How do I install the Basemind Stats skill?

Run npx skillmds@latest add goldziher/basemind-stats in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Basemind Stats safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Basemind Stats?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Basemind Stats free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Basemind Stats?

goldziher (@goldziher) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Basemind Stats by goldziher — Agent Skill

Name: Basemind Stats
Author: goldziher

Basemind Stats

Show a quick dashboard of basemind activity in this session: how many code-map tool calls have run, the per-tool histogram, and the estimated tokens saved vs a hypothetical grep+Read baseline. Use when the user asks "what has basemind done?", "how much is basemind helping?", "show me basemind stats", or invokes `/bm-stats` directly.

goldziher 7d465c4 2.2 KB Updated Sep 17, 2026

File contents

basemind-stats — on-demand usage dashboard

Call admin mode telemetry and render the result as a markdown report.

When to use

The user asks "what has basemind done?", "how much is basemind helping?", "show me basemind stats", or invokes /bm-stats directly. This skill is strictly user-invoked — see Notes.

How to run

Call admin { "mode": "telemetry", "window": "today" } (the default). If the user asks for a specific range, map it to one of "today", "1h", "24h", "all".

Render a markdown block in this shape:

## basemind activity (today)
- **N tool calls** ; top operations: code:outline (18), code:symbols (12), …
- **~K tokens saved** vs grep + Read baseline
- recent: code:outline (4ms, 312B), code:symbols (2ms, 180B), …

If total_calls is 0, say so plainly ("no basemind activity in the window yet"). Don't pretend to have data.
Always disclose the savings model. Add one sentence at the end:

Savings are heuristics. Tools with no realistic baseline (memory, document search, git wrappers) report 0 saved — see the saved_baseline column on each row.

The exact wording can vary; the principle (it's an estimate, here's why) cannot.

When the user asks "--explain"

If they invoke /bm-stats --explain or ask how the savings number is derived, include the per-baseline breakdown from the per_baseline field of the response and call out which tools fall into which bucket. The estimator lives in src/mcp/savings.rs if they want to read the code.

Notes

Don't auto-display the dashboard at the start of every conversation. This skill is strictly user-invoked.
Don't pad missing data. If recent is empty, say so; don't invent example rows.
Don't claim a token-savings number without the disclosure sentence.

---name: basemind-statsdescription: Show a quick dashboard of basemind activity in this session: how many code-map tool calls have run, the per-tool histogram, and the estimated tokens saved vs a hypothetical grep+Read baseline. Use when the user asks "what has basemind done?", "how much is basemind helping?", "show me basemind stats", or invokes `/bm-stats` directly.---# basemind-stats — on-demand usage dashboardCall `admin` mode `telemetry` and render the result as a markdown report.## When to useThe user asks "what has basemind done?", "how much is basemind helping?", "show me basemindstats", or invokes `/bm-stats` directly. This skill is strictly user-invoked — see Notes.## How to run1. Call `admin { "mode": "telemetry", "window": "today" }` (the default). If the user asks for a specific range, map it to one of `"today"`, `"1h"`, `"24h"`, `"all"`.2. Render a markdown block in this shape: ```text ## basemind activity (today) - **N tool calls** ; top operations: code:outline (18), code:symbols (12), … - **~K tokens saved** vs grep + Read baseline - recent: code:outline (4ms, 312B), code:symbols (2ms, 180B), … ```3. If `total_calls` is 0, say so plainly ("no basemind activity in the window yet"). Don't pretend to have data.4. **Always disclose the savings model.** Add one sentence at the end: > Savings are heuristics. Tools with no realistic baseline (memory, document > search, git wrappers) report 0 saved — see the `saved_baseline` column on > each row. The exact wording can vary; the principle (it's an estimate, here's why) cannot.## When the user asks "--explain"If they invoke `/bm-stats --explain` or ask how the savings number isderived, include the per-baseline breakdown from the `per_baseline` field of theresponse and call out which tools fall into which bucket. The estimator lives in`src/mcp/savings.rs` if they want to read the code.## Notes- Don't auto-display the dashboard at the start of every conversation. This skill is strictly user-invoked.- Don't pad missing data. If `recent` is empty, say so; don't invent example rows.- Don't claim a token-savings number without the disclosure sentence.

Frequently asked questions