - if it fits our documented vision well, automatically create a PR of it. (that then another codex reviews)
We have codex running that scans comments for spam and blocks people.
We have codex instances running that verify performance benchmarks and report regressions into Discord.
We have agents that listen on our meetings and proactively start work, e.g. create PRs when we discuss new features while we discuss them.
We build http://clawpatch.ai to split all our projects into functional units to review and find bugs and regresssions.
We do the same split for security with Vercel's deepsec and Codex Security to find regressions and vulnerabilities.
All that automation allows us to run this project extremely lean.
I am so tired of ppl dunking on Peter, who basically runs the largest experiment what the future of work will look like
(and similarly, what the future of security looks like)
People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question:
How would we build software in the future if tokens don't matter?
We constant run ~100 codex in the cloud, reviewing every PR, every issue. If a fix on main lands, @clawsweeper will eventually find that 6 month old issue and close it with an exact reference.
We run codex on every commit to review for security issues (as it's far too easy to miss).
We run codex to de-duplicate issues and find clusters and send reports for the most pressing issues.
We have agents that can recreate complex setups, spin up ephemeral http://crabbox.sh machines, log into e.g. Telegram, make a video and post before/after fix on the PR.
There's codex that watch new issues and - if it fits our documented vision well, automatically create a PR of it. (that then another codex reviews)
We have codex running that scans comments for spam and blocks people.
We have codex instances running that verify performance benchmarks and report regressions into Discord.
We have agents that listen on our meetings and proactively start work, e.g. create PRs when we discuss new features while we discuss them.
We build http://clawpatch.ai to split all our projects into functional units to review and find bugs and regresssions.
We do the same split for security with Vercel's deepsec and Codex Security to find regressions and vulnerabilities.
All that automation allows us to run this project extremely lean.
@levelsio Copy paste this post into Claude + “brainstorm how this might apply to my projects”
People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question:
How would we build software in the future if tokens don't matter?
We constant run ~100 codex in the cloud, reviewing every PR, every issue. If a fix on main lands, @clawsweeper will eventually find that 6 month old issue and close it with an exact reference.
We run codex on every commit to review for security issues (as it's far too easy to miss).
We run codex to de-duplicate issues and find clusters and send reports for the most pressing issues.
We have agents that can recreate complex setups, spin up ephemeral http://crabbox.sh machines, log into e.g. Telegram, make a video and post before/after fix on the PR.
There's codex that watch new issues and - if it fits our documented vision well, automatically create a PR of it. (that then another codex reviews)
We have codex running that scans comments for spam and blocks people.
We have codex instances running that verify performance benchmarks and report regressions into Discord.
We have agents that listen on our meetings and proactively start work, e.g. create PRs when we discuss new features while we discuss them.
We build http://clawpatch.ai to split all our projects into functional units to review and find bugs and regresssions.
We do the same split for security with Vercel's deepsec and Codex Security to find regressions and vulnerabilities.
All that automation allows us to run this project extremely lean.
@steipete I think a lot of people don't get that this will become accessible as the cost of intelligence continues to fall.
Only a few organizations can do this today, but the frontier will move and this style of automation will be commonly available to most in a few years.
@steipete every time i see your workflow i realize how much i have to learn on building with these tools, genuinely always open my mind to how narrow in scope im thinking
@RhysSullivan Build, best way to learn!
Great explanation and worth a read.
Also worth copy pasting into your codex for a brainstorm. It’s going to cost $100 soon.
People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question:
How would we build software in the future if tokens don't matter?
We constant run ~100 codex in the cloud, reviewing every PR, every issue. If a fix on main lands, @clawsweeper will eventually find that 6 month old issue and close it with an exact reference.
We run codex on every commit to review for security issues (as it's far too easy to miss).
We run codex to de-duplicate issues and find clusters and send reports for the most pressing issues.
We have agents that can recreate complex setups, spin up ephemeral http://crabbox.sh machines, log into e.g. Telegram, make a video and post before/after fix on the PR.
There's codex that watch new issues and - if it fits our documented vision well, automatically create a PR of it. (that then another codex reviews)
We have codex running that scans comments for spam and blocks people.
We have codex instances running that verify performance benchmarks and report regressions into Discord.
We have agents that listen on our meetings and proactively start work, e.g. create PRs when we discuss new features while we discuss them.
We build http://clawpatch.ai to split all our projects into functional units to review and find bugs and regresssions.
We do the same split for security with Vercel's deepsec and Codex Security to find regressions and vulnerabilities.
All that automation allows us to run this project extremely lean.
@steipete Tested it today on my own repo: first pass already found 27 issues, including several I had completely missed. This feels like magic. Huge respect to Peter for using access to serious resources to build something that genuinely helps everyone.🦞🚀
Try https://clawpatch.ai on one of your repos and let codex work its magic. It's amazing at uncovering bugs you didn't know you had.
🩹 clawpatch 0.1.0 is live:
Clawpatch maps codebases into semantic feature slices, reviews them for bugs and quality issues, and records explicit fix attempts with validation.
You'll be surprised how much this will find. npm install -g clawpatch https://clawpatch.ai
@steipete When you say “we” how many people are you referring to
@pmarca The Goblins inside the LLM’s demand the tokens
It makes sense
Burn the tokens and the goblins shall rewards you
Interesting.
@steipete Gave it a try and even addresses several findings in my pet project, thanks for sharing it Peter ❤️
https://prokopov.me/posts/trying-clawpatch-on-real-repositories/
meeting transcripts -> coding agent is insanely OP, you can basically yap the whole day then do all the followups in 20 minutes. huge mental unlock.
this is wild
@mwala_joel GPT Realtime 2 + OpenClaw + voice plugins.
@steipete this is cool af. damn need to witness this somehow.
People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question:
How would we build software in the future if tokens don't matter?
We constant run ~100 codex in the cloud, reviewing every PR, every issue. If a fix on main lands, @clawsweeper will eventually find that 6 month old issue and close it with an exact reference.
We run codex on every commit to review for security issues (as it's far too easy to miss).
We run codex to de-duplicate issues and find clusters and send reports for the most pressing issues.
We have agents that can recreate complex setups, spin up ephemeral http://crabbox.sh machines, log into e.g. Telegram, make a video and post before/after fix on the PR.
There's codex that watch new issues and - if it fits our documented vision well, automatically create a PR of it. (that then another codex reviews)
We have codex running that scans comments for spam and blocks people.
We have codex instances running that verify performance benchmarks and report regressions into Discord.
We have agents that listen on our meetings and proactively start work, e.g. create PRs when we discuss new features while we discuss them.
We build http://clawpatch.ai to split all our projects into functional units to review and find bugs and regresssions.
We do the same split for security with Vercel's deepsec and Codex Security to find regressions and vulnerabilities.
All that automation allows us to run this project extremely lean.
@xeophon if this is what the future of work looks like, i'll become a plumber.
@rohan1chaudhari you can use acp, app server and /codex to convert the current session
