Практика Shadowing: How to actually force Claude Code to use the right CLI (don't use CLAUDE.md) - Изучайте разговорный английский по видео

Выберите режим практики

Каждый режим открывает полноэкранную комнату практики.

96 предложений

Если предложения слишком короткие или длинные, нажмите Edit, чтобы их изменить.

One of the most common questions I get about agents

and about claw code is how do I force it to use the right CLI command?

How do I force it to adopt my workflow instead of the workflow that it knows best?

For instance, how do I get it to use PNPM instead of NPM?

How do I get it to call this wrapper script that we wrote instead of calling the thing directly with NPX?

How do I prevent it from using certain commands and only allow it to use other commands?

If you're interested in these kind of questions, this is the stuff that I answer on my newsletter.

I'm working on a Claude code course right now for real engineers, not Vibecoders.

So if you dig that stuff, the link is down below.

The first thing that you probably think about

when you think about steering Claude in one direction but not another is to put information in a Claude.md file.

In other words, to proactively tell it to use PNPM, not NPM.

Now, this will be pretty effective most of the time, especially if like this, you have a Claude.md file that is nearly empty apart from that one instruction.

However, in various places, including in the previous video I just posted, I've advocated almost always deleting your claw.md.

Because if you think about it, this instruction here is only relevant for certain tasks, and putting it in claw.md makes it global for every action that you're going to do in the repo.

LLMs have an instruction budget

that you can really only put about 500 instructions in before it starts getting less

and less powerful and more and more confused.

And we want our LLM thinking about the complicated plans and the implementation that it's going to put together, not having irrelevant instructions about using NPM or PNPM.

And the final thing that makes me uncomfortable about this is the fact

that it's not a deterministic way of preventing a command.

For instance, we may want to disallow it from running destructive commands.

For instance, we never want it to git push.

These kind of negative instructions to the LLM are really bad,

I think, because they burn instruction budget in something that we're not actually using the instruction budget to prevent deterministically.

By adding this, we're reducing our chances of running git push or reducing our chances of running NPM, but we're not preventing it.

So instead, I'm going to show you an approach that prevents it deterministically and guides the LLM towards the correct solution.

The way to do this is via Claude Code hooks.

Hooks allow you to run deterministic code at certain points during Claude Code's execution cycle.

When one of these events fire, all matching hooks run in parallel.

So for instance, you can run a hook when the session starts.

You can run a hook when a permission dialogue appears to automatically approve things.

The one that we're interested in is pre-tool use before a tool call executes can block it.

Our plan here is to use this pretool use hook to before it calls npm to use pnpm instead.

And the cool thing about this is that Claude code already knows how to do this.

And I've actually prepared a prompt inside this file to take the Claude.md, turn it into deterministic hooks, and then put those hooks into your project.

Here's what it looks like.

Take the instructions in your Claude.md file, turn them into deterministic Claude code hooks in this project directory.

Not Once all the instructions will be deterministic, only do the ones you can, such as instructions to use one CLI command over another or disallowing certain CLI commands.

Use separate bash scripts for running the hooks, in other words this is its own .sh file and it gives some syntax here for how to construct that.

This is directly lifted from the Claude code docs.

And then finally below here, first confirm with the user which hooks will be created,

second implement the hooks, third provide the user with instructions on how to test the newly created hooks.

I'll include this in an article which is linked below for you.

So I'm going to copy and paste this, I'm going to go into a fresh Claude Code session here, I'm going to zoom up the terminal a bit, I'm going to paste it in and see what happens.

Alright, it's given me two options here.

It says there are two rules that can be enforced deterministically, block NPM commands or block git push.

Now I've actually it already got some git push blockers in my global setup so I'm just going to say, yeah, do the npm one only.

So that sounds good.

Let's run this and see what happens.

So it's now given us something to review.

It's given us a nice version of the bash command that we saw earlier, except it just checks if it's npm.

Crucially it's checking if the command starts with npm as a command.

It echoes use pnpm not npm and then it exits with an exit code of 2.

So that is looking good to me.

Let's accept that.

It's then going to make it executable by running chmod plus x, so I'm happy with that.

It's then created the configuration inside settings.json here, where we've got now hooks, which is a property on the settings, pretool use, which is the one we saw earlier.

It's matching any bash tools here.

And then when it matches any bash tool, it runs this command, block npm.sh.

So that looks good to me.

We're in a good spot.

And it's now appearing to verify that the hook works in line.

I'm just going to try and run this to see what happens.

And you can see here just up there it said blocked use PNPM not NPM.

So we're definitely getting somewhere.

And finally it's given us some instructions here to test it.

To restart claw code in this project try asking it to run something like NPM install foo.

Alright the first thing I'm going to do is actually remove the instruction from claw.md here.

And then we're going to pull open a fresh clawed code instance

and we're going to say npm install let's say React query.

Okay, let's give it something kind of juicy.

And we can see that the pre-tooled use here,

it said bash hook error blocked use pnpm not npm and now it's running pnpm install tanstat react query instead.

So that's it.

We have prevented one command and we've automatically steered it to use another command.

And crucially we've managed to kill an instruction inside our global clawed.md file.

This is what I love so much about this approach.

You get to take instructions out of your instruction budget and enforce them deterministically.

This means that the instructions that we have in clawed.md, they are available just in time.

They get to hover in the background until clawed actually progressively kind of discovers them.

And this idea of these rules just being enforced just in time, you can take this and apply it to lots of different things.

For instance, I've been turning my style rules, like I really hate positional parameters in functions, and turning them into ESLint rules so

that I can lint Claude into the right thing without needing to warn it or instruct it.

So creating these feedback loops for Claude is so, so powerful.

Now if you dig this, then this and all of my ideas are going to be in my newsletter, so you never miss a trick.

And the link for that is below if you want to click it and sign up.

But thank you so much for watching.

I've been having a blast making these videos and discovering lots of new ideas about Clawed.

What else do you think you can do with Hooks?

What else do you want to see me cover with Clawed Code?

And now of course Clawed is not the be all and end all, right?

Like I'm pretty keen to try out other coding agents too.

And the Hooks idea is not exclusive to Clawed too, so you can take this knowledge and probably take it to Codex or whatever you're using.

But anyway, that's enough rambling.

Thanks for watching and I'll see you in the next one.

Скачать приложение

Всё для свободной речи

ИИ-оценка произношенияОценка каждой фразы

Практика IPAОсвойте каждый звук

СловарьСоберите свой словарный запас

Игра со словамиУчитесь играя

Сканировать QR

Download on theApp Store Get it onGoogle Play

Тот же канал

New Skills! v1.1 brings /wayfinder, /research, /implement, /to-spec, /to-tickets

Business EnglishUniversity StudentsWorking Adults

Most devs don't understand what agents are

Daily ConversationUniversity StudentsWorking Adults

Most devs don't understand how LLM tokens work

Business EnglishUniversity StudentsWorking Adults

New Skills! /handoff, /prototype, /review and /writing-* | Skills Changelog

Business EnglishUniversity StudentsWorking Adults

FOR YOU

Об этом уроке

В этом уроке вы научитесь справляться с типичными вопросами о настройках агента Claude Code и использовании правильных CLI-команд. Мы обсудим, как управлять вашими проектами, используя определенные команды, такие как PNPM и NPM. Также вы получите новое понимание того, как важно правильно организовать инструкции в вашем проекте, чтобы сделать взаимодействие более эффективным. Это особенно полезно для тех, кто хочет учить английский с YouTube, заимствуя Целевой язык программирования в English.

Ключевая лексика и фразы

CLI - интерфейс командной строки, способ взаимодействия с программами.
PNPM - альтернативный пакетный менеджер для Node.js, используемый вместо NPM.
Инструкции - команды, которые вы даете Claude Code для выполнения определенных действий.
Hooks - механизмы для выполнения кода в определенные моменты выполнения программ.
git push - команда, используемая для отправки изменений в удаленный репозиторий.
детерминировано - значит, что результат будет предсказуемым.
проект - набор файлов и инструкций, связанных с вашей рабочей средой программирования.
скрипт - файл, содержащий команды, которые выполняются в определенной среде.

Советы по практике

Чтобы максимально эффективно использовать содержание этого видео, рекомендуем применять технику shadowing. Слушайте и повторяйте фразы из видео в темпе говорящего, уделяя внимание интонации и ударениям. Это поможет улучшить ваше произношение и уверенность в разговорном английском. Обратите внимание на использование технического языка и специфической лексики, связанной с программированием, что может оказаться полезным не только для понимания, но и для применения в реальных ситуациях.

Кроме того, вы можете использовать shadowspeaks, чтобы синхронизировать вашу речь с видео. Воспроизводите каждую фразу, стараясь уловить ритм и мелодику языка. Упражнения с shadow speech помогут вам уверенно говорить на английском, делая акцент на практических аспектах, что особенно важно для тех, кто стремится изучать английский через YouTube.

Регулярная практика разговорного английского и внимание к мелочам помогут вам стать более уверенным спикером, что значительно улучшит ваши навыки

Грамматика в этом видео

Конструкции, которые говорящий использует чаще всего, с точными словами из видео:

Конструкция	В видео
Present Perfect Continuous have/has been + -ing — действие началось раньше и продолжается	I've been turning · I've been having
Пассивный залог be + причастие прошедшего времени — важно, что происходит, а не кто это делает	is directly lifted · will be created · is linked
Present Perfect have/has + причастие прошедшего времени — прошлое действие, важное сейчас	I've advocated · I've actually prepared · have prevented
Придаточные определительные who / which + предложение — уточнение о человеке или предмете	article which is · hooks, which is

Что такое техника Shadowing?

Shadowing — это научно обоснованная техника изучения языка, изначально разработанная для подготовки профессиональных переводчиков и популяризированная полиглотом доктором Александром Аргуэльесом. Метод прост, но эффективен: вы слушаете аудио на английском от носителей языка и немедленно повторяете вслух — как тень, следующая за говорящим с задержкой в 1–2 секунды. В отличие от пассивного прослушивания или грамматических упражнений, Shadowing заставляет мозг и мышцы рта одновременно обрабатывать и воспроизводить реальные речевые паттерны. Исследования показывают, что это значительно улучшает точность произношения, интонацию, ритм, связную речь, понимание на слух и беглость речи — что делает его одним из самых эффективных методов для подготовки к IELTS Speaking и реального общения на английском.

Техника шедоуинга: читать полное пошаговое руководство →

Практика Shadowing: How to actually force Claude Code to use the right CLI (don't use CLAUDE.md) - Изучайте разговорный английский по видео

Выберите режим практики

Скачать приложение

Тот же канал

New Skills! v1.3 brings /pr, /implement-spec, and /retro

mattpocock/skills: A complete AI Coding workflow, end-to-end

I was an AI skeptic. Then I tried plan mode

/wayfinder: Nothing is too big to plan anymore

The 7 phases of AI-driven development

New Skills! v1.2 brings /wait-what, /writing-for-agents, and fixes /grill-me

Learn anything with the /teach skill

5 Claude Code skills I use every single day

Can Cursor's HARDCORE Review Skill Stop The Slop?

New Skills! v1.1 brings /wayfinder, /research, /implement, /to-spec, /to-tickets

Most devs don't understand what agents are

Most devs don't understand how LLM tokens work

New Skills! /handoff, /prototype, /review and /writing-* | Skills Changelog

Рекомендуемое видео

Claude Code: The Advanced Guide (99% of Devs Skip These Features)

How to Force Your Brain to Crave Doing Hard Things

What is clean code? - Uncle Bob

Tragic mistake... Anthropic leaks Claude’s source code

JavaScript Visualized - Event Loop, Web APIs, (Micro)task Queue

How I Learned Procedural Generation

MCP Just Got a Whole Lot Better

Articulate Your Thoughts Clearly: 3 PRECISE Steps!

GitHub Copilot now controls your command line...

PLC Programming #5: User-Defined Data Types (UDTs) Explained

Об этом уроке

Ключевая лексика и фразы

Советы по практике

Грамматика в этом видео

Что такое техника Shadowing?