Launching today
agentfdr reads the transcripts Claude Code already writes and turns them into a flight recording: per-turn timeline, automatic anomaly flags (loops, error streaks, token burns), live watch mode, plan-usage tracking, and cost estimates. Zero instrumentation, 100% local, MIT.
Hi Product Hunt! 👋
A few weeks ago I left Claude Code running overnight. In the morning: 2M tokens gone, and the "fix" was editing the same file in a loop for 40 minutes. I had no idea *why* — the evidence had scrolled away.
Then I realized: Claude Code already writes a complete transcript of every session to disk. Nobody was reading it.
agentfdr is the crash investigator's toolkit for those recordings:
🛫 A per-turn timeline of every tool call, the context window's composition, and output tokens
🚨 Automatic anomaly flags: tool loops, error streaks, context bloat, cache thrash
🔍 A dissection panel for any turn — what it saw, what it did, what it cost
📊 Plan usage (5-hour window / weekly) with calibratable budgets
🚦 A CI gate: `agentfdr assert --no-loops --max-tokens 2M`
Zero instrumentation — `npx agentfdr` and you're looking at your own sessions. Nothing leaves your machine. MIT licensed.
Zooming out: working with coding agents is quickly becoming loop engineering — you design and operate the loop your harness runs: what enters the context, which tools fire, when it stops. You can't engineer a loop you can't see. agentfdr wants to be the instrument panel for that discipline.
Fun fact: every screenshot in the gallery is agentfdr dissecting *the session in which Claude Code built agentfdr itself* — flags and all. 🛬
I'd love your feedback — especially which agent CLIs to support next (Codex CLI? Gemini CLI? Aider?).
RiteKit Company Logo API
@kamihork Congrats on the launch. "The black box for your coding agent" is a sharp framing — stepping through 372 turns to see exactly where it looped, edited the same file 106 times, or blew 50k characters into one tool result is the visibility anyone running agents in anger has wished for. The anomaly flags doing the triage for you is the part that'll click.
You launched without a demo video, and a tool like this lands so much harder when people can see the timeline in motion — so I made you one, free, fully whitelabeled, no watermarks or strings. Drop it into your gallery now while the launch is fresh:
Built it with FoxPlug — it turns your real product updates into launch videos, posts and GIFs automatically. foxplug.com. Keep shipping.
finally something that surfaces loop patterns in long claude sessions without making me grep through jsonl files, the live watch mode is genuinely useful when a run starts drifting.
@veli342040 Thank you! The grep-through-jsonl phase is exactly where this started — I had a folder full of flight recordings and no way to read them.
Glad live watch is earning its keep. One tip for drifting runs: the anomaly chips update live too, so clicking the newest one jumps you straight to the turn where things went sideways. And if you want a hard stop for unattended runs, agentfdr assert --no-loops --max-tokens 2M exits 1 the moment a session crosses the line — works in a wrapper script or CI.
Curious — which agent CLIs would you want supported next? Adapters (Codex CLI / Gemini CLI / Aider) are the top item on the roadmap.
the "assert --no-loops --max-tokens" gate is the part i'd actually want running unattended, not just the timeline after the fact. question on tuning it though: some loops are legitimate, retrying a failing test until it passes, polling a build, re-reading a file after an edit. how does it tell that apart from a genuinely pathological loop before it kills the run? is the anomaly detection just repetition-count based, or does it look at whether the tool calls are converging toward something (diffs shrinking, errors changing) vs just spinning in place
How does it actually surface the anomaly flags in real time during a session, and is there any way to set custom thresholds for things like token burn before it pings you?
does the anomaly detection work offline too, or does it need to ping anywhere to flag loops and token burns? curious how it stays 100% local with that kind of analysis.
Love that you skipped the SDK and just read what Claude Code already writes to disk, zero instrumentation feels like the right call. The per-turn timeline plus automatic loop and token burn flags is exactly what I'd want when something goes sideways mid-session.
how does it pick up the transcripts — is there a config to point it at a custom claude code logs directory or does it default to ~/.claude?