Bm Stats — Development skill for Claude Code
Show the basemind dashboard — resource footprint (disk + RAM) and activity (tool calls, per-tool histogram, estimated tokens saved).
How to install Bm Stats
Installs to ~/.claude/skills/goldziher-basemind-bm-stats/SKILL.md
mkdir -p ~/.claude/skills/goldziher-basemind-bm-stats && curl -fsSL https://raw.githubusercontent.com/Goldziher/basemind/HEAD/commands/bm-stats.md -o ~/.claude/skills/goldziher-basemind-bm-stats/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Bm Stats does
name: bm-stats description: Show the basemind dashboard — resource footprint (disk + RAM) and activity (tool calls, per-tool histogram, estimated tokens saved). Works with or without the MCP server. argument-hint: [today|1h|24h|all]
bm-stats — basemind dashboard
Show a basemind dashboard with two sections: resource footprint (on-disk size + process RAM) and activity (tool calls, per-tool histogram, estimated tokens saved).
When to use
The user asks "how much is basemind helping?
Alternatives in Development
- Claude Code Hooks Mastery — A resource for mastering Claude Code hooks 3.4k ★
- Add Resource — Renamed → /portaljs-add-resource 2.3k ★
- Zerostack — Lightweight coding agent written in Rust, optimized for memory footprint and performance 1.7k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Offline Telemetry Script
Offline analyzer for Claude Code session transcripts (~/.claude/projects/.jsonl). Pure-stdlib Python, no API c
Claude Secretmode
Leave-no-trace ephemeral Claude Code sessions on macOS — runs Claude Code on a RAM disk so transcripts, prompt
Optimus Stats
Show Optimus token usage, subagent dispatch counts, and estimated savings for this project
Session Verify
Dump every kit-loaded resource — auto-memory dir, MEMORY.md disk-vs-runtime parity, working-folder files, work
Nanopi
Tiny Rust port of Pi — a ~4 MB statically-linked coding agent CLI for old/low-resource Linux boxes. OpenAI + A
Goal Check
Check whether recent tool activity still relates to the stated goal in task_plan.md, reporting a drift score a
Related Agents
Stats Analyzer
Analyzes ~/.claude/stats-cache.json and history.jsonl to produce a concise usage report with model token break
Orquestrador
Watches the machine's resources (RAM, CPU, disk, processes, ports). Invoke before starting a heavy build/dev s
Usage Reporter
Reads real Claude Code usage from ~/.claude/stats-cache.json. Reports daily/weekly token usage by model, cache