Tare

io.github.priberry-dataPublished by GitHub account priberry-datav0.2.0Updated Nov 8, 2026

See where your coding agent's tokens and money went, with cache-safe fixes. Local.

VerifiedSTDIODesktop onlyDeveloper ToolsData & AnalyticsAI & ML

Overview

AI-generated overview

Reads local coding-agent logs to show where tokens and money went, plus cost per commit and prompt-cache status.

What you can do
  • Summarize a machine's coding-agent spend: API-equivalent cost, plan-limit use, context fillers, cache rebuilds and suggested fixes
  • Report cost per commit before and after fixes, with a 90% range or a not-enough-data message
  • Inspect one session transcript for context size, cache warmth and warm-versus-cold cost of the next message
  • All three tools run locally and price usage from logs the agents keep on the machine
When to use it
Useful when you want to understand or reduce what Claude Code, Codex CLI, Gemini CLI, Cline, Roo Code or Kilo Code costs on your machine, or to check whether a prompt cache is still warm before sending another message.
Requirements
Runs as a local stdio process via npx (Node.js). No accounts, API keys, environment variables or headers are declared. It reads agent logs already stored on the local machine; desktop only.
Before you install
It reads local agent logs and session transcripts, which can contain prompts, code and tool output; the README says nothing is uploaded and no model is called. The MCP tools are read-only, but the separate CLI commands can change agent settings (hooks, status line) and write backups under the home directory.

Installation

In SourceWeft

  1. Open Tare in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

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

CommandWhat it does
tareWrapped for the last 30 days. --days N, --all, --json, --logs <dir>
tare cardA 1200×630 shareable card (SVG, with a PNG download) and post text. Nothing is uploaded
tare fixInstalls the output trim and the cache status line. --dry-run, --undo, --scope project
tare receiptCost per commit before and after tare fix, with a 90% range and a finish-rate check
tare statusWhat is installed, and how much output the trim has cut so far
tare setupAdds Tare to every AI coding app on this machine. --dry-run, --undo
tare mcpMCP server over stdio: tare_wrapped, tare_receipt, tare_cache

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", "[email protected]", "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.

Source: README.md at commit ebdc3b6

Tools

3

tare_wrapped

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.

Parametersdays

tare_receipt

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

Takes no parameters.

tare_cache

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

Parameterstranscript_pathrequired

Version history

1
  1. v0.2.0LatestNov 8, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts