Skill

cost-tracking

Tracks input, output, and cache token costs for Claude Code API calls using Python scripts, calculating USD costs from Anthropic pricing. Invoke via /cost-tracking or stop phrases like 'stop tracking'.

Python

Anthropic

monitoring

ai-ml

npx claudepluginhub jbdamask/john-claude-skills --plugin john-skills

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Track the exact token cost of any Claude Code operation by marking a start and stop point in the session JSONL.

Supporting Assets

resources/pricing.jsonscripts/start_tracking.pyscripts/stop_tracking.py

SKILL.md

Similar Skills

cost-tracker

2.0k

Tracks Claude Code session costs, sets budget alerts, and optimizes token spend with task budgets, cost drivers, and strategies. Useful for mid-session checks and multi-session planning.

pro-workflow

cost

533

Reports Claude Code session costs, token usage, burn rates, campaign spend, and model breakdowns from native data via /cost with time or campaign filters.

citadel

token-dashboard-claude-analytics

Runs local Python CLI dashboard analyzing Claude Code JSONL transcripts for per-prompt token costs, heatmaps, cache analytics, project comparisons, and optimization tips.

aradotso-trending-skills-37

Stats

Stars23

Forks2

Last CommitMar 8, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Cost Tracking

Track the exact token cost of any Claude Code operation by marking a start and stop point in the session JSONL.

Start Tracking

When the user invokes /cost-tracking:

Determine the current session JSONL path. It lives at:

~/.claude/projects/<project-hash>/<session-id>.jsonl

Find the project directory by looking for the most recently modified .jsonl file under ~/.claude/projects/. The project hash is a mangled version of the working directory path (slashes replaced with dashes, e.g., -Users-johndamask-myproject).

Determine the cost tracking output directory:

~/.claude/projects/<project-hash>/cost-tracking/

Run the start script:

python3 <skill-dir>/scripts/start_tracking.py <session_jsonl_path> <cost_tracking_dir>

Store the returned tracking_id — mention it to the user and remember it for the stop step.

Confirm: "Cost tracking started. I'll calculate costs when you say 'stop tracking'."

Stop Tracking

When the user says "stop tracking", "stop cost tracking", or asks about the cost:

Run the stop script with the tracking_id from the start step:

python3 <skill-dir>/scripts/stop_tracking.py <tracking_id> <cost_tracking_dir>

The script outputs a formatted cost report and writes:

tokens.jsonl — per-entry token log with timestamp, model, input_tokens, output_tokens
summary.json — aggregated cost breakdown by model

Present the report to the user.

Pricing

Pricing is stored in resources/pricing.json (last updated 2026-03-08, source: https://platform.claude.com/docs/en/about-claude/pricing). The stop script loads this file at runtime. It distinguishes between 5-minute and 1-hour cache writes using the cache_creation.ephemeral_* fields in the session JSONL. If pricing appears stale, fetch the pricing page and update resources/pricing.json.