Mertcan Sağlam's profile on Product Hunt

About

Co-founder of shim. We build tools that show what goes to AI models and mask personal data on the way. shim-cli, our open-source tool for coding agents, is on GitHub. Data engineering background (Migros, Obase). You can call me shimcan

Badges

Top 5 Launch

Tastemaker

Gone streaking 10

Gone streaking

View all badges

Maker History

shim-cliSee what your coding agent sends. Mask what you can.
Oct 2026
shimA masking and audit layer between your team and AI models
Jan 2026

🎉

Joined Product HuntJanuary 18th, 2026

Forums

p/shim-cli

•

7d ago

What shim-cli can't do

We launched today, and we'd rather you hear the limits from us before you install.

A prompt you type into Claude Code or Codex is not masked, because neither client lets a hook rewrite it. shim reports it, or blocks it under enforce. Copilot CLI is the exception: there the model gets the masked prompt.
In Claude Code, the output of a failed command can't be replaced. cat .env && cat missing-file exits non-zero and the model reads the .env as is. shim reports it.
Files attached with @ and shell commands are reported, not masked.
Codex and Copilot CLI tool traffic isn't inspected yet. VS Code reports but masks nothing.
Detection is patterns plus checksums. It misses names, postal addresses and passwords with no key name. Treat it as a guard, not a DLP boundary.
No Windows yet. macOS and Linux work.

Why a hook and not an MCP server? An MCP server only sees calls to its own tools. The agent's built-in Read and Bash never pass through it. A hook sits on the client's own tool calls, so it sees those too.

Which of these would stop you from using it? Your answers decide what we fix first.

•

7d ago

AI coding assistants are amazing… until you hit the usage limit😡 what do u do?

One thing nobody really prepares you for when building with AI is how much your workflow depends on usage limits. You re deep into a problem. You ve finally figured out what s wrong. Your AI assistant understands the context, you re making progress, and then You ve reached your usage limit. Come back later. And of course, it never happens when you re casually asking a question. It happens when you re debugging something that has already taken hours. I ve been building my platform using Claude Code and Codex, and I ve learned that managing usage limits is practically another part of the development process. Sometimes I switch between tools. Sometimes I have to stop completely. And sometimes I spend more time planning around the limits than actually fixing the problem. I understand why limits exist. AI models aren t free to run. But when you re using these tools to build a real product, the interruptions can seriously affect your momentum. I m genuinely curious: How do you deal with AI coding assistant usage limits? Do you switch between models, pay for higher plans, plan your sessions around resets, or just accept that your AI developer has decided to take a coffee break?

•

8d ago

Hooks that fixed my agent's most annoying habits. Which one would you set up first?

Quick background if you haven't used them: hooks in Claude Code are your own scripts that run automatically at set points, like right before a command runs or right when the agent finishes its answer. A hook can block that step or send the answer back to be rewritten. CLAUDE.md is something the model reads and can forget after a long session. A hook just runs, every time.

Here are the ones I'd miss most. Each started as a rule in CLAUDE.md that the agent kept breaking.

Replies drift into English after long sessions. A hook checks every answer and sends it back if it isn't in Japanese.

Mertcan Sağlam