Agent skill · Business & Finance

token-tracking

Token usage monitoring and cost tracking with configurable thresholds. Reference this skill to understand pricing and limits.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill token-tracking --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 7 KB
Bundled scripts: none
Path: skills/ai-llm/token-tracking/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

// Project Autopilot - Token Usage Monitoring // Copyright (c) 2026 Jeremy McSpadden <jeremy@fluxlabs.net> # Token Tracking Skill Monitor token usage and costs with configurable thresholds for warnings, alerts, and hard stops. Thresholds can be set globally via `/autopilot:config` and persist across sessions. --- ## Model Pricing (as of 2024) ### Claude Models (4.5 Generation) | Model | Input (per 1M) | Output (per 1M) | |-------|----------------|-----------------| | Opus | $5.00 | $25.00 | | Sonnet | $3.00 | $15.00 | | Haiku | $1.00 | $5.00 | ### Quick Reference | Model | 1K Input | 1K Output | Typical Task | |-------|----------|-----------|--------------| | Opus | $0.005 | $0.025 | ~$0.05-0.20 | | Sonnet | $0.003 | $0.015 | ~$0.02-0.10 | | Haiku | $0.00025 | $0.00125 | ~$0.002-0.01 | --- ## Threshold Types ### Warning (Yellow) ⚠️ - Log warning to progress.md - Display alert to user - **Continue execution** ### Alert (Orange) 🟠 - Log alert to progress.md - Display prominent alert - **Pause and ask for confirmation** - Resume only with explicit approval ### Stop (Red) 🛑 - Log stop reason to progress.md - Save checkpoint immediately - **Halt all execution** - Require manual restar

What's inside
Steps it walks through
  1. Model Pricing (as of 2024)
  2. Claude Models (4.5 Generation)
  3. Quick Reference
  4. Threshold Types
  5. Warning (Yellow) ⚠️
  6. Alert (Orange) 🟠
  7. Stop (Red) 🛑
  8. Configuration Options
  9. By Dollar Amount
  10. By Token Count
  11. Combined
  12. Tracking Data
  13. Token Log Format
  14. Threshold Checks
Ships with 1 file
  • metadata.json
Commands it runs
Warning at $5, alert at $10, stop at $20
Just a hard stop at $50
Warning only
Warning at 100K, alert at 500K, stop at 1M tokens
Using K/M suffixes
Stop at either $20 OR 1M tokens (whichever first)
Set your preferred defaults
View current config
More from claude-skill-registry
All skills →
About this skill
What does the token-tracking skill do?

Token usage monitoring and cost tracking with configurable thresholds. Reference this skill to understand pricing and limits.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill token-tracking --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going