quick-stats · hoangsonww — Claude Code skill: metrics and setup
Get a compact Agent Monitor snapshot covering agent sessions, spending, daily events, and tool usage. Check the latest activity from your terminal.
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill quick-stats -a claude-codeWhat quick-stats does
The quick-stats skill condenses Agent Monitor data into a short terminal summary. Its default view reports the session count, active sessions, accumulated cost, events recorded today, and the most-used tool. It also identifies the model associated with the latest session.
The skill reads statistics, pricing, and analytics from Agent Monitor API endpoints, then checks the newest session for its model and status. Pass cost to focus on spending, sessions to inspect session statuses, or tokens to review input, output, and cache totals. With no argument, it displays the general snapshot.
The output is designed to fit a terminal workflow rather than a detailed analytics report. quick-stats supports Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. Its figures rely on Agent Monitor API data, so the service must be available for the summary to reflect current metrics.
What it helps with
- Check how many agent sessions are currently active
- Review accumulated spending and model-level costs
- Count events recorded during the current day
- Find the most frequently used tool
- Summarize input, output, and cached tokens
Example prompts for the agent
- Show me a compact summary of Agent Monitor.
- Use quick-stats with the
costargument to report spending only. - Run quick-stats with the
tokensargument to summarize token usage.
How to install quick-stats
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill quick-stats -a claude-code2Manually: put the files in place
~/.claude/skills/quick-stats/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/quick-stats/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill quick-stats -a codex2Manually: put the files in place
.agents/skills/quick-stats/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill quick-stats -a cursor2Manually: put the files in place
.cursor/skills/quick-stats/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install hoangsonww/Claude-Code-Agent-Monitor quick-stats2Manually: put the files in place
.github/skills/quick-stats/SKILL.md1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill quick-stats -a gemini-cli2Platform CLI
gemini skills install https://github.com/hoangsonww/Claude-Code-Agent-Monitor --path plugins/ccam-dashboard/skills/quick-statsManually: put the files in place
.devin/skills/quick-stats/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill quick-stats -a opencodeClaude.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 quick-stats
How do I install quick-stats in Claude Code?
Run npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill quick-stats -a claude-code. The installed skill file is at ~/.claude/skills/quick-stats/SKILL.md.
What does quick-stats do?
It condenses Agent Monitor session, cost, event, and tool-usage metrics into a terminal-friendly summary. Separate modes let you focus on spending, session statuses, or token totals.
How can I view only costs or token usage?
Pass cost to get the spending breakdown and related cost metrics. Use tokens for input, output, cache-read, and cache-write totals; sessions switches to session counts and statuses.
Source text
SKILL.md · MIT
---
name: quick-stats
description: >
One-line summary of key Agent Monitor metrics — active sessions, total
cost from the pricing engine, events today from daily_events, top tool
from tool_usage, and current model from the most recent session. Use for
a fast at-a-glance check without leaving the terminal.
---
# Quick Stats
One-line summary of key Agent Monitor metrics.
## Input
The user provides: **$ARGUMENTS**
Options: empty (default), "cost" (cost only), "sessions" (sessions only), "tokens" (token summary).
## Data Sources
| Endpoint | Returns |
|----------|---------|
| `GET /api/stats` | `{ total_sessions, active_sessions, active_agents, total_agents, total_events, events_today, ws_connections, agents_by_status, sessions_by_status }` |
| `GET /api/pricing/cost` | `{ total_cost, breakdown }` |
| `GET /api/analytics` | tokens (total_input, total_output, total_cache_read, total_cache_write — baselines pre-summed), tool_usage, daily_sessions, daily_events |
| `GET /api/sessions?limit=1` | Most recent session for model/status |
## Output
Produce a single-line or compact summary:
**Default format:**
```
📊 127 sessions | 💰 $4.2301 total cost | 🔧 4,892 events | ⚡ 3 active | 🏆 Top tool: Read (1,204)
```
**Cost format:**
```
💰 Total: $4.2301 | Sonnet: $3.1200 | Opus: $0.9800 | Haiku: $0.1301 | Cache efficiency: 67%
```
**Sessions format:**
```
📋 127 total | ✅ 98 completed | ❌ 12 errored | 🏃 3 active | 💤 14 abandoned | Rate: 87%
```
**Tokens format:**
```
🔤 Input: 2.4M | Output: 890K | Cache Read: 1.8M | Cache Write: 340K
```
Keep it short enough to scan in a terminal prompt.
© hoangsonww · MIT · hoangsonww/Claude-Code-Agent-Monitor
Similar skills
All skills for Agent setup: memory, context, orchestration →quick-stats by other authors comes first.