How do I install the Openclaw Usage Dashboard skill?

Run npx skillmds@latest add dvcrn/openclaw-usage-dashboard 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 Openclaw Usage Dashboard safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Openclaw Usage Dashboard?

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 Openclaw Usage Dashboard free to use?

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

Who published Openclaw Usage Dashboard?

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

Openclaw Usage Dashboard by dvcrn — Agent Skill

Name: Openclaw Usage Dashboard
Rating: 4.2 (5 reviews)
Author: dvcrn

Openclaw Usage Dashboard

Generate an interactive local HTML dashboard showing OpenClaw API usage, costs, and rate-limit quotas across multiple LLM providers (Anthropic, OpenAI, Google, Moonshot, Mistral, Cohere, Groq). Reads session transcripts directly — no external service needed. Use when a user asks about API costs, token usage, model spend, quota/rate limits, usage by model or time period, or wants a cost overview dashboard. Triggers on "usage dashboard", "API kosten", "wie viel kostet", "kontingent", "rate limit", "token verbrauch", "cost dashboard", "openclaw costs", "spending overview".

dvcrn Updated Sep 8, 2026 32 repo stars

File contents

OpenClaw Usage Dashboard

Generate a self-contained HTML dashboard from OpenClaw session transcripts. Zero dependencies — Python 3.8+ stdlib only.

Usage

# Real data (reads ~/.openclaw/agents/main/sessions/)
python3 scripts/usage-dashboard-generic.py [output.html]

# Demo mode (generates 30 days of realistic mock data)
python3 scripts/usage-dashboard-generic.py [output.html] --demo

Default output: ~/openclaw-usage-dashboard.html

Override sessions path: set OPENCLAW_ROOT env var.

What It Shows

Cost KPIs: Total spend, today's cost, API calls, active model, cache hit rate, monthly projection
Model config: Active / default / fallback models from openclaw.json
Anthropic quota gauges: 5h and 7d rate limit utilization (requires ANTHROPIC_API_KEY)
Donut chart: Cost distribution by model
Hourly sparkline: Today's call volume by hour
Stacked bars: Cost by period (daily / weekly / monthly / yearly)
Model table: Per-model breakdown with token counts and cost
Detail table + chart: Toggle between table and bar chart view per period
Budget tracker: Set monthly limit, progress bar, localStorage persistence
CSV export: Download any period view as CSV
Provider dropdown: Filter by provider

Supported Providers

Anthropic, OpenAI, Google, Moonshot/Kimi, Mistral, Cohere, Groq — 30+ models with built-in pricing.

Customization

Add models

Edit PRICES dict in the script (price per 1M tokens):

"provider/model-name": {"input": 2.50, "output": 10.00, "cache_read": 1.25, "cache_write": 2.50}

Add to MODEL_COLORS and ALIAS_MAP as needed.

Pricing reference

See references/prices.md for current prices across all providers.

Requirements

Python 3.8+ (stdlib only)
ANTHROPIC_API_KEY in env (optional, for live quota gauges)

---name: openclaw-usage-dashboarddescription: Generate an interactive local HTML dashboard showing OpenClaw API usage, costs, and rate-limit quotas across multiple LLM providers (Anthropic, OpenAI, Google, Moonshot, Mistral, Cohere, Groq). Reads session transcripts directly — no external service needed. Use when a user asks about API costs, token usage, model spend, quota/rate limits, usage by model or time period, or wants a cost overview dashboard. Triggers on "usage dashboard", "API kosten", "wie viel kostet", "kontingent", "rate limit", "token verbrauch", "cost dashboard", "openclaw costs", "spending overview".---# OpenClaw Usage DashboardGenerate a self-contained HTML dashboard from OpenClaw session transcripts. Zero dependencies — Python 3.8+ stdlib only.## Usage```bash# Real data (reads ~/.openclaw/agents/main/sessions/)python3 scripts/usage-dashboard-generic.py [output.html]# Demo mode (generates 30 days of realistic mock data)python3 scripts/usage-dashboard-generic.py [output.html] --demo```Default output: `~/openclaw-usage-dashboard.html`Override sessions path: set `OPENCLAW_ROOT` env var.## What It Shows- **Cost KPIs**: Total spend, today's cost, API calls, active model, cache hit rate, monthly projection- **Model config**: Active / default / fallback models from `openclaw.json`- **Anthropic quota gauges**: 5h and 7d rate limit utilization (requires `ANTHROPIC_API_KEY`)- **Donut chart**: Cost distribution by model- **Hourly sparkline**: Today's call volume by hour- **Stacked bars**: Cost by period (daily / weekly / monthly / yearly)- **Model table**: Per-model breakdown with token counts and cost- **Detail table + chart**: Toggle between table and bar chart view per period- **Budget tracker**: Set monthly limit, progress bar, localStorage persistence- **CSV export**: Download any period view as CSV- **Provider dropdown**: Filter by provider## Supported ProvidersAnthropic, OpenAI, Google, Moonshot/Kimi, Mistral, Cohere, Groq — 30+ models with built-in pricing.## Customization### Add modelsEdit `PRICES` dict in the script (price per 1M tokens):```python"provider/model-name": {"input": 2.50, "output": 10.00, "cache_read": 1.25, "cache_write": 2.50}```Add to `MODEL_COLORS` and `ALIAS_MAP` as needed.### Pricing referenceSee `references/prices.md` for current prices across all providers.## Requirements- Python 3.8+ (stdlib only)- `ANTHROPIC_API_KEY` in env (optional, for live quota gauges)

Frequently asked questions