Skip to main content
Glama

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

Command

What it does

tare

Wrapped for the last 30 days. --days N, --all, --json, --logs <dir>

tare card

A 1200×630 shareable card (SVG, with a PNG download) and post text. Nothing is uploaded

tare fix

Installs the output trim and the cache status line. --dry-run, --undo, --scope project

tare receipt

Cost per commit before and after tare fix, with a 90% range and a finish-rate check

tare status

What is installed, and how much output the trim has cut so far

tare setup

Adds Tare to every AI coding app on this machine. --dry-run, --undo

tare mcp

MCP server over stdio: tare_wrapped, tare_receipt, tare_cache

Related MCP server: contextburn

How the numbers work

  • API-equivalent. Every call is priced at Anthropic's API list prices: fresh input, cache writes (1.25× input for the 5-minute cache, 2× for the 1-hour cache), cache reads and output. On a subscription you pay a flat fee; this is what the same work would cost on the API.

  • Carry cost. A tool's output is written to the cache once and read back on every later call until the conversation is compacted. Tare charges each output for the whole time it stays in context.

  • Cache rebuilds. When most of a prompt is written to the cache again instead of read from it, Tare says why: an idle pause past the cache's lifetime, a model switch, a compaction, or a break.

  • Repeats. A tool call that returned byte-for-byte what the agent already had.

The fixes

Tare cuts waste where it enters the context and never rewrites what's already there, because a rewritten history breaks the prompt cache and costs more than it saves.

  • Output trim (a PostToolUse hook on Bash): output over ~2,500 tokens is cut to the first 40 lines, every line that looks like a failure (with context) and the last 60 lines. The full output is saved in ~/.tare/out/ and the agent is told where.

  • Cache countdown (the status line): how long until the cache goes cold, and what the next message costs warm versus cold. Installed only if you don't already have a status line.

Settings are backed up to ~/.tare/backups/ first, and tare fix --undo removes only Tare's entries.

The receipt

tare receipt compares cost per commit in sessions before and after the fixes, with a bootstrap 90% interval, and checks that as many sessions still reach a commit. With fewer than 8 finished sessions on either side it prints "not enough data" and no number.

In your agent

One command adds Tare to every AI coding app it finds: Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Codex, Gemini CLI, Kiro, opencode, Amazon Q, LM Studio, and Cline, Roo Code and Kilo Code. The entry is pinned to the exact version, each file is backed up first, and --undo removes it.

npx tarelab setup

Or one app at a time:

  • Claude Code plugin: /plugin marketplace add priberry-data/tarelab, then /plugin install tare@priberry.

  • Gemini CLI extension: gemini extensions install https://github.com/priberry-data/tarelab

  • Skill (Claude Code or Codex): copy skills/tare into ~/.claude/skills/ or ~/.codex/skills/.

  • Any MCP client: {"command": "npx", "args": ["-y", "tarelab@0.2.0", "mcp"]}. Then ask "what did my agent cost this month?"

Limits

Tare reads the logs that agents keep on your machine. Cursor's own agent, Windsurf's Cascade, Copilot and the browser app builders (Lovable, Bolt, v0, Replit) keep usage on their servers, so Tare can't see them yet; opencode is next. Cline-family costs are the ones the extension itself recorded. The fix and receipt commands work on Claude Code, where the hooks exist. Token counts for tool output are estimated from text length (the API reports totals per call, not per block). Prices are as of 2026-10-06 for Anthropic and 2026-11-08 for OpenAI and Google, and live in src/prices.mjs.

Apache-2.0 · Built by Priberry, who also make Crumple (crash-test your coding agent) and Greenlit (is your AI-built app safe to launch?).

Available Tools

3 tools
tare_cache
Read-only

For one session transcript: context size, whether the prompt cache is still warm, and what the next message will cost warm versus cold.

Inputs: transcript_path (required).

tare_receipt
Read-only

Cost per commit before and after Tare's fixes were installed, with a 90% range, or a plain 'not enough data yet'.

Inputs: no named parameters.

tare_wrapped
Read-only

Where this machine's coding-agent tokens and money went (Claude Code, Codex CLI, Gemini CLI, Cline, Roo Code, Kilo Code): API-equivalent spend, plan-limit use, what filled the context, cache rebuilds, highlights and the top fixes with estimated savings. Local and free.

Inputs: days.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Analyzes Claude Code session token usage and cost locally — where spend actually lands across cache-read, cache-write and output, and what is consuming the context window. Read-only and offline: it parses your own session files and exposes analyze_claude_cost, get_cost_benchmark and tokenscope_share_summary.
      44 npm
      4
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Lets a coding agent inspect its own run efficiency mid-session from local Claude Code transcripts, exposing the share of paid tokens that became model output versus context re-reading. Ships two stdio tools — one returning the shares as structured data and one returning the full cost-weighted report — with no network calls.
      2
      26 PyPI
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Reads the Claude Code, Codex and OpenCode usage logs already on your machine and reports token totals, per-day and per-hour activity, a per-agent and per-model breakdown, and a year-in-review recap. It makes no network request at all — a test fails if any source file in the package can open a socket.
      4
      14
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Analyzes local Claude Code logs to measure subscription value, waste, and rate-limit usage, including chat share and current limits, without uploading data.
      4
      MIT