24,990 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Zero-key Claude Code cost tracking, per project and per branch. Budget caps with SIGTERM enforcement, reads your local /.claude session logs, and syncs to a hosted team dashboard (Goei).
★not rated 8 2d agoA
tokens not measured
originalMIT
USE WHEN you need a structured OLAP slice of a large codebase, log stream (including multi-GB .gz), CSV export, sitemap or HTML crawl, or an SDD artefact catalog — WITHOUT reading raw file bodies into the context window. Single-pass aggregator: streams input, folds records into an in-memory cube by user-picked…
A Model Context Protocol server for generating charts using AntV. This is a TypeScript-based MCP server that provides chart generation capabilities. It allows you to create various types of charts through MCP tools. Runs locally from the @antv/mcp-server-chart npm package.
★not rated 8 1y agoA
tokens not measured
originalMIT
MCP server for FAIM forecasting SDK - Enables Claude to perform time series forecasting using Chronos2 and TiRex models. Runs locally from the @faim-group/mcp npm package.
The Weckr cost and margin toolkit for your AI assistant. Bundles skills that integrate the Weckr SDK, look up current LLM token prices, estimate what an AI feature costs per user before you ship, and audit which of your pricing plans are unprofitable at today's model prices. Covers OpenAI, Anthropic, Gemini, and Kimi.
★not rated 8 18d agoA
tokens not measured
originalMIT
Send push notifications, build audiences, and view campaign analytics from PushEngage. Runs locally from the @pushengage/mcp npm package. Needs 2 environment variables to run.
★not rated 8 3mo agoA
tokens not measured
originalMIT
Automation discovery audit. When the user says "flowhunt setup" walk them through a 5-question workflow intake (role, pain points, failed attempts, sacred areas, goal) and then wire Gmail/Calendar/Slack/task-tracker/optional messaging connectors and optionally install ActivityWatch. When the user says "flowhunt audit"…
Judgment-layer review of Claude Code token usage. Use when the user asks to audit token costs, review Claude Code spending, check context waste, or interpret a tokenscope report. Runs the tokenscope profiler, then interprets its findings with knowledge of the project's actual workflow — separating mechanical waste…
Audit and trace Tableau workbooks (.twbx/.twb) from Claude Code: calculated-field lineage, unused fields, duplicate calcs, performance findings, filters, worksheets, stored SQL, and workbook-to-workbook diffs. Runs 100% locally over stdio; the workbook never leaves your machine.
★not rated 8▲
+1 1mo agoA
tokens not measured
originalMIT
A personalized AI nutrition coach built as a skill. Works for both men and women — with proper sex-based coaching built in, not bolted on. Logs food, tracks macros, learns your patterns, and remembers your data across conversations.
★not rated 8▲
+1 4mo agoA
tokens not measured
originalMIT