Kevin Cao

Founder of Sumi Interactive,
Maker of Grid Diary

[Kevin Cao @kyoji2]

@kevinzhow 好奇在手机上coding时间已经超过在电脑前了吗

[Peter Steinberger 🦞 @steipete]

Here's a simple loop: Tell codex to maintain your repos, wake up every 5 minutes and direct work to threads. That makes it easy to parallelize+steer work as needed.

I use a orchestrator skill combined with my triage+autoreview+computer use skills, so some work can land autonomously. https://t.co/FbBoJTIcfd
https://t.co/8389roVnOm

[Pavel Durov @durov]

We now support rich formatting for all chatbots.

Tables, nested lists, inline media, formulas, headers and more — right in Telegram messages.

🔨 Start building! Docs: https://t.co/zgzPOOUJF5

[Jordan Morgan @JordanMorgan10]

Here are the skills that ship with Xcode 27.

Apple did a fantastic job with these (no surprise) from what I've poked around and looked at. Baseline SwiftUI guidance, and nuggets on how to use the new stuff like the reorderable APIs.

$ xcrun agent skills export --output-dir ~/Desktop/xcode-skills

[Emil Kowalski @emilkowalski]

To get good animations from an AI you need to get good at telling it what you want:

- "stagger this list of items"
- "make this animation direction-aware"
- "spacial consistency", "crossfade", "layout animation",

I made a motion vocabulary for this:
https://t.co/ExAxpr31no

[Kevin Cao @kyoji2]

如果不需要编辑功能，直接用 Codex 也是极好。主要是阅读体验比在终端里面舒服。

[Kevin Cao @kyoji2]

打算集中学习一下 Github 上高星的开发和设计主题的 skills。发现体验最好的还得是 Obsidian。新开一个 vault，拉取各个repo。配置主题选Baseline。再装一个插件Terminal用来side by size 跑 claude ，有问题就问。目标是 distill 出适合自己的最佳实践。

[Kevin Cao @kyoji2]

@lochieaxon @motiondotdev 怀旧一下

[Brotzky @brotzky]

Introducing https://t.co/ycxJEf1z7w!

A new space where I explore how the best apps in the world are built.

First piece:
How's Linear is so fast? a technical breakdown.

https://t.co/9Vu1syrn1i

[Zed @zeddotdev]

Terminal Threads are live in Zed v1.3.5!

You can now run claude, amp, pi, or any terminal-based workflow as a managed thread in the Threads Sidebar, right next to your other agent threads.

[Ben Blumenrose @benblumenrose]

Our 2026 Design in AI Report is now live!

This report is the culmination of thousands of people hours and many late nights to create what we believe is the most comprehensive, well-researched report capturing and synthesizing the state of Design + AI today.

While we used AI in many areas, a report like this still required deep thinking, grit, and humans coming together to do what they do best.

The final report spans nearly 20k words covering the survey results of over 900 people paired with dozens of qualitative interviews.

Over the coming months we will also release 7 beautiful case studies showing how top design teams are working on the ground featuring designers at @AnthropicAI, @framer, @linear, @NotionHQ, @Shopify, @SierraPlatform, and @stripe.

This work is a true labor of love to help guide a design community we hold so dear.

Link in the comments and please let us know what you think. Your feedback helps us shape how we will evolve this work over the coming years...

[OpenAI Developers @OpenAIDevs]

Your Mac can hold down the fort while you work from your phone.

Enable remote connection in the Codex desktop app, then turn on “Keep this Mac awake.”

When your Mac is powered on and plugged in, Codex can keep running there while you work from the ChatGPT mobile app.

[Thariq @trq212]

a prompt I've been using a lot recently:

implement <SPEC> and while you do, keep a running implementation-notes.html file (or markdown) with decisions you had to make weren't in the spec, things you had to change, tradeoffs you had to make or anything else I should know

[Pedro Duarte @peduarte]

everything you need to know about how the team built the new @raycast from the ground up

honestly worth a read 👉 https://t.co/vP4OUpIHSV

there's nothing to hide

[Kevin Cao @kyoji2]

@lexrus 我也是这么用，但是被封号过一次

[Aaron @aaronp613]

Apple accidentally left Claude.md files in today's Apple Support app update (v5.13)

[Zed @zeddotdev]

We've shipped more than a thousand versions of Zed, but all of them began with zero. Today, that changes.

https://t.co/AJ0crNOFhU

[Cursor @cursor_ai]

We’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor.

Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products.

[Zed @zeddotdev]

Parallel Agents just shipped. Mix and match any agent, run them all at once, and manage everything from a new Threads Sidebar. Claude Agent, Codex, Zed's agent, or anything on ACP. One window, across all your projects.

https://t.co/Px91WvwBAw

[Ronin @DeRonin_]

10 GitHub repos to spend 60-90% less tokens in Claude Code:

1. RTK (Rust Token Killer)

CLI proxy that filters terminal output before it hits your context

- 60-90% reduction on common dev commands
- one binary, zero dependencies
- works with Claude Code, Cursor, Copilot

Repo: https://t.co/WayvpBtyBH

2. Context Mode

Sandboxes raw tool output into SQLite instead of dumping it into context

- 98% context reduction on Playwright, GitHub, logs
- only clean summaries enter your conversation
- works as Claude Code plugin

Repo: https://t.co/YNbFIGQz7X

3. code-review-graph

Local knowledge graph that maps your codebase with Tree-sitter

- Claude reads only what matters, not the entire repo
- 49x token reduction on large monorepos
- 6.8x on average reviews

Repo: https://t.co/9gIzmAWN12

4. Token Savior

MCP server that navigates code by symbols, not full files

- 97% reduction on code navigation
- persistent memory across sessions
- 69 tools, zero external deps

Repo: https://t.co/OtvhrMgGWh

5. Caveman Claude

makes Claude talk like a caveman to cut output tokens

- 65-75% output reduction
- one-line install
- keeps full technical accuracy

Repo: https://t.co/onBeghTyfH

6. claude-token-efficient

one CLAUDE.md file that keeps responses terse

- drop-in, no code changes
- reduces output verbosity on heavy workflows
- best for output-heavy sessions

Repo: https://t.co/j6MKo9klQe

7. token-optimizer-mcp

MCP server with caching, compression, and smart tool intelligence

- 95%+ token reduction through intelligent caching
- compresses repeated tool outputs

Repo: https://t.co/0jIVQ4ANls

8. claude-token-optimizer

reusable setup prompts for optimizing any project

- 90% token savings in 5 minutes
- reduces doc token usage from 11K to 1.3K

Repo: https://t.co/puil9WwFGB

9. token-optimizer

finds ghost tokens that silently eat your context

- survives compaction without losing quality
- fixes context quality decay

Repo: https://t.co/92G8e4yeGq

10. claude-context (by Zilliz)

code search MCP that makes your entire codebase the context

- ~40% reduction with equivalent retrieval quality
- hybrid BM25 + dense vector search

Repo: https://t.co/yjfiQOSy15

[ how to stack them ]:

you don't need all 10. pick 2-3 based on your workflow:

> heavy terminal output? RTK
> big codebase? code-review-graph + Token Savior
> lots of MCP servers? Context Mode
> quick fix? Caveman + claude-token-efficient

most people are burning tokens without knowing it

run /context in a fresh session and see how much is gone before you even type a word

your pocket will thank me later :<)