# Cost Tracking

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-brody-0125-my-claude-skills-cost-tracking`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [brody-0125](https://agentstack.voostack.com/s/brody-0125)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [brody-0125](https://github.com/brody-0125)
- **Source:** https://github.com/brody-0125/my-claude-skills/tree/main/plugins/plugin-introspector/skills/cost-tracking

## Install

```sh
agentstack add skill-brody-0125-my-claude-skills-cost-tracking
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Cost Tracking — Model Pricing & Calculation

> Provides pricing data and calculation methods for API cost estimation.

## Model Pricing (per 1M tokens, USD)

| Model | Input | Output | Cache Write (5m) | Cache Read |
|-------|-------|--------|------------------|------------|
| claude-opus-4-6 | $5.00 | $25.00 | $6.25 | $0.50 |
| claude-sonnet-4-5 | $3.00 | $15.00 | $3.75 | $0.30 |
| claude-haiku-4-5 | $1.00 | $5.00 | $1.25 | $0.10 |

*Prices as of 2026-02. Source: [platform.claude.com/docs/en/about-claude/pricing](https://platform.claude.com/docs/en/about-claude/pricing). Update when pricing changes.*

## Cost Calculation

### Per-Request Cost

```
cost = (input_tokens × input_price / 1_000_000) +
       (output_tokens × output_price / 1_000_000) +
       (cache_write_tokens × cache_write_price / 1_000_000) +
       (cache_read_tokens × cache_read_price / 1_000_000)
```

### Session Cost Estimation

When actual API token counts are unavailable, use estimates:

```
estimated_input_tokens = sum(tool_input_chars) / 4
estimated_output_tokens = sum(tool_result_chars) / 4
estimated_cost = estimated_input_tokens × input_price / 1_000_000 +
                 estimated_output_tokens × output_price / 1_000_000
```

**Accuracy note**: chars/4 estimation has ±20% error. Actual API usage data (from api_traces.jsonl) provides exact costs when available.

## Budget Thresholds

| Level | Threshold | Action |
|-------|-----------|--------|
| INFO | >$0.50/session | Log to stats |
| WARNING | >$2.00/session | Alert (MEDIUM severity) |
| CRITICAL | >$10.00/session | Alert (HIGH severity) |

## Cost Efficiency Metrics

| Metric | Formula | Target |
|--------|---------|--------|
| Cost per tool call | session_cost / tool_calls | = 8
corroboration_bonus = (confirming_agents - 1) × 0.1
Confidence = min(base + corroboration_bonus, 1.0)
```

### Effort (1-5)

| Level | Description |
|-------|-------------|
| 1 | Single line addition/change |
| 2 | Multi-line section modification |
| 3 | New section or procedure step |
| 4 | Structural change across multiple sections |
| 5 | Component rewrite or new component |

### Risk (1-5)

| Level | Description |
|-------|-------------|
| 1 | Additive only (no existing behavior changed) |
| 2 | Minor behavior modification in non-critical path |
| 3 | Critical path modification with clear rollback |
| 4 | Cross-component change with interaction risk |
| 5 | Core algorithm/flow change |

### Priority Mapping

```
ROI >= 2.0 → CRITICAL
ROI >= 1.0 → HIGH
ROI >= 0.5 → MEDIUM
ROI <  0.5 → LOW
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [brody-0125](https://github.com/brody-0125)
- **Source:** [brody-0125/my-claude-skills](https://github.com/brody-0125/my-claude-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-brody-0125-my-claude-skills-cost-tracking
- Seller: https://agentstack.voostack.com/s/brody-0125
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.