cost-tracker — Claude Code skill: costs and setup
The cost-tracker skill helps you review Claude Code session costs, set budget checkpoints, and spot expensive work patterns. Use it when planning work across sessions.
MIT ★ 2,966 updated 2026-09-29
/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflowWhat cost-tracker does
cost-tracker explains how to inspect session spending and identify common cost drivers, including large file reads, broad searches, repeated tool calls, and model choice. To check costs before a session ends, it points to the status bar or /cost; the session total appears when the session is over. Its budgets are planning guidance, not enforced caps.
The skill gives task-based cost and tool-call estimates, then suggests checkpoints at 50%, 80%, and 100% of a budget. At a checkpoint, decide whether to wrap up or continue in a fresh session. Other suggestions include narrowing prompts, reading large files in sections, and batching independent calls. It recommends Haiku for simple lookups, Sonnet for features, and Opus for architecture. Code quality should not be traded away to save tokens.
What it helps with
- check the cost of an active session
- estimate a budget for a bug fix or feature
- spot operations that drive token spending
- decide when to wrap up or start a fresh session
Example prompts for the agent
- Review this session's costs and identify the main spending drivers.
- Set a tool-call budget for implementing a large feature.
- Suggest ways to reduce token use while searching this project.
How to install cost-tracker
1Plugin marketplace
/plugin marketplace add rohitg00/pro-workflow/plugin install pro-workflow@pro-workflowThis installs the whole pro-workflow plugin with all its skills
2Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill cost-tracker -a claude-code3Manually: put the files in place
~/.claude/skills/cost-tracker/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/cost-tracker/
1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill cost-tracker -a codex2Manually: put the files in place
.agents/skills/cost-tracker/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill cost-tracker -a cursor2Manually: put the files in place
.cursor/skills/cost-tracker/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rohitg00/pro-workflow skills/cost-tracker2Manually: put the files in place
.github/skills/cost-tracker/SKILL.md1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill cost-tracker -a gemini-cli2Platform CLI
gemini skills install https://github.com/rohitg00/pro-workflow --path skills/cost-trackerManually: put the files in place
.devin/skills/cost-tracker/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.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 cost-tracker
How do I install cost-tracker in Claude Code?
First add the marketplace with /plugin marketplace add rohitg00/pro-workflow, then install the plugin with /plugin install pro-workflow@pro-workflow.
What does cost-tracker do?
It helps review Claude Code session costs, identify spending drivers, and plan token and tool-call budgets. The budgets are guidance rather than hard limits.
How can I check spending before a session ends?
Check the status bar or run /cost. The final session cost is shown when the session ends.
Source text
SKILL.md · MIT
---
name: cost-tracker
description: Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.
user-invocable: true
---
# Cost Tracker
Monitor and optimize Claude Code session costs.
## Trigger
Use when:
- Checking session costs
- Setting budget alerts
- Optimizing token spend
- Planning multi-session work
## Cost Awareness
### Check Current Costs
```bash
# Session cost is shown at the end of each session
# Mid-session: check the status bar or run /cost
```
### Cost Drivers
| Operation | Relative Cost | Optimization |
|-----------|--------------|-------------|
| Large file reads | High | Use offset/limit params |
| Broad grep searches | Medium | Scope to specific dirs |
| Subagent spawning | High (new context) | Reuse agents via SendMessage |
| Repeated tool calls | Cumulative | Batch operations |
| MCP tool calls | Variable | Minimize round-trips |
| Model selection | 3-10x difference | Use haiku for simple tasks |
### Token Budget by Task Type
| Task | Typical Cost | Budget Alert |
|------|-------------|-------------|
| Bug fix | $0.10-0.50 | $1.00 |
| Feature (small) | $0.50-2.00 | $3.00 |
| Feature (large) | $2.00-8.00 | $10.00 |
| Refactor | $1.00-5.00 | $7.00 |
| Code review | $0.20-1.00 | $2.00 |
### Tool-Call Budgets
Set explicit budgets by task complexity:
| Task Type | Tool-Call Budget | Wrap-Up At |
|-----------|-----------------|------------|
| Quick fix / lookup | 20 calls | 15 |
| Bug fix | 30 calls | 25 |
| Feature (small) | 50 calls | 40 |
| Feature (large) | 80 calls | 65 |
| Refactor | 50 calls | 40 |
At the wrap-up threshold: commit progress, assess remaining work, decide whether to continue or start fresh.
### Optimization Strategies
1. **Scope prompts tightly** — "Fix the auth bug in src/auth/login.ts" vs "Fix the auth bug"
2. **Use the right model** — Haiku for simple lookups, Sonnet for features, Opus for architecture
3. **Delegate to subagents** — Search/explore operations in subagents keep main context lean
4. **Compact proactively** — Don't wait for auto-compact; compact at task boundaries
5. **Read selectively** — Use `offset` and `limit` params for large files
6. **Batch operations** — Multiple independent tool calls in one message
7. **One-pass discipline** — Write complete solution, test once, stop if green
8. **No re-reads** — Don't re-read unchanged files; trust cached knowledge
9. **Read before write** — Never write a file without reading it first
10. **Kill output bloat** — No sycophantic openers, no closing fluff, no prompt restatement
## Budget Alerts
Set mental checkpoints:
- **50% budget** — Are you on track? Should you compact?
- **80% budget** — Wrap up current task, avoid new exploration
- **100% budget** — Commit what you have, start fresh session
## Output
```text
COST TRACKER
Session cost: $X.XX
Token usage: [input]K in / [output]K out
Cache hit rate: ~XX%
Top cost drivers:
1. [operation] — $X.XX
2. [operation] — $X.XX
Optimization tips:
- [specific suggestion]
```
## Rules
- Track costs as awareness, not hard limits
- Never sacrifice code quality to save tokens
- Compact at task boundaries, not mid-task
- Use subagents for exploration-heavy work
© Rohit Ghumare · MIT · rohitg00/pro-workflow