Cost Tracker

Token Budget by Task Type

Tool-Call Budgets

Set explicit budgets by task complexity:

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

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