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... show more
27 条评论

Source for the skills and how to install them here:

Read the damn docs is so real 😭😭😭

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

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*

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

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.

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?

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

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.

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

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。

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

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

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

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

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

让一个代理盯另一个,听着就很打工人

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

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

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.

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

Super dope! Thanks for sharing!

today I was trying this one

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

almost always catches something meaningful in my experience

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

good idea, I’ll do that



