The Claude Code Source Leak: fake tools, frustration regexes, undercover mode • Hacker News Board

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#11

Post by simianwords » Tue, Mar 31, 2026, 6:41 PM UTC

alex000kim wrote: post #9

simianwords wrote: post #5

> The obvious concern, raised repeatedly in the HN thread: this means AI-authored commits and PRs from Anthropic employees in open source projects will have no indication that an AI wrote them. It’s one thing to hide internal codenames. It’s another to have the AI actively pretend to be human. I don’t get it. What does this mean? I can use Claude code now without anyone knowing it is Claude code.

technically you're correct, but look at the prompt https://github.com/alex000kim/claude-code/blob/main/src/util... it's written to _actively_ avoid any signs of AI generated code when "in a PUBLIC/OPEN-SOURCE repository". Also, it's not about you. Undercover mode only activates for Anthropic employees (it's gated on USER_TYPE === 'ant', which is a build-time flag baked into internal builds).

I don’t know what you mean. It just informs to not use internal code names.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#12

Post by ripbozo » Tue, Mar 31, 2026, 6:41 PM UTC

I don't understand the part about undercover mode. How is this different from disabling claude attribution in commits (and optionally telling claude to act human?)

On that note, this article is also pretty obviously AI-generated and it's unfortunate the author didn't clean it up.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#13

Post by seanwilson » Tue, Mar 31, 2026, 6:42 PM UTC

Anyone else have CI checks that source map files are missing from the build folder? Another trick is to grep the build folder for several function/variable names that you expect to be minified away.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#14

Post by peacebeard » Tue, Mar 31, 2026, 6:42 PM UTC

The name "Undercover mode" and the line `The phrase "Claude Code" or any mention that you are an AI` sound spooky, but after reading the source my first knee-jerk reaction wouldn't be "this is for pretending to be human" given that the file is largely about hiding Anthropic internal information such as code names. I encourage looking at the source itself in order to draw your conclusions, it's very short: https://github.com/alex000kim/claude-code/blob/main/src/util...

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#15

Post by giancarlostoro » Tue, Mar 31, 2026, 6:44 PM UTC

simianwords wrote: post #11

alex000kim wrote: post #9

Earlier quoted context omitted.

technically you're correct, but look at the prompt https://github.com/alex000kim/claude-code/blob/main/src/util... it's written to _actively_ avoid any signs of AI generated code when "in a PUBLIC/OPEN-SOURCE repository". Also, it's not about you. Undercover mode only activates for Anthropic employees (it's gated on USER_TYPE === 'ant', which is a build-time flag baked into internal builds).

I don’t know what you mean. It just informs to not use internal code names.

I agree with you, I think people are overthinking this.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#16

Post by simianwords » Tue, Mar 31, 2026, 6:44 PM UTC

> The multi-agent coordinator mode in coordinatorMode.ts is also worth a look. The whole orchestration algorithm is a prompt, not code.

So much for langchain and langraph!! I mean if Anthropic themselves arent using it and using a prompt then what’s the big deal about langchain

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#17

Post by robflynn » Tue, Mar 31, 2026, 6:45 PM UTC

simianwords wrote: post #11

alex000kim wrote: post #9

Earlier quoted context omitted.

technically you're correct, but look at the prompt https://github.com/alex000kim/claude-code/blob/main/src/util... it's written to _actively_ avoid any signs of AI generated code when "in a PUBLIC/OPEN-SOURCE repository". Also, it's not about you. Undercover mode only activates for Anthropic employees (it's gated on USER_TYPE === 'ant', which is a build-time flag baked into internal builds).

I don’t know what you mean. It just informs to not use internal code names.

It also says don't announce that you are AI in any way including asking it to not say "Co-authored by Claude". I read the file myself.

I'm still inclined to think people might be overreacting to that bit since it seems to be for anthropic-only to prevent leaking internal info.

But I did read the prompt and it did say hide the fact that you are AI.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#18

Post by AnimalMuppet » Tue, Mar 31, 2026, 6:47 PM UTC

anonymoushn wrote: post #7

OfirMarom wrote: post #4

Undercover mode is the most concerning part here tbh.

why

Well, as a general rule, I don't do business with people who lie to me.

You've got a business, and you sent me junk mail, but you made it look like some official government thing to get me to open it? I'm done, just because you lied on the envelope. I don't care how badly I need your service. There's a dozen other places that can provide it; I'll pick one of them rather than you, because you've shown yourself to be dishonest right out of the gate.

Same thing with an AI (or a business that creates an AI). You're willing to lie about who you are (or have your tool do so)? What else are you willing to lie to me about? I don't have time in my life for that. I'm out right here.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#19

Post by dkenyser » Tue, Mar 31, 2026, 6:47 PM UTC

peacebeard wrote: post #14

The name "Undercover mode" and the line `The phrase "Claude Code" or any mention that you are an AI` sound spooky, but after reading the source my first knee-jerk reaction wouldn't be "this is for pretending to be human" given that the file is largely about hiding Anthropic internal information such as code names. I encourage looking at the source itself in order to draw your conclusions, it's very short: https://git…

> my first knee-jerk reaction wouldn't be "this is for pretending to be human"...

"Write commit messages as a human developer would — describe only what the code change does."

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#20

Post by giancarlostoro » Tue, Mar 31, 2026, 6:47 PM UTC

ripbozo wrote: post #12

I don't understand the part about undercover mode. How is this different from disabling claude attribution in commits (and optionally telling claude to act human?) On that note, this article is also pretty obviously AI-generated and it's unfortunate the author didn't clean it up.

It's people overreacting, the purpose of it is simple, don't leak any codenames, project names, file names, etc when touching external / public facing code that you are maintaining using bleeding edge versions of Claude Code. It does read weird in that they want it to write as if a developer wrote a commit, but it might be to avoid it outputting debug information in a commit message.