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 tellmefrankie/news-engine --skill claude-cost-trackergit clone --depth 1 https://github.com/tellmefrankie/news-engineWrote 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/tellmefrankie/news-engine/claude-cost-tracker)<a href="https://agentmods.dev/skills/tellmefrankie/news-engine/claude-cost-tracker"><img src="https://agentmods.dev/badge/skills/tellmefrankie/news-engine/claude-cost-tracker/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/tellmefrankie/news-engine/claude-cost-tracker"><img src="https://agentmods.dev/badge/skills/tellmefrankie/news-engine/claude-cost-tracker.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 | $0.00000 | $0.00692 |
| Opus 5 | $0.00000 | $0.00346 |
| Sonnet 5 | $0.00000 | $0.00138 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
claude-cost-tracker 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 11d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude API Cost Tracker
Track your Anthropic API spend by project, model, and task type. Know exactly what each feature costs before it ships.
What it does
- Pulls usage data from Anthropic API billing endpoint
- Breaks down cost by: project, model (Opus/Sonnet/Haiku), date range
- Flags expensive operations (prompts > $0.10 per call)
- Projects monthly spend from current daily burn rate
- Identifies which tasks are best candidates for model downgrade (Opus → Sonnet)
Usage
Check my Claude API costs for this week.
Break down by: model, project tag, daily trend.
Flag any single calls over $0.05.
Project monthly spend at current rate.
Suggest which tasks could switch from Opus to Sonnet without quality loss.
Example Output
Claude API Cost Report — Week of May 13, 2026
TOTAL THIS WEEK: $4.23
Opus 4.5: $3.10 (73%) — news analysis pipeline
Sonnet 4.5: $0.89 (21%) — investment briefing
Haiku 4.5: $0.24 (6%) — price monitor checks
DAILY BURN: $0.60/day
MONTHLY PROJECTION: ~$18/month
TOP EXPENSIVE CALLS (this week):
$0.14 — filter.ts:45 — 50-article importance ranking prompt
$0.09 — analyze.ts:88 — per-article deep analysis (x5 articles)
$0.04 — briefing.ts:12 — portfolio summary generation
OPTIMIZATION SUGGESTIONS:
filter.ts ranking prompt: Switch to Sonnet — saves ~$0.06/day ($1.80/month)
Confidence: HIGH — filtering is structured JSON output, not nuanced reasoning
price monitor heartbeat: Already on Haiku — optimal
Model Downgrade Analysis
The skill evaluates each prompt type against downgrade criteria:
| Task type | Opus needed? | Recommendation |
|---|---|---|
| Structured JSON extraction | No | → Sonnet |
| Importance ranking (1-5) | No | → Haiku |
| Nuanced sentiment analysis | Yes | Keep Opus |
| Code generation | Situational | Test Sonnet first |
| Multi-step reasoning chains | Yes | Keep Opus |
Configuration
Track Claude costs:
API key: (reads from ANTHROPIC_API_KEY env)
Date range: last 7 days
Group by: model, then by file/prompt tag
Budget alert: warn if projected monthly > $30
Downgrade candidates: flag any Opus task where Sonnet could substitute
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.
- 11d ago First seen · 86 lines · 0 tokens per session scan A 9bd25eff2387
claude-cost-tracker is a skill published in the GitHub repository tellmefrankie/news-engine (1 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 692 tokens. 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
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
excel-author
Build auditable financial workbooks headless via openpyxl.
solana
Query Solana wallets, tokens, txs, and NFTs in USD.
stocks
Stock quotes, history, search, compare, crypto via Yahoo.
merger-model
Build M&A accretion/dilution workbooks in Excel.