Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add brody-0125/my-claude-skills --skill cost-trackinggit clone --depth 1 https://github.com/brody-0125/my-claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/brody-0125/my-claude-skills/cost-tracking)<a href="https://agentmods.dev/skills/brody-0125/my-claude-skills/cost-tracking"><img src="https://agentmods.dev/badge/skills/brody-0125/my-claude-skills/cost-tracking/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/brody-0125/my-claude-skills/cost-tracking"><img src="https://agentmods.dev/badge/skills/brody-0125/my-claude-skills/cost-tracking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.00933 |
| Opus 5.5 | $0.00008 | $0.00373 |
| Sonnet 5.5 | $0.00004 | $0.00187 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
cost-tracking scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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. 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 | <$0.03 |
| Cost per productive call | session_cost / productive_calls | <$0.05 |
| Input/Output ratio | input_tokens / output_tokens | 3:1 to 6:1 (normal range) |
Improvement ROI Scoring
Formula for prioritizing improvement proposals:
ROI_score = (Impact × Confidence) / (Effort × Risk)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 115 lines · 21 tokens per session scan A 1428bd1e70f9
cost-tracking is a skill published in the GitHub repository brody-0125/my-claude-skills (2 stars, last pushed 8mo ago), licensed MIT. It adds 21 tokens to every session and 933 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
brainstorming
Structured brainstorming for Symfony projects - explore requirements, identify components, and plan architecture collaboratively.
executing-plans
Methodically execute implementation plans with a TDD approach, incremental commits, and continuous validation.
using-symfony-superpowers
Entry point for Symfony Superpowers - lightweight workflow guidance and command map.
writing-plans
Create structured implementation plans for Symfony features with clear steps, dependencies, and acceptance criteria.
architect
Answer build-or-adopt honestly, then design one committed architecture from your own understanding of the problem — driven by ranked quality attributes, stress-tested against the field and against change, proven by a walking skeleton, its consequences confirmed by the user, committed to ARCHITECTURE.md. A command the…
designer
Settle the look before the pixels — audience and context first, then the base and the delta, directions drawn as tiles from a written brief and a critic's read of the chosen one, accessibility as the floor, one design language committed to DESIGN.md as tokens with roles. A command the user types, for work with an…