What is usaspending-guide?

A guide for using USAspending, a public U.S. government database of federal awards and spending. It explains how to trace awards, recipients, funding accounts, and reporting periods without mixing different kinds of totals.

It supports federal award investigations, recipient and funding-account tracing, spending comparisons, and research into emergency funding.

It reduces errors caused by using the wrong identifier, period, award type, recipient level, or spending measure when comparing government data.

usaspending-guide — Skill for Claude Code by cyanheads

Install

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.

Any agent

npx skills add cyanheads/usaspending-mcp-server --skill usaspending-guide

Clone the repo

git clone --depth 1 https://github.com/cyanheads/usaspending-mcp-server

Made for: Claude Code.

Or install usaspending-mcp-server, the plugin that ships this one along with the rest of its 35 skills, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cyanheads/usaspending-mcp-server/usaspending-guide/github.svg)](https://agentmods.dev/skills/cyanheads/usaspending-mcp-server/usaspending-guide)

Your own site

<a href="https://agentmods.dev/skills/cyanheads/usaspending-mcp-server/usaspending-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/usaspending-mcp-server/usaspending-guide/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cyanheads/usaspending-mcp-server/usaspending-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/usaspending-mcp-server/usaspending-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,076 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00044	$0.01076
Opus 5.5	$0.00018	$0.00430
Sonnet 5.5	$0.00009	$0.00215
Haiku 4.5	$0.00004	$0.00108

Measured 2d ago against content hash 5544e979461e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

usaspending-guide 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 2d 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.

skills/usaspending-guide/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope

Use USAspending for federal award investigations and spending comparisons. Award search cannot establish coverage before 2007-10-01; use bulk downloads for earlier award searches. This restriction does not describe the federal-account tools' reporting-year coverage.

Identifiers

Preserve identifiers returned at each hop rather than constructing them from display names:

Award search's generated_internal_id opens the award detail and award drill-down tools. The displayed award number is not the chain ID. An IDV child's generated_unique_award_id opens that child's detail.
Recipient search's id, award detail's recipient.recipient_id, and recipient-category rows' recipient_id identify recipient profiles. Preserve the hierarchy suffix; UEI and DUNS are separate identifiers.
Award funding rows' federal_account and account search's account_number open the federal-account tools. A detail's Treasury Account Symbol child code is not a federal-account code.

Gates

Before comparing amounts across tools, fix the award types, period, recipient hierarchy, geographic scope, and measure being compared. Search and time series default to contracts; an unfiltered geography query covers every award type. Do not compare their defaults as if they describe the same population.

Before treating an empty ID-keyed listing as evidence of no activity, confirm the award or account with its detail tool. A nonexistent ID can also return an empty listing. Check pagination and response notices before describing any result as exhaustive.

Before attributing a matching award's amount to an Assistance Listing or DEF code, inspect the award's listing obligations or DEF funding breakdown. These filters select matching awards; the returned whole-award amount is not the requested listing's or code's share.

Workflows

Investigate a recipient

Resolve the organization with usaspending_search_recipients and inspect its profile before choosing a parent, child, or standalone entity. For exact-entity trends, carry that recipient hash into usaspending_spending_over_time and explicitly select award types. The profile covers every award type and defaults to the trailing 12 months; select a fiscal year when comparing annual results.

Read the full file on GitHub · 57 lines

Changes

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.

2d ago Changed · +2 lines 5544e979461e
10d ago First seen · 55 lines · 44 tokens per session scan A 717e9c061159

Subscribe to this mod's changes

usaspending-guide is a skill published in the GitHub repository cyanheads/usaspending-mcp-server (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,076 once invoked, about $0.0002 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 2026-10-27.

Finance and fintech Research ai-agents ai-tools cyanheads federal-spending fiscal-policy government-contracts

usaspending-guide next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
usaspending-guidecyanheads/usaspending-mcp-server	Skill	5	3d ago	Apache-2.0	A	44	Claude Code
exchange-rates-guidecyanheads/exchange-rates-mcp-server	Skill	1	3d ago	Apache-2.0	A	57	Claude Code
financetravisjneuman/.claude	Skill	107	yesterday	MIT	A	48	Claude Code, Codex
investment-memo-generatortravisjneuman/.claude	Skill	107	yesterday	MIT	A	37	Claude Code, Codex
levyseaworld008/Commonly-used-high-value-skills	Skill	74	yesterday	MIT	A	50	Claude Code, Codex
financial-analystseaworld008/Commonly-used-high-value-skills	Skill	74	yesterday	MIT	A	27	Claude Code, Codex
earnings-call-analyzerseaworld008/Commonly-used-high-value-skills	Skill	74	yesterday	MIT	A	33	Claude Code, Codex