dashboard · localixai — Claude Code skill: what it does, how to install
dashboard is a Claude Code skill that builds a local token usage dashboard from transcripts on your machine. It opens a standalone HTML report in your browser.
MIT ★ 171 updated 2026-11-17
/plugin marketplace add localixai/tokendoctor
/plugin install tokendoctor@tokendoctorWhat dashboard does
The skill runs tokendoctor-dashboard --open, passing --days if an argument was provided. It inspects usage numbers across stored transcripts without reading message bodies, creating an HTML report.
The output reveals top token consumers, subagent consumption shares, and the costliest model or effort level. Because the report includes project directories and session identifiers, the generated HTML stays strictly local.
Running this skill requires the tokendoctor-dashboard executable in your shell. Model invocation is turned off via disable-model-invocation: true.
What it helps with
- inspect local token consumption across sessions
- measure the token share taken by subagents
- identify the costliest model and effort level
- view session metrics without exposing transcript text
Example prompts for the agent
- Build a token dashboard for the last 14 days
- Open the token usage dashboard
- Show token metrics for the past 3 days
How to install dashboard
1Plugin marketplace
/plugin marketplace add localixai/tokendoctor/plugin install tokendoctor@tokendoctorThis installs the whole tokendoctor plugin with all its skills
2Skills CLI (Vercel)
npx skills add localixai/tokendoctor --skill dashboard -a claude-code3Manually: put the files in place
~/.claude/skills/dashboard/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/dashboard/
1Skills CLI (Vercel)
npx skills add localixai/tokendoctor --skill dashboard -a codex2Manually: put the files in place
.agents/skills/dashboard/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add localixai/tokendoctor --skill dashboard -a cursor2Manually: put the files in place
.cursor/skills/dashboard/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install localixai/tokendoctor skills/dashboard2Manually: put the files in place
.github/skills/dashboard/SKILL.md1Skills CLI (Vercel)
npx skills add localixai/tokendoctor --skill dashboard -a gemini-cli2Platform CLI
gemini skills install https://github.com/localixai/tokendoctor --path skills/dashboardManually: put the files in place
.devin/skills/dashboard/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about dashboard
How to install dashboard in Claude Code?
Run /plugin marketplace add localixai/tokendoctor followed by /plugin install tokendoctor@tokendoctor.
What does the dashboard skill do?
It parses usage metrics from local transcripts and displays a self-contained HTML summary of token distribution in your web browser.
What is required to run the dashboard skill?
You need the tokendoctor-dashboard command available in your Bash environment.
Source text
SKILL.md · MIT
--- name: dashboard description: Build and open a local dashboard of where your Claude Code tokens went, from every transcript on this machine. disable-model-invocation: true allowed-tools: Bash(tokendoctor-dashboard *) argument-hint: [days] --- Run `tokendoctor-dashboard --open` (add `--days $ARGUMENTS` when a number was given). It reads the usage figures in this machine's transcripts (never message text), writes one self-contained HTML file and opens it in the browser. Give the path it prints, and in two or three lines say what stands out: the headline share, the share that went to subagents, and the model and effort that took the most. The file holds project names and session ids, so it stays on this machine.
© rsaryev · MIT · localixai/tokendoctor
Similar skills
All skills for Agent setup: memory, context, orchestration →dashboard by other authors comes first.