performance

A command for viewing token use, costs, and performance measurements from Claude Code sessions.

In plain words
What is it for?
Checking metrics for the current session or for daily, weekly, or monthly periods through ccusage.
Why use it?
It gathers session- or calendar-period usage information without requiring you to inspect it manually.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/stefan-jansen/claude-code-toolkit/performance
Clone the repo
git clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkit
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 703 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00006 $0.00703
Opus 5 $0.00003 $0.00351
Sonnet 5 $0.00001 $0.00141
Haiku 4.5 $0.00001 $0.00070

Measured 2d ago against content hash 54cfc770bbc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/memory/commands/performance.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Metrics

View token usage, costs, and performance metrics for your Claude Code sessions.

Usage

# View current session metrics
/performance

# View daily metrics
/performance daily

# View weekly metrics
/performance weekly

# View monthly metrics
/performance monthly

# Get help with ccusage
/performance help

Implementation

# Check if ccusage is available
if ! command -v npx >/dev/null 2>&1; then
    echo "❌ Performance monitoring requires npx (Node.js)"
    echo ""
    echo "To enable performance tracking:"
    echo "1. Install Node.js: https://nodejs.org/"
    echo "2. Run: npx ccusage@latest"
    exit 1
fi

# Parse arguments
TIMEFRAME="${ARGUMENTS:-session}"

echo "📊 Claude Code Performance Metrics"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo ""

case "$TIMEFRAME" in
    daily|day)
        echo "📅 Daily Usage Report"
        npx ccusage@latest daily
        ;;
    weekly|week)
        echo "📅 Weekly Usage Report"
        npx ccusage@latest weekly
        ;;
    monthly|month)
        echo "📅 Monthly Usage Report"
        npx ccusage@latest monthly
        ;;
    help|--help)
        echo "📚 ccusage Help"
        npx ccusage@latest --help
        ;;
    session|*)
        echo "💬 Current Session Metrics"
        npx ccusage@latest session

        # Also show daily summary
        echo ""
        echo "📅 Today's Summary"
        npx ccusage@latest daily
        ;;
esac

echo ""
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo ""
echo "💡 Performance Tips:"
echo "   • Use MCP tools for efficiency:"
echo "     - Serena: 70-90% token reduction on code operations"
echo "     - Context7: 50% faster documentation lookup"
echo "     - Sequential Thinking: Better analysis with fewer iterations"
echo "   • Monitor usage regularly to optimize workflows"
echo "   • Consider caching frequently accessed documentation"

Features

Token Usage Tracking

  • Session-level metrics
  • Daily, weekly, monthly aggregation
  • Cost calculation based on model pricing

Read the full file on GitHub · 126 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 126 lines · 6 tokens per session scan A 54cfc770bbc1

Subscribe to this mod's changes

performance is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 6 tokens to every session and 703 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.