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)
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
Claude Code is not developer friendly.
Why Anthropic can't provide such a setting, we will never know!
"spinnerVerbs": {
"mode": "replace",
"verbs": ["Working"]
}
They bothered to let you override default nonsense messages with custom messages, but they still don't want to let you see what you are actually interested in. The actual information is kept hidden.
Luckily, new open weight models from China caught up with Anthropic, so you can use a sane harness with a much cheaper subscription and never look back.
But regarding khoury's original point about the actual "gas in the tank" (billing/account balance)—no, my tool doesn't show that either.
Since `claude-devtools` strictly parses your local `~/.claude/` logs and makes zero network calls, it doesn't have access to your Anthropic account to pull your actual dollar balance.
What it does provide is high-resolution context usage. Instead of just a total session count, it breaks down tokens per-turn (e.g., how many tokens were eaten by reading a specific file vs. the tool output). It helps you manage your context window locally, but for billing, you're unfortunately still stuck checking the web dashboard.
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!
Thanks for giving it a spin tonight! Let me know if you run into any issues.
"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...
1. Cross-platform distribution: Shipping an Electron app across macOS (ARM/Intel), Linux (AppImage/deb/rpm), Windows, and maintaining a standalone Docker/Node server just requires a lot of platform-specific build configs and overrides (especially for electron-builder).
2. Agentic coding guardrails: As I built most of this project using Claude Code itself, I wanted strict boundaries when it writes code
The ESLint, Prettier, strict TS, Knip (dead code detection), and Vitest configs act as quality gates. They are what keep the AI's output from drifting into unmaintainable spaghetti code. Without those strict constraints, agentic coding falls apart fast.
I'd rather have 20 config files enforcing quality than a clean root directory with an AI running wild. That said, I totally take your point—I should probably consolidate some of these into package.json to clean things up.
Which ones, ESLint and Prettier and so on? Those are just for "nice syntax", and doesn't actually help your agent with what they actually fall over themselves with, which is about the design of your software, not what specific syntax they use.
The goal is to prevent the agent from getting derailed by basic noise. Forcing it to deal with strict TS errors, dead code (Knip), or broken formatting in the feedback loop keeps the context clean.
It’s less about architecting the app and more about giving the agent immediate stderr signals so it stays on the rails.
That's not what I was getting at either, but the design is pervasive in your program, not just something that sits as a document on top, but codified in the actual program.
> The goal is to prevent the agent from getting derailed by basic noise
Ah, I see. Personally I haven't seen agents getting slower and less precise of that, but I guess if that's the issue you're seeing, then it makes sense to try to address that.
Out of curiosity, what model/tooling are you using, only Claude Code? I've mostly been using Codex as of late, and it tends to deal with those things pretty easily, while none of the agents seems to be able to survive longer on their own without adding up too much technical debt too quickly. But maybe that's at another lifecycle than where you are getting stuck currently.
But it turns out Claude Code's official VS Code extension is built to read these exact same local `.jsonl` files. So unless Anthropic decides to intentionally break their own first-party extension, it should remain relatively stable.
Of course, they will add new payload types (like the recent "Teams" update), but when that happens, it's pretty trivial to just add a new parser handler for it—which I've already been doing as they update the CLI.
So far, it's been surprisingly easy to maintain!
I have a similar project that started out as just a log viewer but is now a full session manager etc (https://github.com/kzahel/yepanywhere). My approach was to occasionally run zod schema validations against all my local sessions to make sure the frontend has a pretty faithful schema. I've noticed sometimes when I run claude cli it modifies some jsonl files, it might be doing some kind of cleanup or migration, I haven't looked too deeply into it (yepanywhere detects when files change so I see those sessions as "unread, externally tracked")
Also, this isn't a wrapper—it’s a passive viewer. I built it specifically to keep the native terminal workflow intact.
It’s especially useful when you're running multiple parallel sessions. Have you ever tried digging through raw JSON logs to retroactively debug passed sessions at once, since the session is already shut down? It’s nearly impossible without a proper UI. This tool is for those "post-mortem" moments, not just for watching a single stream.
It's more like standard observability. You don't watch your server logs all day, but when an error spikes, you need deep tracing to find out why.
I use this when the agent gets stuck on a simple task or the context window fills up way faster than expected. The tool lets me "drill down" into the tool outputs and execution tree to see exactly where the bad loop started.
If you're running multiple parallel sessions across different terminal tabs, trying to grep through raw logs to find a specific failure is a massive productivity sink. This is for when things go sideways and you need to solve it in seconds, not for babysitting every keystroke.