alt Hacker NewsShow HN: I built a tool to un-dumb Claude Code's CLI output (Local Log Viewer)
Hi HN,
I built this because I got tired of the Claude Code CLI hiding details from me.
Recent updates have replaced critical output with summaries like "Read 3 files" or "Edited 2 files". To see what actually happened, I was forced to use `--verbose`, which floods the terminal with unreadable JSON and system prompts.
I wanted a middle ground: *Full observability without the noise.*
`claude-devtools` is a local Electron app that tails the session logs in `~/.claude/` to reconstruct the execution trace in real-time.
*Unlike wrappers, it solves the visibility gap in your native terminal workflow:* 1. *Real Diffs:* It shows inline diffs (red/green) the moment files are edited, instead of just a checkmark. 2. *Context Forensics:* It breaks down token usage by File vs Tool Output vs Thinking (so you know exactly why your context window is full). 3. *Agent Trees:* It visualizes sub-agent execution paths which are usually interleaved and confusing in the CLI.
It’s 100% local, and works with the logs already on your machine. No API keys required.
Repo: https://github.com/matt1398/claude-devtools (Screenshots and diff viewer demo are in the README)
Comments
You're on the path. Keep going.
All these coding agents should support custom otel endpoints with full instrumentation (http, mcp, file system access, etc).
Does it also show usage? I think it's pretty ridiculous we have to install 3rd party packages/implement it ourselfs just to see how much gas is left in the tank basically. Or constantly check the usage tab on the web, but still.
You could also use braintrust here https://github.com/braintrustdata/braintrust-claude-plugin
Oh, wow. I was debugging the same in copilot (the only "work approved" agent) in Intellij, which showed that copilot didn't return commands output at all. I wrote a comment under relevant issue, if you're curious.
I think there are quite a few bugs lingering in those agent-cli's and observability, would help a lot with reporting. Taking yours for a spin this evening, thank you!
there was also this last year not updated in a while but the view handling is better than native verbose :
"claude-trace" Record all your interactions with Claude Code as you develop your projects. See everything Claude hides: system prompts, tool outputs, and raw API data in an intuitive web interface.
https://github.com/badlogic/lemmy/tree/main/apps/claude-trac...
I checked the repository and it has >20 config files, just for a simple tool, something is terribly in todays development
Won't this break every time the log format changes?
For those who don't want to install yet another wrapper, you can just use the `--verbose` flag: https://code.claude.com/docs/en/cli-reference#cli-flags
the emdashes lmfao
If it hasn't been said before, Anthropic should hire this person.
Cant you just look at the diffs? Not sure the point of using Claude and having to babysit every change it makes, kind of defeats the purpose. Like would you sit watching a Junior devs every keystroke.
Why not just use something sane by default? It's not like there are not better alternatives to Claude Code.
Opencode is great as a full replacement. Works out of the box.
Pi code agent[1] is even better, if you spend some time in it, you can customize is to your liking. It's a vi and Emacs combined for agents.
[1] https://pi.dev