claude-lean vs AI Usage
claude-lean is a plugin bundle for AI coding tools published by taejunoh. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). AI Usage is an MCP server published by MohitBansal321. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-23. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  AI Usage | |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: d743ad3 No figure published Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.16.1 Downloads/month (npm): 2 263 Downloads/week (npm): 435 Forks (GitHub): 0 Stars (GitHub): 1 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | claude-lean | AI Usage |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | No figure on GitHub | 1 |
| Forks (GitHub) (differs) | No figure on GitHub | 0 |
| Last release (differs) | Not published | 2026-10-23 |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (ai-usage-mcp) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Licence (differs) | Not stated | MIT |
| Repository (differs) | github.com/taejunoh/claude-lean | github.com/mohitbansal321/ai-usage-mcp |
| Changes in the last 7 days (differs) | 0 | 3 |
| First seen | 2026-10-11 | 2026-10-11 |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
claude-lean
Automatic token measurement, cost analysis, and CLAUDE.md optimization for Claude Code sessions. Uses tiktoken (cl100k_base) for accurate token counting, detects bloated config files on session start via hooks, and proactively optimizes to reduce costs. Includes before/after benchmarking with per-model cost comparison.
AI Usage
Reports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
How to run each
claude-lean As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install claude-lean@claude-communityAI Usage As a local MCP server: npm package
claude mcp add --transport stdio ai-usage-mcp -- npx -y ai-usage-mcpCommands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: claude-lean · What it can do: AI Usage · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.