scoobydont-666 Cost Optimizer
Three cost dimensions: Claude API, Infrastructure, Cloud Hosting.
1. Claude API Costs
Model Pricing (per million tokens — input/output)
| Model | Input | Output | Use For |
|---|---|---|---|
| opus | $5.00 | $25.00 | Architecture decisions, adversarial review |
| sonnet | $3.00 | $15.00 | Default — code edits, analysis |
| haiku | $1.00 | $5.00 | Status checks, file reads, git ops |
Session-Miser Routing Rules
- Start every session on
sonnet(default) - Escalate to
opusonly for: deep reasoning, security review, complex architecture - Delegate to
haikusubagents for: search, log tails, file reads, git status, simple transforms - Use effort levels:
opus:lowis cheaper than full opus for structured tasks
See: session-miser skill for full routing logic.
See: token-miser skill for subagent cost controls.
Anti-Patterns (Avoid)
- Using Opus for git commits or file reads
- Not delegating read-only work to Haiku subagents
- Running full sessions on Opus when Sonnet suffices
- Skipping effort level specification on Opus calls
Token Tracking via Analytics Tool
# Session cost summary (use your analytics tool)
analytics-tool stats
# Cost by model
analytics-tool cost
# Dashboard (local)
open http://127.0.0.1:<service-port>
# Weekly report
analytics-tool report --period week
See: budi-analytics skill for analytics implementation.
2. Infrastructure Costs
Electricity
- TOU rates apply — peak hours cost 2-3x off-peak
- Solar offset via Enphase IQ Gateway ()
- Key metric:
solar_net_watts— positive = free electricity (exporting) - When net_watts > 0: run full mining fleet, cost = $0 for that power
Mining Profitability (Hashrate Hedger)
- Inputs: XMR spot price, network difficulty, pool hashrate, electricity rate, solar_net_watts
- Decision: run full fleet / throttle / pause based on break-even threshold
- Infrastructure: pool relay host (P2Pool relay), dedicated miner host (~10.5 KH/s), GPU-capable hosts (GPU-accelerated mining)
- Never run mining on relay nodes — they are NOT miners
Service Power Draw (approximate)
| System | Draw | Notes |
|---|---|---|
| GPU host (idle) | ~150W | Dual GPU cards |
| GPU host (mining) | ~400W+ | GPU-accelerated RandomX |
| Relay host | ~35W | CPU-only, no discrete GPU |
| Mining host | ~90W | High-performance CPU mining |
See: solar-energy skill for TOU and battery pre-positioning.
See: crypto-monero-wizard skill for mining profitability formulas.
3. Cloud Hosting — When Required
Projected Year 1 costs (when deployed):
- AWS/Azure app hosting: $40-80/mo
- Ollama inference stays self-hosted on GPU infrastructure (no cloud cost)
- PostgreSQL: RDS
$15/mo or self-hosted on GPU infrastructure ($0 marginal) - CDN/storage: minimal (<$5/mo at launch volume)
Strategy: maximize self-hosted workloads on local infrastructure before adding cloud spend.
Weekly Cost Review Checklist
session-snitch stats— check session token spend vs prior week- Grafana dashboard — GPU power draw trend
- Check solar production vs consumption ratio
- Review any cloud services added since last review
- Confirm no Opus usage for mechanical tasks (check budi by model)
Related Skills
session-miser— model routing decisionstoken-miser— subagent cost enforcementbudi-analytics— token spend dashboards and CLIsolar-energy— electricity offset via solarcrypto-monero-wizard— mining cost/profitability