Building Agent River. Stop waiting for your Claude Code agents. Let them wait for you.
#buildinpublic | AI dev tools
Joined December 2022
- Tweets2.8K
- Following153
- Followers544
- Likes6.7K
Inspired by this, here is a simpler prompt to secure your tailscale network 👇🏻
Hey fellow Tailscale loving friends, with all the security shenanigans going on here’s a prompt I recommend for making sure the weakest link on your talilnet can’t wreck everything else over ssh or otherwise.
Give your agent this and let it walk you thru locking down your ACL:
gist.github.com/alexknowshtm…
An Van retweeted
Agents reinvented how we produce code. It changed our tools and half of our workflow. It’s time for the other half to catch up.
Today, we’re shipping Entire: the Git forge for agent-human collaboration. We’ve built @GoEntire using Entire. Now we want to see what you'll build with it.
Here’s why and what’s different. 🧵
An Van retweeted
Before adding another subagent ask what problem it's solving. A bloated system prompt is often the issue.
Skills and tool search can fix that without splitting context across agents. My rule of thumb is to keep a subagent when the work is parallel, needs fresh context or one agent really can't pick the right tools.
Otherwise, fold it into the main loop, turn its prompt into a skill, run your evals and keep whatever wins.
Good write-up:
claude.com/resources/article…
This is the way
Finally summarized what I've been sending to friends in DMs View article
my fseventsd grew to almost 70gb
time to end this by moving all repos to an elastic scratch disk
also no spotlight indexing and time machine snapshots there, which reduces the overall disk load
OK, so: an elastic vol w/ fseventsd turned off. had to be elastic as I didn't want to pre-reserve space.
TL;DR: created an APFS volume with nolog + disable Spotlight indexing at ~/repos - persists and looks like a normal folder to every app.
script: github.com/elithrar/dotfiles…
I’ve set up this app and Pushover notifications to buy an iPhone Duo when it will be available nearby.
let’s see if I can secure one …
just use wehbs.github.io/ReadyForPick… free and open source with pushover notifications
An Van retweeted
Screen sharing that actually fits your screen.
Your Mac on iPhone, iPad and iPhone Duo. Super duper fast.
Apple Store Mitarbeiter sagte: iPhone Duo ist in komplett Deutschland ausverkauft. Es gibt vielleicht nur noch in Apple Store Köln welche
Aber es lohnt sich immer nach Mitternacht, die Verfügbarkeit zu prüfen
An Van retweeted
Today we announce 1Password for Agents platform, building with companies @Muse, SpaceX Super Intelligence Grok @Bot, @AnthropicAI’s @Claudeai, @OpenAI, @TownAI, @Browserbase, @Browser_use, @heydana_ai, Instinct, @usekernel, @Perplexity_ai, @tryramp, @Tomo, and @wajo_ai, with more integrations on the way. 🎉
We've heard from so many of our customers who want to use these new personal AI agents to help them get more done, but want more control over what the agent can access with the same trust and ease of use they get when using 1Password directly.
1Password for Agents gives your agents access without giving up your passwords. When an agent reaches a sign-in form, it requests a credential from your vault. If you approve the request, 1Password directly auto-fills the credential in the destination site so the agent can’t see or take possession of the credentials.
The agent gets the task done, but it doesn’t get your passwords..
You stay in control. 1Password for Agents free and optional for personal and family accounts. Unless you opt-in to an agent connector, agents cannot touch your vault.
➡️Learn more: bit.ly/487da6J
An Van retweeted
Quick reminder that the free limit reset from last month expires tomorrow at 9am PT! 🙏 If you haven't used yours yet, it's still waiting for you in Settings > Usage (or clau.de/reset)
An Van retweeted
We launched OSS Scanner, which gives critical open source projects free, periodic vulnerability scans from our strongest models.
Each finding includes a proof-of-concept, and a patch where possible.
red.anthropic.com/oss-scanne…
An Van retweeted
OK, so: an elastic vol w/ fseventsd turned off. had to be elastic as I didn't want to pre-reserve space.
TL;DR: created an APFS volume with nolog + disable Spotlight indexing at ~/repos - persists and looks like a normal folder to every app.
script: github.com/elithrar/dotfiles…
Life is good now. 🎉 Tell your agent to:
- create a new volume in you mac
- disable fseventsd (and spotlight) on it
- and move your projects folder to it
- remount it
For extra points move you pnpm cache folder to it.
(Start the conversation outside of your projects folder, Also you might need to kill a ton of processes)
An Van retweeted
Details:
- We push to main
- Buildkite runs tests and builds images
- GitHub Actions then runs infrastructure security checks and kicks off deployments
- Failed check blocks deployment, pings commit author in Slack
- CI keeps running on later pushes while we fix it
- Later fixes can make CI green again and enable deployment
- GitHub Actions deploys the server after checks pass, first staging then prod, takes usually in ~10 minutes
- Durable agent infra has a 2-hour deploy cadence
- CLI releases run every 4 hours, built/tested in Buildkite and published via GitHub Actions
Yup, we have SOC2 and push to main:
ampcode.com/notes/thats-not-…
An Van retweeted
In the next version of Bun
bun lint is a 26x faster ESLint-compatible linter with over 1,000 builtin rules - reads eslint & oxlint configs.
ALT Poster for bun lint, an ESLint-compatible linter built into Bun. Headline: 26x faster than ESLint. Table of lint times on real projects, each with its own config and plugins, bun lint vs ESLint: shadcn/ui 2.1 s vs 90.4 s (43x), chakra-ui 0.59 s vs 22.6 s (38x), vscode 15.8 s vs 404 s (26x), mastodon 6.6 s vs 100 s (15x), playwright 4.9 s vs 53.4 s (11x). On vscode, 9,823 of 9,826 messages are identical. 99.6% of ESLint's tests pass. 99.8% of oxlint's tests pass. 2x faster than oxlint with 3x less memory. 1,021 rules built in, including type-aware rules.
An Van retweeted
Why are you still using pull requests?
Is it for code review?
If so, do you really think your or your colleagues catch bugs and mistakes that an Opus 5.5 or Fable or Astra won't find? You can literally spawn all three of them and have them check four times each.
(Also, don't tell me you don't have a "stamp plz" Slack channel or group chat somewhere.)
Is it for knowledge sharing?
Surely there's better ways for that now than the PR, no? We have models that can generate explainer videos, presentations, podcasts, games, quizzes, walkthroughs, ... for any piece of code it can reach.
Is CI the reason?
Well ackshually, CI means continuous integration and its original meaning is the *opposite* of having long-lived branches and PRs.
But, leaving that aside, your agents are hopefully already running the tests before they push something, and hopefully they can run as long as they want and don't block you so they can run the whole test suite and generate "irrefutable proof" and end-to-end demo videos and so on... And so they run the tests and confirm and then you push to a branch and everything runs again and then you merge and then it runs again? That doesn't make sense, does it?
Maybe you work in open source and you accept contributions, in which case I can't speak to the value of pull requests. It's been 2 years since my last OSS contribution. But from what I heard, the time of the PR is coming to an end in OSS too?
I honestly don't get why people still stick to PRs.
With agents you can now move 10x faster, you can finally do real continuous integration, and get more confidence in the changes the agent made.
Don't slow yourself down by having all the changes pile up in a PR.
Just found out Moshi supports webhooks
Together with OSC 7501 I’ve setup a custom routing for push notifications:
When afk and session blocked or asking then send a push notification to my iPhone
Nowadays attention management is everything
Claude Code v2.1.295 supports OSC 7501 (program status). Incredible speed @AnthropicAI supporting this protocol which will help hundreds or thousands of downstream applications! They had access to Rex and verified through Rex it works. 🥰
An Van retweeted
@fnthawar and I talked about how the skill of coding agents is "being in the details"
like running a company, you can't know everything but caring obsessively about the right details is what makes something great
it could be code, architecture, design, UX- whatevers needed
