Claude MarketplacesSubmit
priberry-data avatar

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
View on GitHub

Tools

3 tools

Public 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 monthlyAgent 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 language

Readme

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

View the full README on GitHub

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

More from priberry-data

Related AI & LLM Tools MCP servers

View all
1r09722akabennett avatarNanoPDFr09722akabennett/nano-pdf-mcpAI-powered PDF editing and generation MCP server using Gemini Pro.1stars
2rishav0123 avatarSentimatixrishav0123/sentimatixReal-time NSE/BSE stock sentiment, news NLP, technical analysis & RAG search via MCP.1stars
3rumblingb avatarAgentPayrumblingb/agentpayAgent payments, API key vaulting, and governed mandates. Agents spend within user-defined limits.1stars
4rumblingb avatarAgentpay Sentinel Mcprumblingb/agentpay-sentinel-mcpSecurity guardrails for AI agent payments1stars
5sunflash12 avatarForge Cascade MCP Memory Serversunflash12/forge-cascade-mcpAI memory buyer routing with Forge docs, pricing, paid recommendations, and MCP discovery.1stars
6the402ai avatarMcp Serverthe402ai/mcp-serverAI agent service marketplace — browse, purchase, and manage services via x402/USDC0stars