Skip to content
Research Agent Skillsby Kalaris Labs
Install
Scientific Databasesv1.3AdaptedMIT

usfiscaldata

Query the U.S. Treasury Fiscal Data REST API for federal financial data. No API key required. Use for national debt (Debt to the Penny), Daily Treasury Statements, Monthly Treasury Statements, Treasury securities auctions, interest rates, foreign exchange rates, savings bonds, or U.S. government revenue and spending statistics.

Install this skill

Works with Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, and 70+ other harnesses.

skills.sh CLI (Recommended)
npx skills add KalarisLabs/research-agent-skills --skill usfiscaldata
uvx (Python tool runner)
uvx research-agent-skills install usfiscaldata

Documentation & Instructions

U.S. Treasury Fiscal Data API

Free, open REST API from the U.S. Department of the Treasury for federal financial data. No API key or registration required.

Base URL: https://api.fiscaldata.treasury.gov/services/api/fiscal_service

Browse 54 datasets and 179 data tables via the dataset search. Verify endpoint paths on each dataset's API Quick Guide — paths change over time.

Installation

uv pip install requests pandas

Quick Start

import requests
import pandas as pd

BASE_URL = "https://api.fiscaldata.treasury.gov/services/api/fiscal_service"

# Get the current national debt (Debt to the Penny)
resp = requests.get(f"{BASE_URL}/v2/accounting/od/debt_to_penny", params={
    "sort": "-record_date",
    "page[size]": 1
})
data = resp.json()["data"][0]
print(f"Total public debt as of {data['record_date']}: ${float(data['tot_pub_debt_out_amt']):,.0f}")
# Get Treasury exchange rates for recent quarters
resp = requests.get(f"{BASE_URL}/v1/accounting/od/rates_of_exchange", params={
    "fields": "country_currency_desc,exchange_rate,record_date",
    "filter": "record_date:gte:2024-01-01",
    "sort": "-record_date",
    "page[size]": 100
})
df = pd.DataFrame(resp.json()["data"])

Authentication

None required. The API is fully open and free.

Core Parameters

Parameter Example Description
fields= fields=record_date,tot_pub_debt_out_amt Select specific columns
filter= filter=record_date:gte:2024-01-01 Filter records
sort= sort=-record_date Sort (prefix - for descending)
format= format=json Output format: json, csv, xml
page[size]= page[size]=100 Records per page (default 100)
page[number]= page[number]=2 Page index (starts at 1)

Filter operators: lt, lte, gt, gte, eq, in

# Multiple filters separated by comma
"filter=country_currency_desc:in:(Canada-Dollar,Mexico-Peso),record_date:gte:2024-01-01"

Key Datasets & Endpoints

Debt

Dataset Endpoint Frequency
Debt to the Penny /v2/accounting/od/debt_to_penny Daily
Historical Debt Outstanding /v2/accounting/od/debt_outstanding Annual
Schedules of Federal Debt /v1/accounting/od/schedules_fed_debt Monthly

Daily & Monthly Statements

Dataset Endpoint Frequency
DTS Operating Cash Balance /v1/accounting/dts/operating_cash_balance Daily
DTS Deposits & Withdrawals /v1/accounting/dts/deposits_withdrawals_operating_cash Daily
Monthly Treasury Statement (MTS) /v1/accounting/mts/mts_table_1 (18 tables — see datasets-fiscal.md) Monthly

Interest Rates & Exchange

Dataset Endpoint Frequency
Average Interest Rates on Treasury Securities /v2/accounting/od/avg_interest_rates Monthly
Treasury Reporting Rates of Exchange /v1/accounting/od/rates_of_exchange Quarterly
Interest Expense on Public Debt /v2/accounting/od/interest_expense Monthly

Securities & Auctions

Dataset Endpoint Frequency
Treasury Securities Auctions Data /v1/accounting/od/auctions_query As Needed
Treasury Securities Upcoming Auctions /v1/accounting/od/upcoming_auctions As Needed
Treasury Securities Buybacks /v1/accounting/od/buybacks_operations As Needed

Savings Bonds

Dataset Endpoint Frequency
I Bonds Interest Rates /v1/accounting/od/i_bonds_interest_rates Semi-Annual
Savings Bonds Issues, Redemptions & Maturities /v1/accounting/od/savings_bonds_report Monthly

Response Structure

{
  "data": [...],
  "meta": {
    "count": 100,
    "total-count": 3790,
    "total-pages": 38,
    "labels": {"field_name": "Human Readable Label"},
    "dataTypes": {"field_name": "STRING|NUMBER|DATE|CURRENCY"},
    "dataFormats": {"field_name": "String|10.2|YYYY-MM-DD"}
  },
  "links": {"self": "...", "first": "...", "prev": null, "next": "...", "last": "..."}
}

Note: All values are returned as strings. Convert as needed (e.g., float(), pd.to_datetime()). Null values appear as the string "null".

Common Patterns

Load all pages into a DataFrame

Use the bounded fetch_all() helper in parameters.md. For small result sets, a single request with page[size]=10000 may suffice when meta.total-pages is 1.

# Single-page fetch when total-pages == 1
params = {"sort": "-record_date", "page[size]": 10000}
resp = requests.get(f"{BASE_URL}/v2/accounting/od/debt_outstanding", params=params)
result = resp.json()
if result["meta"]["total-pages"] > 1:
    raise ValueError("Use fetch_all() from parameters.md for multi-page results")
df = pd.DataFrame(result["data"])

Aggregation (automatic sum)

Omitting grouping fields triggers automatic aggregation:

# Sum all deposits/withdrawals by record_date and transaction type
resp = requests.get(f"{BASE_URL}/v1/accounting/dts/deposits_withdrawals_operating_cash", params={
    "fields": "record_date,transaction_type,transaction_today_amt"
})

Reference Files

Agent operating procedure

  1. Check the environment. Confirm network access, API keys (if required) and the database's current API documentation and rate limits.
  2. Pin down the inputs. Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.
  3. Run a small version first. Fetch a single known record and check the response format before bulk queries.
  4. Execute the full task using the instructions and references above.
  5. Validate the result. Identifiers resolve, record counts are reported, and the database version or access date is recorded.
  6. Report. State what was run (versions, commands, parameters), what was checked, and what is still uncertain.
If this happens Do this
HTTP 429 or 5xx errors Respect rate limits with backoff, batch requests, and report partial results honestly.
A function, flag or endpoint in these instructions is missing in the installed version Check the installed version's own documentation (help(), --help, official docs), adapt, and tell the user. Never invent an API.
A required input, identifier or parameter is ambiguous Ask the user, or state the assumption explicitly before running.

Integrity rules

  • Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.
  • Never invent accession numbers, IDs or records; report 'not found' instead.
  • Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.
  • Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.

Trigger Prompts & Evaluation Corpus

These evaluation prompts test that the agent correctly selects usfiscaldata for relevant tasks and leaves it out for near misses.

Should trigger (3)

  • should trigger

    “what's the current total public debt outstanding?”

    expects Queries the Debt to the Penny endpoint (/v2/accounting/od/debt_to_penny) sorted by -record_date with page[size]=1, reports tot_pub_debt_out_amt converted from string to a number, and states the record_date of the value.

  • should trigger

    “I'm writing a paper on federal interest costs. Can you pull monthly interest expense on the public debt from fiscal year 2015 through 2024 into a pandas DataFrame and save it as interest_expense.csv? I want record_date, the expense category, and the amount. Watch out for pagination, I think there are more than 100 rows.”

    expects Uses the Fiscal Data API interest_expense endpoint (/v2/accounting/od/interest_expense) with fields, a filter on record_date gte/lte, and paginates via page[number] and meta total-pages (a bounded fetch_all). Converts string values to numeric, handles 'null' strings, writes the CSV, and reports record counts, query parameters and the access date.

  • should trigger

    “I need to know how much demand there was at recent 10-year Treasury note auctions, like bid-to-cover ratios over the past two years, and also which auctions are coming up next. No idea where to get this for free without signing up.”

    expects Identifies the keyless Treasury Fiscal Data API and uses auctions_query for historical auction results (filtered by security type and date, selecting bid-to-cover fields) and upcoming_auctions for the schedule. Runs a small query first to confirm field names rather than guessing them, and reports the results with the dates.

Near misses (2)

  • near miss

    “Get me daily closing prices and volume for the 10-year Treasury ETF IEF for the last year and compute its rolling volatility.”

    expects Does not use the Treasury Fiscal Data API, since ETF market prices are not in it. A market-data source such as yfinance or a financial data provider is more appropriate.

  • near miss

    “Run a regression of GDP growth on the unemployment rate using quarterly FRED series and report the coefficients with robust standard errors.”

    expects Does not use the Treasury Fiscal Data API. This is a macroeconomic data and regression task that should use a FRED data source and a statistics or econometrics tool such as statsmodels.