正在加载视频...

视频加载失败

Claude Code's full source code just leaked via a .map file in their npm registry. Direct link: One guy already backed it up on GitHub. Repo:

90,773 次观看 • 7 个月前 •via X (Twitter)

51 条评论

slash1s 的头像
slash1s7 个月前

also check out this new market

cristal💎 的头像
cristal💎7 个月前

source code leak is the ultimate alpha

slash1s 的头像
slash1s7 个月前

🫡

Gerard Sans | Axiom 🇬🇧 的头像
Gerard Sans | Axiom 🇬🇧7 个月前

Time zones did not help. Good morning SF! Anthropic skill prompt issue. They just needed: “DO NOT leak code. PLEASE (x3)” They didn’t get hacked. They just shipped the full 57 MB Claude Code CLI source, every prompt, every secret, to npm. Shadow repo. ↓

slash1s 的头像
slash1s7 个月前

🤔

Alex Fil 的头像
Alex Fil7 个月前

You mean this?

slash1s 的头像
slash1s7 个月前

yes👀

grev 的头像
grev7 个月前

That's really cool, thanks!

slash1s 的头像
slash1s7 个月前

welcome bro

magsimich 的头像
magsimich7 个月前

Alfa

Bizzi 的头像
Bizzi7 个月前

Time to dissect and customise to suit our needs.

slash1s 的头像
slash1s7 个月前

yep

Atenov int. 的头像
Atenov int.7 个月前

Someone's gonna get fired

slash1s 的头像
slash1s7 个月前

🤫

shmidt 的头像
shmidt7 个月前

interesting…

slash1s 的头像
slash1s7 个月前

🤫

RCOM 的头像
RCOM7 个月前

I guess Claude will visit that guy and explain why that was a crucial error 🤣

slash1s 的头像
slash1s7 个月前

😂😂

morph 的头像
morph7 个月前

new era for agents?

slash1s 的头像
slash1s7 个月前

will see👀

Artsy 的头像
Artsy7 个月前

Are our devises comprised?

slash1s 的头像
slash1s7 个月前

🤔

zostaff 的头像
zostaff7 个月前

is it true?

slash1s 的头像
slash1s7 个月前

yes bro

Bober_smart 的头像
Bober_smart7 个月前

this is useful

slash1s 的头像
slash1s7 个月前

yep.

leopardracer 的头像
leopardracer7 个月前

i'm going to analyze it

slash1s 的头像
slash1s7 个月前

gl bro

Yarchi 的头像
Yarchi7 个月前

source code leaking through a .map file is the most embarrassing way to ship lmao

slash1s 的头像
slash1s7 个月前

haha😅

Parletto 的头像
Parletto7 个月前

what possible doors does ths open tho?

slash1s 的头像
slash1s7 个月前

a lot..

Ragesh L 的头像
Ragesh L7 个月前

The Direct Link Show 404 Error Did you have any other Link original source code

slash1s 的头像
slash1s7 个月前

check the repo

Nano D. 的头像
Nano D.7 个月前

Check these graphs as well it will help a lot:

Mohammed AL-Majhali 的头像
Mohammed AL-Majhali7 个月前

You can run and customize your version here:

rari 的头像
rari7 个月前

👀👀👀 im very excited

slash1s 的头像
slash1s7 个月前

let's goo

kvro 的头像
kvro7 个月前

time to check it

slash1s 的头像
slash1s7 个月前

right now!

xofin 的头像
xofin7 个月前

H do we install it ?

Tramp 的头像
Tramp7 个月前

How can we use this in our favour?

Pavel Hegler 🫆 的头像
Pavel Hegler 🫆7 个月前

I just released their unreleased KAIROS feature:

Paone 的头像
Paone7 个月前

this is useful thx broski

cvxv666 的头像
cvxv6667 个月前

woah this could change the industry

slash1s 的头像
slash1s7 个月前

will see soon 😉

dunik 的头像
dunik7 个月前

This is very sad news, but everyone makes mistakes and that’s only natural

slash1s 的头像
slash1s7 个月前

sadly but true yes

Insomnia 的头像
Insomnia7 个月前

haha okay

Spivach 的头像
Spivach7 个月前

leaked because of being selfcoded? looks fun

slash1s 的头像
slash1s7 个月前

👀👀

相关视频

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,568 次观看 • 5 个月前