From ultraship
Tracks AI build costs per feature via Node.js script. Logs token usage with bash, generates dashboards for spend breakdowns by task/model, trends, insights, and optimization recommendations.
npx claudepluginhub houseofmvps/ultraship --plugin ultrashipThis skill is limited to using the following tools:
Know exactly what each feature costs to build with AI. Budget smarter, spend less.
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.
Generates advanced cost insights for Claude Code sessions: efficiency scoring, waste detection, ROI metrics, model savings calculator, anomaly detection, and GitHub badges. Use to optimize AI spend.
Tracks AI token consumption across providers, detects waste, estimates theoretical costs, and suggests optimizations. Useful for monitoring usage, quotas, and efficiency in AI interactions.
Share bugs, ideas, or general feedback.
Know exactly what each feature costs to build with AI. Budget smarter, spend less.
node ${CLAUDE_PLUGIN_ROOT}/tools/cost-tracker.mjs <project-directory> show
Parse the JSON output for cost history and summary.
Present spending overview:
Total Spend:
By Task/Feature:
By Model:
Daily Trend:
Generate actionable insights:
To log a new cost entry:
node ${CLAUDE_PLUGIN_ROOT}/tools/cost-tracker.mjs <project-directory> log "<label>" <input_tokens> <output_tokens> --model=claude-opus-4-6
Labels should be descriptive kebab-case: auth-feature, bug-fix-login, refactor-api, seo-optimization
Based on spending patterns:
If debugging > 30% of spend:
/test-driven-development skillIf a single task > 3x average:
Model optimization:
Help the user understand when and how to log costs:
When reviewing cost data, help the user think about the economics of building with AI:
Worth building with AI (high ROI):
Consider alternatives:
Cost benchmarks for solo founders:
| Task Type | Expected Cost | If Higher, Investigate |
|---|---|---|
| New API endpoint | $1-5 | Complex business logic or unclear spec |
| Bug fix | $0.50-3 | Missing tests or hard-to-reproduce issue |
| Full feature (frontend + backend) | $5-20 | Large scope or frequent rework |
| Refactoring | $2-10 | Unclear boundaries or missing tests |
| Content/copy generation | $0.25-1 | Too many revision cycles |