From pro-workflow
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.
npx claudepluginhub rohitg00/pro-workflow --plugin pro-workflowThis skill uses the workspace's default tool permissions.
Monitor and optimize Claude Code session costs.
Tracks token usage and estimates costs for AI agent sessions. Use for monitoring spend, budget limits, or generating reports.
Tracks real-time costs and manages budgets for Claude Code sessions, displaying spend, burn rate, budget status, per-tool and per-model breakdowns. Invoke via /cost-guardian subcommands or keywords like 'cost', 'budget'.
Enforces cost-conscious mode reducing output tokens 40-70% and costs 30-60% via concise responses, model routing to haiku/sonnet, and efficient patterns. Auto-triggers on budget/cost/token mentions.
Share bugs, ideas, or general feedback.
Monitor and optimize Claude Code session costs.
Use when:
# Session cost is shown at the end of each session
# Mid-session: check the status bar or run /cost
| 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 |
| 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 |
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.
offset and limit params for large filesSet mental checkpoints:
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]