Pratique du Shadowing: 9 Insane Claude Mods I Already Can't live Without - Apprendre l'anglais à l'oral avec la vidéo

Choisissez un mode d'entraînement

Chaque mode ouvre une salle d'entraînement en plein écran.

223 phrases

Si les phrases sont trop courtes ou trop longues, cliquez sur Edit pour les ajuster.

Anthropic just launched mods for Cloud Code and I think it's one of the biggest updates they've shipped in a while.

With mods, Cloud can now build features for itself.

Any feature you wish

Cloud had, you just describe it and it builds it right into Cloud Code.

So in this video, I'll explain what a mod is and how easy it is to build one.

I'll show you the nine best mods to use after analyzing, building and trying out more than a hundred different ones over the last weeks.

And I'll give away all of the mods for free so you can install them for yourself.

Now, if you don't know me yet, I'm Ben, I'm a three -time founder and now run an AI agency

and one of the largest AI communities for professionals and business owners,

where I teach how to use AI to actually automate work or build an AI business.

So what is a mod?

A mod is basically a plugin that changes how

Cloud Code looks and behaves, both in the desktop app or in the terminal.

Now, you can essentially use or build mods that customize how the interface or harness itself looks or behaves,

which is really powerful because it can drastically improve the way you work with AI.

And it's really a reason to consider switching to the Cloud Code tab if you're still used to working in Cloud Cowork.

The easiest way to explain a mod is by giving you an example of the first mod that I built,

which already really improves the way I work with AI, the Brain Dump mod.

Now, many people, including me, do a lot of long voice brain dumps when prompting Cloud.

But these brain dumps often get messy.

Voice transcriptions often contain errors.

They jump around a lot.

They're, of course, very unstructured and sometimes even contradict themselves.

So I build a mod that automatically turns these messy brain dumps into a clear structured prompt before

Cloud even processes it.

And the way a mod works is very simple.

Every time something happens in Cloud Code, it sends out a signal.

For example, when you send a prompt, when Cloud is about to use a tool, when a sub -agent starts, or when Cloud finishes a reply.

A mod just listens for one of those signals and can then do something when that signal fires.

So my brain dump mod listens for the moment I send a prompt.

It then automatically checks if what I just sent is a long, massive brain dump.

And if it is, it blocks it.

So the prompt is held back before Claude gets it.

And then in this case, it uses another AI model in the background to ask me a few clarifying questions about my brain dump

and then turns that into a clear prompt according to Entropic's best practice prompting framework, covering the task, the why,

the guardrails, and what done looks like.

Cloud can then process that clear prompt instead of my messy brain dump.

So that's really what a mod is.

You make it listen for a signal and it can then watch, change or block what happens.

And with those few building blocks, you can build almost any feature you want.

And making mods yourself is really easy.

You just describe what you want and Cloud builds it.

In this case, I said something like build me a mod that catches my long voice brain dumps,

ask me a few clarifying questions and then rewrite the prompt into my prompting framework.

Claude then uses its built -in skill called plugin authoring to build the mod for you.

And if something doesn't work the way you want, you just tell Claude what to change, just like with a skill.

Now, finally, there are basically two types of mods.

Ones that use AI, like this one, which uses your plan's usage, just like a normal message,

and ones that only track or show things on screen, which cost nothing to run.

Now, all of the mods

that I'll show in this video will be in a zip

file in the free resources in the first link in the description below, which you can just throw into a Claude chat

and say install these mods for me and Claude will then add them to your own account.

Now the second mod is one of my favorites and it's called helper desk.

In short it shows you exactly what your sub -agents are doing while Claude works.

If you've been using newer models like Opus 5 .5 you know they use a lot of sub -agents.

For example every time I ask Claude to help me ideate on a new video

it spins up a bunch of sub -agents to do the research.

Now this is generally good because Claude can analyze more things faster

and keep the main chat clean

but the problem with this is there's no real way to see what each subagent is doing,

how much it's spending, or how far along it is.

So you just sit there not knowing if it will take another 5, 10, or 15 minutes.

So this mod fixes that in two ways.

First, it'll give you a purple taskbar right above your prompt box

that fills up every time a to -do gets ticked off, so you see how far along the whole job is,

and which step it's on right now.

And second, you get a side panel where every subagent gets its own little cloth crap, with its own color, its own progress bar,

and what it's costing you.

So you can see exactly which one is slowing things down

and how they add up to the total cost of your chat.

Now this mod just watches every time

Cloud starts a sub -agent or ticks off a to -do and then changes what

Cloud code shows on screen by drawing the taskbar and the side panel.

So it doesn't use any AI to do that.

So it costs nothing to run.

And because it's a mod, you can ask

Cloud to change how it looks, for example, to give each sub -agent a name that matches its role.

Now credit to Johnny Savvy's a progress mod for this one, which I used as inspiration, but I rebuilt this mod for my own workflow.

Now the next mod has made a real difference to my token spend and it's called cash plot.

In short, it tells you exactly when an old chat is about to get expensive and can keep it cheap for you.

Now, if you use plot a lot, you probably have a few long chats you keep coming back to,

for example, after lunch or the next morning.

But what most people don't know is that coming back to an old chat can cost you far more than you think.

And that's because of something called the cash every time you send a message Claude rereads your entire chat.

And to make that cheaper, Entropic saves a copy of your chat on its own servers after every reply,

which is called the cache or keeping your chat warm.

And while the chat is warm, Claude just reads that saved copy for a fraction of the normal price.

On Opus 5 .5, only a 20th of that normal price.

But that saved copy only lives there for a limited amount of time.

And once that timer runs out, the chat or cache goes cold,

which means that saved copy is gone and Claude has to reread and save the whole chat again at full price.

And on a long chat that can make the same message up to 40 times more expensive.

For example, on a long Opus 5 .5 chat, that's about 4 cents warm versus $1 .6 cold every single time you come back.

And that timer is actually very short, one hour on a Claude subscription and only five minutes with an API key.

And the problem is you have no idea when that timer actually runs out.

So the cash clock mod listens for the moment clod finishes its reply

and then shows a countdown until your chat goes cold using the timer straight from entropic's own reply

so it's not a guess and

100

if you know you'll come back to the chat later maybe after lunch you just click keep warm

101

or type slash keep warm then right before the cache goes cold it sends a small hidden message

102

that keeps the entire chat warm so the timer starts again

103

that costs only a few cents each time

104

which is of course far less than one called restart

105

and it stops by itself when you send your next message or after two hours.

106

Credits to Karan Bensal for this one whose cash tax mod inspired this one.

107

Now the next mod is one that I built myself and it works really well together with cash clock.

108

It's called handoff

109

and in short it moves your work to a fresh chat

110

at the right moment without losing any context from your original chat.

111

Now if you work with Claude on bigger projects you know chats can get really long

112

and the longer a chat gets the worse the answers get.

113

That's because Claude can only hold so much in its short term memory for a single chat, which is also called the context window.

114

So the fuller it gets, the harder it is for Claude to keep track of everything so it starts missing details and mixing things up,

115

which is also called context rot.

116

Now, Claude tries to fix this of course by compacting the chat,

117

which basically means it summarizes the older parts to free up space in the chat.

118

But a summary always loses some details so the answers still get worse over time.

119

And if the cash has gone cold on top of that, every new message will cost you far more too.

120

So at some point, you do want to start a fresh chat without losing all of the context

121

and progress you've built up, of course.

122

But it's hard to know when to actually do that.

123

Now, this mod fixes both these problems and it can fire in three different moments.

124

First, when your chat hits 250 ,000 tokens, which is sort of the cutoff point for Claude losing a little bit of its performance.

125

Second, when the cash clock sees the cash go cold.

126

And third, you can just type in slash handoff to trigger it.

127

It then reads the whole chat, all the files

128

Cloud used or created in the chat, the skills, the tools, and the links it used,

129

and then writes a well -structured handoff prompt for the new chat that's much more detailed than the short summary

130

Cloud makes when it compacts a chat.

131

And you then get a simple button to start a fresh chat with that prompt

132

so the new chat knows exactly where you left off with all of the context of the progress in the next steps.

133

And because it's just a prompt, you can also use it to hand the task over to someone else on your team

134

so they can pick up exactly where you stopped.

135

But before I show you the next one, very quickly, if you enjoy this type of content, you'll really enjoy my AI Accelerator,

136

where you get access to my 30 -day cloud course

137

that takes you from beginner to pro in less than one hour a day.

138

A full course on growing an AI business based on everything me

139

and my team have learned over the last three years running an AI agency.

140

You also get access to unlimited one -on -one live AI consulting with AI experts and a big library of skills,

141

templates, and resources across all business departments.

142

So definitely check it out in the link in the description below.

143

Now, the fifth mod is a really good way to make

144

Cloud actually remember your rules and preferences, and it's called Reflect.

145

In short, it spots when you give

146

Cloud a rule and asks you where you want to save that rule.

147

Now, if you use

148

Cloud Code, you might know it has auto memory.

149

So it saves some things that it thinks are relevant in Cloud's built -in memory

150

or if you have a cloud .md or an agents .md

151

and maybe a second brain it can save it in there too.

152

Now that's generally really good but we don't really control what it saves

153

and what it forgets and often it just doesn't save things

154

or rules that actually would be great to have in your memory.

155

So this mod fixes that by listening to every prompt you send in every chat

156

and checking if you just gave cloud a hard rule.

157

For example something like never use mdashes or keep LinkedIn hooks under 12 words

158

and if it spots one of those hard rules you automatically get a pop -up asking

159

if you want to save it to your built -in memory, your Cloud .md, or your second brain if you work with one.

160

And if you want your role saved somewhere specific, for example in a skill, you can just ask

161

Cloud to change the mod to however you want it to work.

162

Now credit to Bayram Anorkov's Cloud Reflect skill that inspired me to build this mod.

163

Now the next mod is the one that really helped me move from CoWork to Cloud Code and it's called Chat Inventory.

164

Now the reason I did many of my tasks in CoWork instead of Code until recently is because of its UI.

165

If you've used CoWork you know its side panel where you see the to -do list, the connectors and skills

166

Cloud is using and the files it's reading and creating.

167

It's one of the things I like most about CoWork because you always know what

168

Cloud is actually doing and the Cloud Code tab just doesn't show you that.

169

So especially on longer tasks it feels a little bit like a black box.

170

So this mod that I built listens for every tool call, connector call, and skill that

171

Cloud uses during a chat and keeps track of them in a side panel called in this chat.

172

So just like in cowork, you see the to -do list with the goal at the top,

173

every connector Cloud is calling with its logo and how many times it's called, the skills it's using, and the files it's reading and creating.

174

For example, when Cloud builds a client report from your CRM, your email, and your drive, you can see exactly where it pulled everything from.

175

And because it only keeps track of what's happening and doesn't use any AI, it costs nothing to run.

176

Now the 7 mod is really useful for me and it's called a screen share mode.

177

In short, it hides private information in your cloud code chats whenever someone else can see your screen.

178

Now think about how often your cloud chats can end up on someone else's screen.

179

Maybe you share your screen in a team meeting, on a sales call, or during a training,

180

or maybe you record videos for social media like me, or quick looms to show a teammate how you did something

181

and the moment you do everything in

182

that chat is out there client names email addresses deal values even your own personal details

183

and most of the time you only notice when it's already too late so

184

when you turn this mod on by just typing slash screen share before

185

you share your screen it changes what cloud code shows on screen

186

so every name email phone number

187

and dollar amount turns into a gray bar now for me of course this one's perfect

188

because I record a lot of my own chats for these videos

189

and before I had to make up fake client names now I just turn on screen share mode

190

and use my real chats.

191

Now the next mod comes straight from Anthropic and it's called Replay Theater.

192

In short it replays every edit Claude made to your file so you can see exactly what changed.

193

Now if you do a lot of copywriting

194

or design work with Claude you know how many edits a single draft can go through.

195

For example you ask Claude to tighten your newsletter draft it makes a dozen changes in one go

196

and now you have no idea what it caught or rewrote.

197

And until now, the only way to find out was to compare the versions yourself or ask Claude to list every change.

198

Now, this mod keeps track of every change Claude makes to your file.

199

After Claude's reply, you just type slash replay and it basically plays back all those changes one after the other.

200

So you see exactly what Claude changed and you can go back to an earlier version you like better.

201

Now, keep in mind, it only works on files.

202

So your draft needs to be a document cloud edits, not just text in a chat.

203

Now the last mod is another one that I built myself and it becomes really important once you get into mods.

204

It's called Switchboard and in short it lets you see and switch off every mod you're running all in one place.

205

Now trust me, once you start you'll end up building,

206

installing and testing a lot of mods and the same thing will happen that happened with skills for many people.

207

People installed hundreds of them and I had no idea which ones were actually on their account, which ones they're using etc.

208

And right now there's no quick way in the desktop app to see every mod that's running

209

or to switch one off in the middle of a chat.

210

So this mod adds one simple command.

211

When I type slash mods, it opens a switchboard with every mod that's running right now.

212

I can turn each one on or off and hide the extra panels some mods add to my screen.

213

So if a mod gets in the way during a task,

214

I just switch it off and every new mod I add shows up in this list by itself.

215

So I never lose track of what's running.

216

Now again, you can download all of the mods for free in the first link in the description below.

217

And if you want to get access to my full 30 -day

218

Cloud course that takes you from beginner to pro in less than one hour a day, unlimited one -on -one AI consulting,

219

a full AI business course, and a community with professionals and business owners actively using AI,

220

you can check out my AI accelerator in the link in the description.

221

As always, thank you so much for watching.

222

And if you enjoyed this video, I highly appreciate a like and a subscribe.

223

And if you want to learn more about Cloud Code, you can check out the video here above.

Télécharger l'application

Tout pour parler couramment

Prononciation IAChaque phrase notée

Phonétique (IPA)Maîtrisez chaque son

VocabulaireEnrichissez votre lexique

Jeu de vocabulaireApprenez en jouant

Scanner le QR

Download on theApp Store Get it onGoogle Play

Même chaîne

Claude 2.0 is Insane (All Updates Explained)

Daily ConversationWorking Adults

FOR YOU

Vidéo recommandée

340 phrases

Vocabulaire et conseils d’expression pour cette leçon

Cette leçon d’expression orale s’appuie sur la vidéo « 9 Insane Claude Mods I Already Can't live Without ». Les mots qui reviennent le plus souvent : mod, chat, cloud, Claude, code. Cette vidéo contient 223 phrases et 3192 mots à répéter en shadowing. La partie parlée dure 14:06. Le locuteur parle vite, environ 226 mots par minute : attendez-vous à des liaisons et à des sons réduits. 83 % des mots font partie des 3 000 mots les plus courants en anglais ; le reste mérite d’être vu avant de commencer.

Vocabulaire clé de cette vidéo

15 mots de la vidéo à retenir, avec leur prononciation et leur sens :

Mot	Prononciation	Sens
cloud nom	/ˈklaʊ̯d/	nuage
prompt verbe	/pɹɑmpt/	inciter
dump verbe	/dʌmp/	se débarrasser de
skill nom	/skɪl/	habileté, compétence
timer nom	/ˈtaɪmɚ/	minuteur
clock nom	/klɑk/	indicateur de vitesse, compteur de vitesse
edit verbe	/ˈɛdɪt/	modifier, corriger
install verbe	/ɪnˈstɔl/	installer
messy adjectif	/ˈmɛsi/	désordonné, désorganisé
cache nom	/kæʃ/	cache, mémoire cache
summary nom	/ˈsʌm.ə.ɹi/	résumé, sommaire
unlimited adjectif	/ʌnˈlɪm.ɪ.tɪd/	illimité
compact adjectif	/kəmˈpækt/	compact
behave verbe	/bɪˈheɪv/	se comporter
inspire verbe	/ɪnˈspaɪə(ɹ)/	inspirer

Les verbes à particule que vous entendrez

Mot	Sens
check out verbe	mater, regarder
run out verbe	épuiser, être à court
come back verbe	revenir
end up verbe	se terminer, se finir
fill up verbe	remplir
find out verbe	découvrir, savoir
give away verbe	offrir, donner
go through verbe	traverser

La grammaire de cette vidéo

Les structures que le locuteur utilise le plus, avec les mots exacts de la vidéo :

Structure	Dans la vidéo
Phrases conditionnelles if + proposition, will/would + verbe — une condition et son résultat	if you know you'll come
Present perfect have/has + participe passé — une action passée qui compte encore maintenant	they've shipped · has made · has gone
Voix passive be + participe passé — l’accent est mis sur ce qui arrive, pas sur qui le fait	is held · is called · is also called
Propositions relatives who / which + proposition — une précision sur une personne ou une chose	chat, which is · tokens, which is

Prononciation à surveiller

Le locuteur utilise 26 contractions et formes réduites, comme doesn't, I'll, don't. Prononcez-les sous leur forme courte, telles que vous les entendez.

Les sons « sh » et « zh »: cache /kæʃ/, essentially /ɪˈsɛnʃəli/, inspiration /ˌɪn.spɪˈɹeɪ.ʃən/, subscription /səbˈskɹɪpʃən/, fraction /ˈfɹæk.ʃən/
Mots longs — placez bien l’accent: unlimited /ʌnˈlɪm.ɪ.tɪd/, essentially /ɪˈsɛnʃəli/, inspiration /ˌɪn.spɪˈɹeɪ.ʃən/, automobile /ˈɔː.tə.məˌbil/, accelerator /əkˈsɛl.əˌɹeɪ.tɚ/

Les sons difficiles pour les francophones :

/h/ — il se souffle, il n’est pas muet: behave /bɪˈheɪv/, hook /hʊk/, harness /ˈhɑɹ.nəs/, helper /ˈhɛlpɚ/
/tʃ/ et /dʒ/ — à ne pas adoucir en « ch » et « j »: usage /ˈjuːsɪd͡ʒ/, subagent /ˌsʌbˈeɪ̯.d͡ʒənt/, switchboard /ˈswɪt͡ʃˌbɔɹd/
/r/ anglais — langue recourbée, sans frotter la gorge: prompt /pɹɑmpt/, replay /ˈɹiːpleɪ/, summary /ˈsʌm.ə.ɹi/, framework /ˈfɹeɪm.wɜːk/, inspire /ɪnˈspaɪə(ɹ)/

Comment s’entraîner avec cette vidéo

Écoutez la vidéo en entier une fois sans parler et notez les mots que vous ne connaissez pas.
Commencez à la vitesse 0,75×, répétez phrase par phrase, puis revenez à la vitesse normale quand cela devient facile.
Enregistrez-vous et comparez avec l’original, en faisant attention à des mots comme cloud, prompt, dump.

Qu'est-ce que la technique du Shadowing ?

Le Shadowing est une technique d'apprentissage des langues fondée sur la science, développée à l'origine pour la formation des interprètes professionnels. Le principe est simple mais puissant : vous écoutez de l'anglais natif et le répétez immédiatement à voix haute — comme une ombre suivant le locuteur avec un décalage de 1 à 2 secondes. Les recherches montrent une amélioration significative de la précision de la prononciation, de l'intonation, du rythme, des liaisons, de la compréhension orale et de la fluidité.

Technique du shadowing : lire le guide complet étape par étape →

Pratique du Shadowing: 9 Insane Claude Mods I Already Can't live Without - Apprendre l'anglais à l'oral avec la vidéo

Choisissez un mode d'entraînement

Télécharger l'application

Claude 2.0 is Insane (All Updates Explained)

Claude Code Mods Explained: Customize Your Setup

It’s not just you

Opus 5.5 Just Changed Video Editing Forever (free skills)

Give Me 24 minutes, I'll Give You 1,000+ hours of Claude Knowledge

GitHub Copilot now controls your command line...

JUST $1 For Billions of Tokens?! (DeepSeek v4 Pro)

How I deploy serverless containers for free

LangChain in 5 Minutes (Explained Clearly)

The Engineering that Runs the Digital World 🛠️⚙️💻 How do CPUs Work?

How I Learned Procedural Generation

When AIs act emotional

The easy way to keep your repos tidy.