Latitude for Claude Code

This is solving a real problem. I run automated agents (social media engagement, security audits, competitor monitoring) and the hardest part isn't building them — it's knowing when they silently fail. I built a custom "doctor" module that diagnoses and self-heals agent errors, but a proper observability layer would have saved me weeks.The "auto-generated evals from production failures" is the killer feature here. How granular is the token cost tracking per agent task?

Does this work for Claude design? 😅

The captures locally framing caught my attention — curious how the telemetry hook actually intercepts Claude Code's runtime. Is it patching the Node.js fetch layer, or hooking at the MCP transport level? Asking because system prompts in Claude Code often contain sensitive workspace context (repo structure, file contents), so understanding the data path before it hits Latitude's servers matters a lot for teams in regulated environments.

- On macOS the installer writes ~/Library/LaunchAgents/so.latitude.claude-code-telemetry.plist which runs launchctl setenv BUN_OPTIONS=--preload=... on every login. That sets BUN_OPTIONS for every Bun process on your machine, not just claude — so any other Bun-based tool you run will also load their preload shim. Wider blast radius than "just Claude Code."^^ Might be worthwhile reeling that in a bit. Every Bun process is a bit overreaching.

Oh man! Needed it. Claude is making me crazy, cause I never know where my tokens go. Thanks for helping on this and wish you all the best here!

Token-burn observability for Claude Code is the kind of thing you only think to build after you blow a session on a regex loop. Curious how you handle the per-tool breakdown when an agent calls bash ten times for the same file read. Is it parsed from stream events or from the response after the fact?

congratulations, how much overhead does telemetry collection add to latency during active sessions?

Does the recurring failure detection use heuristics, or are you applying some ML based pattern analysis?

Does it work for Claude Cowork projects? I mainly burn my limits on Cowork sessions.

this is genuinely what we need, especially being able to spot which sessions burn way more tokens than others lol. Does this support the Claude Team plan, or API-only for now?

Hey everyone,It's Cesar, founder of Latitude.If you keep hitting your Claude Code limits faster than you'd expect, this shows you why. Full session trace: system prompt, every tool call, subagent spawns, per-turn token cost. You see where your context actually went and which actions burn the most.Same thing works if you're using Claude Code as a harness for your own agent: track cost and latency per session, and get recurring failures auto-flagged across runs.Install is one command:npx -y @latitude-data/claude-code-telemetry installIt's free, traces stay in your Latitude account.Happy to answer technical questions in the thread.