Skip to main content
skill CX Codex

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.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill quick-stats -a claude-code
Open on GitHub

What 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 cost argument to report spending only.
  • Run quick-stats with the tokens argument 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-code

2Manually: put the files in place

~/.claude/skills/quick-stats/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/quick-stats/

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.

From the same set22

regression-watch Compares an older baseline window of session history with a recent one and reports which metrics got worse: errors, cache, compactions, cost per session. CX Codex +1 ★ 1,121repo stars benchmark The benchmark skill takes one session or a few recent ones and compares them with the rolling average from Agent Monitor data: cost, tokens, tool count and workflow complexity. Each metric comes back as a percentile of the population. CX Codex +1 ★ 1,121repo stars session-debug Pulls a single Claude session out of Agent Monitor and reports its event chain, subagent tree, token spend and failures. CX Codex +1 ★ 1,121repo stars event-trace Turns one Claude session into an ordered timeline of its events, flagging gaps, failures and tool calls that never finished. CX Codex +1 ★ 1,121repo stars live-watch Polls the Agent Monitor /api/stats endpoint a few times in a row and reports how the counters shift across that window. Useful when you want motion, not a single snapshot. CX Codex +1 ★ 1,121repo stars spend-forecast Turns the daily session trend on the Agent Monitor dashboard into a spend projection for the end of the week or month. CX Codex +1 ★ 1,121repo stars cost-alert Walks through the budget rules configured in Agent Monitor and the alerts that already fired, with a plain explanation of what set each one off. CX Codex +1 ★ 1,121repo stars memory-review Walks the agent's file-based memory: CLAUDE.md files and per-project auto-memory. Flags facts that went stale or grew too big. CX Codex +1 ★ 1,121repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor