Tare
priberry-data/tarelab
See where your coding agent's tokens and money went, with cache-safe fixes. Local.
- GitHub stars
- 1
- tools
- 3
- transport
- STDIO
- last updated
- Nov 8, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
tare_wrappedShows the same wrapped summary as the `tare` command over MCP.
Shows the same wrapped summary as the `tare` command over MCP.
No parameter schema in public metadata yet.
tare_receiptReturns the cost-per-commit receipt comparison over MCP.
Returns the cost-per-commit receipt comparison over MCP.
No parameter schema in public metadata yet.
tare_cacheReturns cache status information over MCP.
Returns cache status information over MCP.
No parameter schema in public metadata yet.
Sponsors
Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthly
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any language
Agent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any languageReadme
tare
Same work, fewer tokens, with the receipt.
Your coding agent keeps a log of every API call it makes. Tare reads those logs, prices every token, and shows where the money went: Claude Code, Codex CLI, Gemini CLI, and Cline, Roo Code and Kilo Code in VS Code, Cursor, Windsurf and the other VS Code-based editors. For Codex on a ChatGPT plan it also shows how close you came to the plan's usage limits. Then it cuts the waste without breaking the prompt cache, and proves each saving on your own work. It runs locally, uploads nothing and never calls a model.
npx tarelab
YOUR AGENT, WRAPPED · last 30 days · 254 sessions · 79,905 API calls
$6,720 API-equivalent spend
$623 of it was avoidable (9%)
Where it went
Reading cached context ██████████████████████ $3,809
Writing to the cache ████████████ $2,072
Output (thinking incl.) █████ $838
The highlights
› ~82k tokens load before you type a word.
› Coffee-break tax: $722 re-caching after 636 pauses.
› Sub-agents spent $2,734 (41%).
A real month of Priberry's own Claude Code use.
Commands
Details
- Repository
- github.com/priberry-data/tarelab
- Website
- tare.priberry.com
- Categories
- AI & LLM Tools, Data & Analytics
- Package
tarelab- Transport
- STDIO
- Registry
- MCP registry, active
