thread2026-04-25c/5Z6DtEvN
—
Output formatready
x-contentmd
1,599 chars · 400 tokensUTF-8 · LF
# —
---
Built clawsweeper, which runs 50 codex in parallel around the clock, scans issues/prs deep and closes what is already implemented or what makes no sense.
Closed around 4000 issues today, a few thousand are in the pipeline. (rate limits are rough) https://github.com/openclaw/clawsweeper
#### —
My favorite part: instead of a dashboard it just updates the README as it works.
Readme is the new dashboard.
#### —
@WG_Mojo it's a lot of issues. still took all day.
#### —
@WG_Mojo Glad we have @OpenAI supporting us!
#### —
@SahilSatralkar Jjust about 5000 to go!
#### —
@tymrtn I tried hard to make sure we only close valid cases (and ping people that their stuff got fixed) glad to hear!
#### —
@lukejmorrison @sama most helpful is if you test main and yell at us if we break stuff
#### —
@emonuxui GPT 5.5 high is pretty good!
#### —
@netrunner_btc I reviewed a few 100 and they all seemed correct, GPT 5.5 is a goat.
#### —
@Red1OneX you can swap codex with claude with one line change
#### —
@Red1OneX It's a script. You change the word. I can't possibly make it simpler or more flexible.
#### —
@raarts 2 days
#### —
@DanutPralea 🤣
#### —
@jullle3 50 took about 20h, so 1 would take weeks.
#### —
@juminoz slop
#### —
@darkstalwart @thsottiaux I have him on speed dial.
#### —
@snapss nope
#### —
@R1ckvandelaar pretty sure, maybe just not as reliable. GPT 5.5 is the most reliable coding model.
ref · 5Z6DtEvNxmdbot.com/c/5Z6DtEvN