Every repository, priced
Spend rolls up per repository, so you know which project is expensive before the invoice lands.
- hashtrack-cloud
- api-gateway
- sync-worker
- docs-site
See every token, by user
Hashtrack breaks token usage down per person, so you know who is using their budget.
AL
Alice BO
Bob CA
Carol DA
DaveWhich models are doing the work
Every token is attributed to the model that spent it, so you can see which models perform best.
What your team leans on
Skills ranked by how often your team runs them, across every harness.
Any agent, one source of truth
Hashtrack pulls token and cost data out of every harness your team runs.
What each repository costs
Every dollar is attributed to the repo that spent it, so each project carries its own budget line.
Works with the agents you already use
Hashtrack logs tokens and cost for every turn, whichever harness you run.
Claude Code soon
GitHub Copilot soon
Codex soon
%20{%20:root%20{%20filter:%20none;%20}%20}%20@media%20(prefers-color-scheme:%20dark)%20{%20:root%20{%20filter:%20none;%20}%20}%20%3c/style%3e%3c/svg%3e)
OpenCode soon
pi - Claude Code soon
- GitHub Copilot soon
- Codex soon
- OpenCode soon
- pi
- Claude Code soon
- GitHub Copilot soon
- Codex soon
- OpenCode soon
- pi
- Claude Code soon
- GitHub Copilot soon
- Codex soon
- OpenCode soon
- pi
- Claude Code soon
- GitHub Copilot soon
- Codex soon
- OpenCode soon
- pi
- Claude Code soon
- GitHub Copilot soon
- Codex soon
- OpenCode soon
- pi
- Claude Code soon
- GitHub Copilot soon
- Codex soon
- OpenCode soon
- pi
- Claude Code soon
- GitHub Copilot soon
- Codex soon
- OpenCode soon
- pi
- Claude Code soon
- GitHub Copilot soon
- Codex soon
- OpenCode soon
- pi
- Claude Code soon
- GitHub Copilot soon
- Codex soon
- OpenCode soon
- pi
- Claude Code soon
- GitHub Copilot soon
- Codex soon
- OpenCode soon
- pi
- Claude Code soon
- GitHub Copilot soon
- Codex soon
- OpenCode soon
- pi
What Hashtrack puts on the record
Repository spend, model costs, skill usage, and harness adoption — one ledger for the whole team.
What each model costs
Model-level spend shows where optimisation pays off.
- Opus 5.5 $1,684
- Sonnet 5.5 $962
- GPT 5.3 Codex $431
- DeepSeek v4.1 Flash $118
The skills your team runs
Ranked by runs, across every harness.
- ponytail 1.3K
- svelte-code-writer 962
- plannotator 611
- supabase 384
Which harnesses are in use
Sessions per agent, so you know which tools your team actually runs.