Scott Chacon
@scottchacon.com
about 1 month ago That is... pretty amazing.
💬 0
♻️ 0
❤️ 0
That is... pretty amazing.
Bring back any message or code instantly.
Use /rewind to pick a checkpoint, then choose what to restore: conversation, code, or both.
Never lose your conversation or code again. This is not what Unkey is for at all.
Our engineering and design team has been testing 20+ side-by-side comparisons across frontier and open models. All runs are public and open source. Benchmark for this demo here: github.com/CommandCode... We ran a test between Opus 5, GPT-5.6 Sol, and Kimi K3.
One prompt. Across all three models. With our /design command.
Ranking (DX, features, and cost):
🔹 Opus 5: 10/10 · $0.25
🔹 Kimi K3: 9.5/10 · $0.12
🔹 GPT-5.6 Sol: 7/10 · $0.32 just shipped a fix, weirdly tricky issue to fix in the general case!
this is the endpoint of bsky.app/profile/macw... - i did get a little printer kind of a review of a lil printer for enhancing my field notes journals with photos macwright.com/2026/07/24/p... New in Command Code: dont-ask permission mode.
Runs exactly what your allowlist permits
Everything else gets denied
Built for CI jobs, cron, and unattended runs
$ cmd --permission-mode dont-ask
No more hung jobs. Opposite of --yolo It's always DNS. Now you can prove it
Changelog #0300
• DNS logs
• Query the Railway API from the CLI
• Fixes and improvements
railway.com/changelog/2026-07-24-dns-logs Claude Opus 5 is now live in Command Code.
- Anthropic's latest thoughtful and proactive model
- On frontier intelligence, closet to Fable 5 at half price
- Available on plans (Pro, Max, Team)
Try now: $ cmd --model claude-opus-5 Claude Opus 5 is now available in Netlify AI Gateway and Agent Runners.
Call it from your Functions with the Anthropic SDK. No API keys, no auth setup, and caching and rate limiting come along for free.
www.netlify.com/changelog/cl... Imagine a trivia app that never runs out of questions. KP explains how AI Gateway lets you route requests to models like Claude or OpenAI so your app can generate new content on the fly instead of relying on hardcoded data.
Join us for a live demo of the Elicit API and MCP server.
Title: AI Agents Grounded in Evidence: A Live Demo of the Elicit API and MCP Server
Presenter: Panda, Software Engineer at Elicit
Date and Time: Wednesday, July 29, 2026, 10am PT
Register: crowdcast.io/c/dxk71bqnsq2w "Your environment variables exceed the 4KB limit."
If that error message just triggered something in you: it's retired. The env var size limit no longer applies on the current Functions runtime.
Your private keys can be as long as they need to be now.
www.netlify.com/changelog/20... the padding isn't even that necessary, which is such a bummer - scure/base and other enc/dec libraries have nopad options but they're nonstandard :/
Your workflow. Your coding agent. KP and Tania explain why Netlify lets you choose the AI agent that fits your workflow instead of locking you into one option.
Ling 3.0 Flash is live in Command Code
MoE model built for token-efficient agentic inference at production scale.
- Free for all subscribers
- 124B params (~5.1B active/token)
- 256K context, tool use, implicit caching
Try it:
$ cmd --model inclusionai/ling-3.0-flash-free Five security vulnerabilities were disclosed in React Router today. All patched in react-router 7.18.0.
Upgrade, then check your deploy previews. Public previews and branch deploys stay vulnerable until deleted. What Netlify users need to know: www.netlify.com/changelog/20... Update: CSV filtering is actually not public yet. This was a mistake on our end. Sorry for misleading!
ICYMI: the 4KB env var limit for Netlify Functions is gone.
If you've ever played code golf with your connection strings, you can stop. Add as many API keys, secrets, and feature flags as your project actually needs.
www.netlify.com/changelog/20... Woah, first I'm hearing of this. Jazzed
switched to typescript 7 for coding on @val.town. extremely good. yep