Matthew Parris
@parrisdigital
Building products and ideas with intention. AI, systems, real-world execution.
You might like
unpopular opinion: most AI code reviewers are useless I tested them for months, and here are the best ones 👉 Cursor BugBot: nearly perfect catches everything but costs $40/mo on top of your Cursor sub 👉 Augment Code: solid and getting better fast 👉 Codex: very detailed…
Claude Code - Official Multi Agent Orchestration This is a disabled feature, but through CC Mirror, I have been able to enable it It is so simple, yet powerful and IMO beats every orchestration I've seen There's no point building your own Updating CC Mirror later today so…
8/ I use a few subagents regularly: code-simplifier simplifies the code after Claude is done working, verify-app has detailed instructions for testing Claude Code end to end, and so on. Similar to slash commands, I think of subagents as automating the most common workflows that I…
I cleaned up things and published a version of CLI for bulk scan/summarization for folks along with an agent Skill to use it. Check it out here: github.com/smerchek/bulk-…
Introducing the N Skills Marketplace It my personal curated marketplace of the best Skills that actually allow work to get done This is a public list that you can apply to be on Day one skills: - dev-browser @sawyerhood - gastown @nummanali - zai-cli @nummanali
I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit. My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to…
Claude Code is looking INSANE for 2026: - Agent Swarms: Exit plan mode with swarm - instructions for launching swarm teammates when ExitPlanMode is called with isSwarm set to true - Session Search Assistant: - agent prompt for finding relevant sessions based on user queries,…
Thanks to @robinebers , my eyes have been opened to @conductor_build ! Testing this as we speak! 7 mins until 2026! Let's go!
still here? cool, here's some more interesting stuff: in the process of making a macOS app, I also discovered that making icons with AI is not that easy. tried a few things, didn't work. but then I found a super cool (and FREE) tool to make icons, directly from Apple, called…
Tools I actually use myself got Claude Code: 1. WhatsApp bridge for Claude Code: • warelay by @steipete • github.com/steipete/warel… 2. The best browser control plugin: (i tried them all, this is the most reliable) • dev-browser by @sawyerhood • github.com/SawyerHood/dev… 3.…
Want to try it? Open Claude Code and install the plugin. /plugin marketplace add browserbase/claude-code-plugin /plugin install browserbase@browserbase-cloud Run the setup script then use Claude Code normally. Browser commands go to the cloud.
"🤖 Generated with Claude Code" tired of Claude Code claiming spamming this everywhere? you can turn this off! just add this to your ~/.claude/settings.json (or ask Claude Code to to this for you 😂) { "attribution": { "commit": "", "pr": "" } } done!
Terminal UI Skill that I use, bookmark it 📂 --- name: terminal-ui-design description: Create distinctive, production-grade terminal user interfaces with high design quality. Use this skill when the user asks to build CLI tools, TUI applications, or terminal-based interfaces.…
If you're still sleeping on the dev-browser Skill from @sawyerhood Then check out GPT 5.2 in Codex programatically browsing the docs for @Seedream_AI on the ByteDance VolcEngine site 1. npm i -g openskills 2. openskills install SawyerHood/dev-browser 3. openskills sync Done
not to mention that they literally work throughout christmas to ship more features. gotta respecc that. conductor.build/changelog
I successfully ran a Claude Code instance for 24-hours without any action from me. I gave it long(qdrant) and short(sqlite) -term memory, and access to a browser. The run generated: - 500 projects - ~450k LOC - 20 long-term records - 1500+ screenshots denislavgavrilov.com/p/clopus-02-a-…
Here's the agent I ran, and a repository to have more in the future. Might turn this into a marketplace for plugins instead if I keep maintaining them. github.com/robinebers/cla…
We’re excited to partner with @cursor_ai through our integration with Cursor Hooks. With Hooks, Corridor provides instant security checks the moment code is written. This is the next step in our journey to make agentic coding trustworthy and safe. How we do it: 🧵
My vision for utilising Code Agents as General Purpose Agents Through advanced orchestration, a hybrid of deterministic vs non-deterministic What the experience would look like:
If you want to have Opus 4.5 at it's MAX in Claude Code Update ~/.claude/settings.json { "env": { "CLAUDE_CODE_MAX_OUTPUT_TOKENS": "64000", "MAX_THINKING_TOKENS": "31999" } } - double the output - ultrathink always on Ctrl+O will show thinking in verbose mode
United States Trends
- 1. Packers 179 B posts
- 2. Caleb Williams 48,6 B posts
- 3. McManus 17,1 B posts
- 4. Ben Johnson 33,3 B posts
- 5. LaFleur 38,6 B posts
- 6. Jordan Love 18,2 B posts
- 7. Bregman 24,4 B posts
- 8. Cubs 24,2 B posts
- 9. #GBvsCHI 6.782 posts
- 10. Matthew Golden 8.377 posts
- 11. Red Sox 7.124 posts
- 12. Devers 3.702 posts
- 13. DJ Moore 7.142 posts
- 14. Cancun 6.378 posts
- 15. Al Michaels 3.446 posts
- 16. #NFLPlayoffs 16,2 B posts
- 17. Colston Loveland 6.664 posts
- 18. Nixon 22 B posts
- 19. Rams 80,8 B posts
- 20. Dennis Allen 3.868 posts
You might like
-
AP,X
@apkoolj -
SIR X MAN
@Sirxman1 -
bacfromdead1
@BACfromthedead1 -
Axle1324Gaming
@axle1324 -
CvzFinest617x
@CvzFiNeSt27 -
Scrub Nurse
@ScrubNurse3 -
Adam
@adamcrinson661 -
SPLENNDIFFEROUS
@SPLENNDIFFEROUS -
Lyddite
@Lyddite70 -
Taozochi
@taozochi -
Cyber🦇
@CyberKnoxx -
Lerm01
@lerm01 -
JimmyCooks25
@Killanitis -
HRBomber
@hrbomber -
Jesse Darby
@JesseDarby2
Something went wrong.
Something went wrong.