- Home
- Skills
- Agents & Orchestration
- LLM Spend Receipt
Works with the AI Agents you already use
LLM Spend Receipt
Convert LLM usage exports into automated daily spend receipts with cache analysis and cost caps.
$5
LLM Spend Receipt
Example session with this skill installed
Run a spend receipt for usage.csv dated 2025-05-14. The typical daily spend is $5.00. Focus on the 'project_id' tag.
- Read your context and instructions
- Compiled the llm spend receipt
Spend receipt processed for 2025-05-14. Identified a cost spike driven by prompt cache misses in the production workspace.
Spend receipt — 2025-05-14
Total: $12.45
Cache: 12% of input tokens were hits (~$0.85 vs miss-price)
Tokens: 1.2M in / 450k out / 180k cache-read / 50k cache-write
Requests: 1,420
By model
- claude-3-5-sonnet $8.10 65% 800k in / 300k out cache 15%
- claude-3-opus $4.35 35% 400k in / 150k out cache 5%
By tag
- production-api $9.50 76%
- staging-tests $2.95 24%
Blew up
- production-api — $9.50 (76% of day)
- day is 2.49× typical ($5.00)
Cap
- production-api: hard-cap near $6.50/day
- claude-3-5-sonnet: cache hit 15% — reorder the prompt (static prefix first, variable text last)
- account: page if a day exceeds $7.50 (1.5× typical)
Next steps
- Review the
production-apisystem prompt to increase cache hits. - Apply the $6.50 hard-cap in the provider dashboard for the
production-apikey. - Update
typical_usdto $10.00 if this new volume is the new baseline.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Usage dashboards are often buried behind auth walls or cluttered with irrelevant metrics. Developers lack a simple, automated way to see exactly where their daily LLM budget went without manual reconciliation.
What it does
- Parses provider usage CSVs or API responses into a phone-sized text receipt.
- Calculates real cache-hit rates to show actual savings versus list prices.
- Identifies "blow-up" events where a specific model or tag consumed a disproportionate share of the daily budget.
- Generates actionable caps, such as hard-cap suggestions or prompt reordering for better caching.
- Distinguishes between cache-miss, cache-read, and cache-write token buckets for accurate pricing.
Frameworks & tools
Python 3.10+ standard library (csv, pathlib). Supports any provider exporting CSV usage data (Anthropic, OpenAI, etc.).
Why this beats prompting it yourself
General-purpose prompts often fail at token bucket math, incorrectly pricing cached tokens as standard input tokens. This skill enforces strict normalization across different header aliases and ensures $0 rows from local or seat-based models are retained for an accurate view of total system load.
Use cases
- Automate a morning Slack/email notification showing yesterday's total model spend.
- Audit a large agent run to see if caching strategies are actually reducing costs.
- Identify runaway jobs in a multi-tenant environment using tag-based grouping.
- Set baseline 'typical spend' alerts to catch billing spikes before the invoice arrives.
Known limitations
It is a daily operator view, not an accounting tool for invoice disputes or tax reconciliation. It does not perform multi-month forecasting.
Requires Python 3.10+. Does not perform multi-month forecasting or invoice reconciliation. Accuracy depends on user-provided rates if the CSV lacks a cost column.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
Requires