Skill GitHub has been achieved internally
Model selection is a huge driver for AI spend; we just reduced our cost-per-PR from $80 to $30 by switching from Opus 5 to GPT 5.6. We made this decision not by guessing, but by benchmarking. I want to show you how you can do this too!
Join me for a live session on building custom model benchmarks:
Thursday, September 17th 2pm ET
We'll build a custom benchmark that replays your past agent conversations against a set of different models to find the best cost/performance pick. I'll whiteboard the entire setup so you can do this yourself, and we'll walk through the batteries-included version with Warp Factories.
RSVP: 📅
Show more
I'm hosting a workshop next Thursday, Sept 3rd on how to build self improvement loops for agents. The idea is simple, yet super powerful: build agents that review past conversations, score the quality, and suggest skill improvements to fix inefficiencies.
You'll walk away with a workflow you can apply to any setup, and an understanding of how this fits into a wider approach for software development with Warp Factories. Hope to see you there!
RSVP: 📅
Show more
Introducing /skill-doctor v1
Skill doctor is a skill that improves your skills:
- Crawls your past CC, Codex, or Warp convos
- Scores them for efficiency and code quality
- Proposes diffs to your skills that you'd actually merge (STE-100 approved)
🔖
Show more
Been seriously impressed adding self-improvement to our agent conversations so far.
We've merged 5 self-improvement PRs in the past few days, including this one that caught token burn in our message passing system for orchestration
Show more
We run all the agents in our company out of this one config file. Calling it... terraform for agents. Would you use it?
Working on a skill that improves your skills:
/skill-doctor
- Crawls your past CC, Codex, or Warp convos
- Scores them for efficiency and code quality
- Proposes diffs to your skills that you'd actually merge (hardest part I'm still tuning...)
Would you use it?
Show more
🚨 Unpopular take: Slack is a pretty nice place to work with agents.
- You can see how engineers smarter than you write their prompts
- You can tag in designers to look before you ship something ugly
- It's much easier to review screenshots and recordings that the agent sends
Show more
More CLI coding agents needs to support `cd`-ing around different directories while you're in a session. It's so freeing
I can't believe I'm still using Grok 4.5 (medium) as my daily. It's such a good default
Introducing multi-agent orchestration in Oz, with support for Claude Code, Codex and the Warp Agent.
Use /orchestrate to delegate complex tasks across a team of agents, locally or in the cloud.
Show more
Tomorrow...
Subagent process "Gus" has something big to share
Coming soon. 👀
Thanks @AllThingsOpen for letting us share the way we manage open-source at Warp!
The pace of progress is wild. Now at 600+ contributions across 96 contributors in just a few weeks.
Show more
i love how people build the most beautiful effects a computer could ever render, and we can all just fork their dots to use it ourselves
but then I open bluetooth manager, or dolphin, or other software, and its the ugliest piece of interface ever made
am I just bad at linux??
Show more
Okay but he has a… point
There are a lot of small differences between the Claude Code and Codex CLIs:
- Different skill names and shortcuts
- Different built-ins (ex. docs, browser testing)
- Subtle gaps in featureset (ex. available hooks)
Here's what you need to know:
Show more
The past 48 hours of Warp open source have been busy.
A few strong community PRs are in review now, covering terminal search, SSH history, worktrees, logs, and cloud agent UI. 🧵
Intro to Warp - terminal basics, Claude Code setup, and cloud handoff with Oz
I never use planning mode in Codex.
GPT 5.5 loves to research, so I just have a conversation and reach a pseudo-plan in chat.
Then, I let it implement, maybe with a /fork beforehand to keep that plan as a revisit-able point.
Probably the biggest switch coming from Claude Code
Show more
