Greynewell Tokentrace
- 6 repo stars
- Updated February 17, 2026
- greynewell/tokentrace
greynewell-tokentrace is a Claude Code plugin that traces token usage with spans, latency percentiles, and alerts.
About
greynewell-tokentrace is a Claude Code plugin marketplace entry that helps developers answer a blunt question: where did your tokens go? Instead of guessing from bill shock, you get span-oriented tracing, latency percentiles, and alerts suited to agent sessions that fan out across tools and sub-calls. Developers running Claude Code daily benefit when a feature ship suddenly doubles spend or when responses lag without an obvious bottleneck. The plugin sits primarily in Operate monitoring, but the same metrics support Ship performance tuning and Grow analytics when you correlate usage with experiments. It is an observability integration—not a code generator—so expect to install it once agents are in real use, wire alerts you will act on, and review traces after heavy debugging or automation recipes. Community metadata points at enrichment and recipe-oriented tooling; treat it as operational instrumentation layered on top of your existing skills rather than a replacement for tests or security review.
- Answers where did your tokens go with trace-style visibility into agent runs
- Latency percentiles for spotting slow tool or model paths
- Alerting hooks when usage or performance crosses thresholds
- Chef/recipe-style tooling keywords suggest composable observability recipes for Claude workflows
- Single-plugin bundle focused on cost and performance forensics
Greynewell Tokentrace by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin install greynewell-tokentrace@greynewell/tokentraceAdd your badge
Show developers this plugin is listed on Skillselion. Paste this into your README.
| repo stars | ★ 6 |
|---|---|
| Last updated | February 17, 2026 |
| Repository | greynewell/tokentrace ↗ |
What it does
Install when agent sessions burn tokens or feel slow and you need spans, latency percentiles, and alerts to see where usage actually goes.
Who is it for?
Best when you're running frequent Claude Code automation and need production-minded visibility into token spend and latency—not just monthly invoices.
Skip if: Early Validate prototypes with almost no agent traffic, or teams unwilling to tune alerts and review trace output.
What you get
After install, you can inspect traces and percentiles and get alerts so you trim wasteful agent paths and fix latency hotspots.
- Span-level visibility into token-heavy agent steps
- Latency percentile views for bottlenecks
- Alert signals when usage or performance drifts
Recommended Plugins
Ahmedasmar Devops Claude SkillsA Claude Code Skills Marketplace for DevOps workflows189
Akin Ozer Cc Devops SkillsA practical skill pack for DevOps work in Claude Code and Codex.281
Antonbabenko Terraform SkillThe Claude Agent Skill for Terraform and OpenTofu - testing, modules, CI/CD, and production patterns2.2k
Aws Samples Aws Emr Utilities1 plugin45
Awudevelop Claude PluginsProduction-ready Claude Code plugins for workflow automation and productivity
Axiomhq CliThe power of Axiom on the command line.59How it compares
Token and latency observability plugin, not an LLM integration for product features.
FAQ
Who is Greynewell Tokentrace for?
It is for Claude Code users—especially developers—who run agents often and need to understand token consumption and latency at span level.
When should I use Greynewell Tokentrace?
Use it in Operate when costs climb or sessions slow down, and during Ship perf work when you want percentile-based latency evidence before scaling usage.
How do I add greynewell/tokentrace to my agent?
Install the greynewell/tokentrace plugin from its marketplace repo in Claude Code, configure tracing and alerts per the project docs, then run agent tasks you want measured.