Steve Krouse
@stevekrouse.com
about 1 month ago woah, so fun! curious how this app ends working out! lmk if there's anything i can do to help
💬 0
♻️ 0
❤️ 1
woah, so fun! curious how this app ends working out! lmk if there's anything i can do to help
AI code works, but not like you.
Devs waste time fixing the same patterns, rewriting tests/docs, waiting on PRs, and losing context between sessions.
Command Code learns your style and applies it across projects.
Make AI code like you → commandcode.ai Nice!
New in v0.26.20
Command Code supports Qwen 3.7 Max
Frontier coding model with long-horizon agent execution.
Try it out with /model #ZedEditor Download Zed and view the full changelog here:
zed.dev/releases/pre... Completion menu items can now show a single-letter kind badge next to each entry. Enable it with `"completion_menu_item_kind": "symbol"`.
The agent can now render inline images and Mermaid diagrams directly in the thread. 🖼️ 🧜♀️
You can now configure a separate model for subagents with the new `agent.subagent_model` setting.
Tip: Use a frontier model for the main agent, and something faster and cheaper for subagents.
"agent": {
"subagent_model": {
"model": "gpt-5-mini",
"provider": "zed.dev"
}
} Run custom git commands on any commit in the git graph. Define a global task using the new git task variables to add it to the context menu.
A beautiful new History tab landed in the git panel. 🌳 See all the commits on the current branch in one scrollable list.
🚀 We shipped v1.3 yesterday. Here are the highlights!
Terminal Threads have landed.
Open a terminal right in the Threads Sidebar and run claude, codex, or any other CLI agent alongside your built-in agent threads.
zed.dev/blog/termina... Building a real-time AI chatbot used to mean wiring up model APIs, streaming, auth, and a backend before you saw the UI.
Now you start with a prompt. Nahrin Jalal shows how Agent Runners handles the rest.
www.netlify.com/blog/how-to-... Read the full breakdown and all sixteen modes here:
↳ Blog: commandcode.ai/blog/slash-...
↳ Docs: commandcode.ai/docs/design Introducing "/design": the skill that turns Command Code into your terminal-native design partner.
One command. 16 modes. Each one knows what to look for, what to change, and what to leave alone.
npm i -g command-code
cmd
/design help Austrian .at sales versus Anguillan .ai sales is the leading indicator in the Bluesky versus Twitter rivalry
CipherStash + Prisma Next integration just shipped 🚀
Add cipherstash.EncryptedString() to your contract for searchable encryption.
Encrypted data stays queryable, your rules live in the contract & plaintext only appears when you explicitly decrypt it.
pris.ly/cipherstash... A dollar for $40 of DeepSeek V4 Pro usage?
Hard to say no to that. “The wave will pass. The products will be quietly deprecated or repositioned. The companies that survive this cycle will be the ones who figured out how to offer compute as a capability that developers tap into, not as a place they move into.”
pepicrft.me/blog/sell-co... The completed systematic review can be found at the link below. elicit.com/review/55ee... Below is a recap of the notable features we discussed:
- Run multiple searches and combine results.
- Verify decision making.
- Import full text with chrome extension.
- Extract data from tables and figures.
- Generate report with citations.
- Enable dual reviews.
- Leverage Elicit APIs. The full walkthrough of Elicit Systematic Review is now live.
During the session, we ran a complete review from start to finish in 60 minutes while highlighting the cool new features that really made this feat possible.
Try out your protocol at elicit.com.
www.youtube.com/watch?v=MdM... Heads up for Nuxt users: The Nuxt team disclosed four CVEs yesterday, including a route middleware bypass.
Upgrade to nuxt 3.21.6 or 4.4.6 as soon as possible. Full breakdown of impact on Netlify deployments in the changelog.
www.netlify.com/changelog/20... Try Terminal Threads now in Zed v1.3.5:
zed.dev/releases/sta...