正在加载视频...

视频加载失败

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and...

43,664 次观看 • 4 个月前 •via X (Twitter)

27 条评论

Steve (Builder.io) 的头像
Steve (Builder.io)4 个月前

Source for the skills and how to install them here:

max 的头像
max4 个月前

Read the damn docs is so real 😭😭😭

Will Undrell 的头像
Will Undrell4 个月前

honourable mention to /thermo-nuclear-code-review here, defo worth using if you've not head of it before

Daniel Day Jewish 的头像
Daniel Day Jewish4 个月前

Smart points. Definitely clicking because I'm always interested in seeing if there's a better way to get them to read the damn docs *shakes fist*

Tyler Mayberry 的头像
Tyler Mayberry4 个月前

/read-the-damn-docs is brilliant. Definitely using that one.

Raffaele 的头像
Raffaele4 个月前

The /read-the-damn-docs one is underrated. Agents guess at the API because they optimize to sound right, not to be right. Making the doc lookup a required step, not a suggestion, is what cut our wrong-API failures the most. Now it has to cite the source before acting.

Piers Rollinson 的头像
Piers Rollinson4 个月前

Nice. I like the idea of /agent-watchdog. I’ll give it a try. Do you use any skills/MCPs for Claude to manage Codex and vice-versa?

Paul Takisaki 的头像
Paul Takisaki4 个月前

I'm doing a similar thing to agent watchdog. def taking the read the damn docs process, I'm tired of manually prompting that.

赛博命理师 的头像
赛博命理师4 个月前

This matches my 9-agent build: the cross-check layer is where the real engineering lives, not the agents. What I'd add to watchdog-style checks: persistent memory. Mine logs every miss to a 'mistake ledger', so it catches the same failure across runs, not just one thread.

Carry 的头像
Carry4 个月前

the fact that /read-the-damn-docs has to exist is the funniest indictment of these things

Charlie · 云马AI · 免🪜稳连 Claude/GPT/Gemini API 的头像
Charlie · 云马AI · 免🪜稳连 Claude/GPT/Gemini API4 个月前

这个点真的戳中了。我现在也会让一个模型盯另一个模型,尤其是改代码和跑测试这种活,单代理太容易自信犯错,多一层旁观者反而省时间。

Dipanshu Kushwaha 的头像
Dipanshu Kushwaha4 个月前

That's a smart approach! Having a backup always helps. Love the teamwork between agents!

Brosko 的头像
Brosko4 个月前

two agents checking each others work is so funny to me basically just vibes peer review at this point 💀

AI Mastery Guide 的头像
AI Mastery Guide4 个月前

having two agents check each other's work is honestly such a simple fix for the trust problem with coding agents

Ritik Verma 的头像
Ritik Verma4 个月前

"The biggest upgrade wasn't a better model. It was giving the model a second opinion."

Yordis Prieto 的头像
Yordis Prieto4 个月前

The most impactful one for humans to help the machine I created for my team is the most trivial one Check it out, asking to share and document the 3 keys has been priceless

安叫兽|Bird🕊️ 🔶 BNB 的头像
安叫兽|Bird🕊️ 🔶 BNB4 个月前

让一个代理盯另一个,听着就很打工人

Samian 的头像
Samian4 个月前

having the watchdog actually intervene vs just flag is the difference. passive watchers feel safe until you realize they're postmortems

Yagyesh Bobde 的头像
Yagyesh Bobde4 个月前

agent-watchdog is the one i don't have yet. how does it actually catch the other agent drifting without you babysitting both?

也无风雨也雾晴 的头像
也无风雨也雾晴4 个月前

One skill I keep coming back to: ask the agent to name the files it expects to touch before it edits anything. It catches a surprising number of bad runs before they become a messy diff.

mentallystronger 的头像
mentallystronger4 个月前

I usually just have Claude review the PRs Codex makes and vice versa. And Copilot just resolves merge conflicts lol.

Tem 的头像
Tem4 个月前

Super dope! Thanks for sharing!

@ferueda 的头像
@ferueda4 个月前

today I was trying this one

John 的头像
John4 个月前

does the watchdog ever catch something meaningful or does it mostly just confirm the first agent got it right

Steve (Builder.io) 的头像
Steve (Builder.io)4 个月前

almost always catches something meaningful in my experience

overflowy 的头像
overflowy4 个月前

Can you make a tutorial video showcasing how you use these skills in your daily workflow?

Steve (Builder.io) 的头像
Steve (Builder.io)4 个月前

good idea, I’ll do that

相关视频

🚨 OpenAI just launched Codex, a brand-new autonomous coding agent that can build features and fix bugs on its own. We’ve been using it Every 📧 for a few days, and I’m impressed. I invited Alexander Embiricos (ben davies), a member of the product staff responsible for Codex, to demo Codex and talk about it live on a special edition of AI & I: What Codex is and how it works Codex is designed to be used by senior engineers—it performs coding tasks like adding features or fixing bugs autonomously. It's built to allow you to start many sessions at once, so you can have multiple agents working in parallel. Codex is built to have "taste" OpenAI trained Codex to have the taste of a senior software engineer. It knows how big codebases work, how to write a good PR, and uses clean, minimal code. Why an “abundance mindset” is best for interacting with agents Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task like a difficult bug—it’s worth it even if only one of them succeeds. How OpenAI is thinking about agents Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes. OpenAI’s vision for the future of programming In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding. Watch below!

Dan Shipper 📧

145,487 次观看 • 1 年前

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.

Steve (Builder.io)

126,758 次观看 • 5 个月前

Every AI company I've talked to is solving the same problem: How to let several agents write to the same data without one silently undoing another's work? Omnigraph is an open-source graph database that versions data the way developers already version code: ↳ Each agent writes on its own branch ↳ Omnigraph checks every merge against the latest main ↳ A policy blocks direct writes to main GitHub repo: (don't forget to star it 🌟) To test this, I gave Codex and Claude Code one shared graph of services and teams, with one task each, as shown in the video below: - Codex moved a service from RabbitMQ to Kafka. - Claude Code handed that same service's on-call to a new engineer. Both agents started from the same version of that service. Codex merged cleanly, but Claude Code got flagged for a conflict, rebuilt its change on the latest main, and then merged. A row lock only helps when two agents hit the same record at the same moment. But an agent's task usually touches many records over several minutes. A branch keeps that whole change isolated until it merges, and each merge leaves a diff you can review and a history of who changed what. Omnigraph is written in Rust, and agents connect to it over MCP. I shared the GitHub repo above. To dive deeper, I wrote a full breakdown of why shared agent data needs branches, diffs, and merge checks, not just row locks. It walks through a real run with two Claude Code agents, from the refused merge to the clean retry. Read it below. Read it below.

Avi Chawla

16,277 次观看 • 4 天前