usaspending

usaspending is a skill for Claude Code, Codex from iblai/government-agents. It costs 29 tokens per session (582 once invoked), scanned A, original, MIT.

A connection to USASpending.gov, the U.S. government’s public database of federal contracts, grants, loans, and other spending.

In plain words
What is it for?
Use it to check a vendor’s past government awards, compare prices for similar goods or services, study agency spending, and examine competitive versus sole-source awards.
Why use it?
It avoids manually searching government award records and makes public spending data available for research and comparisons.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to check a vendor’s past government awards, compare prices for similar goods or services, study agency spending, and examine competitive versus sole-source awards.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iblai/government-agents/usaspending
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 iblai/government-agents --skill usaspending
Clone the repo
git clone --depth 1 https://github.com/iblai/government-agents

Made for: Claude Code, Codex.

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.

agentmods badge for usaspending

README.md
[![agentmods](https://agentmods.dev/badge/skills/iblai/government-agents/usaspending/github.svg)](https://agentmods.dev/skills/iblai/government-agents/usaspending)
Your own site
<a href="https://agentmods.dev/skills/iblai/government-agents/usaspending"><img src="https://agentmods.dev/badge/skills/iblai/government-agents/usaspending/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.

agentmods 80×15 button for usaspending

Your own site · 80×15
<a href="https://agentmods.dev/skills/iblai/government-agents/usaspending"><img src="https://agentmods.dev/badge/skills/iblai/government-agents/usaspending.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 582 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00582
Opus 5 $0.00015 $0.00291
Sonnet 5 $0.00006 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 11d ago against content hash 85220bb7005e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

usaspending 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.

skills/usaspending/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

USASpending.gov

What it is

USASpending.gov is the official open-data source for U.S. federal spending, operated by the Department of the Treasury. It provides public access to contract awards, grants, loans, and sub-award data reported by federal agencies under the DATA Act and FFATA. Procurement and budget agents use it for market research, price benchmarking, and spending transparency reporting.

When to use this skill

  • Researching prior government award history for a vendor or NAICS/PSC code during market research
  • Benchmarking prices by looking at historical award amounts for similar product/service categories
  • Generating budget transparency reports showing agency obligation and outlay data
  • Cross-checking agency internal obligation data against public disclosure records
  • Identifying competitive vs. sole-source award rates for a commodity area

Credentials

This skill authenticates using variables from the OpenClaw daemon env file ~/.openclaw/.env (template: .env.example). Required variables:

  • USASPENDING_API_BASE_URL - base URL for the API (default: https://api.usaspending.gov)

Note: USASpending.gov is a public API and does not require an API key for standard usage. No secret credentials are needed.

Key operations

  • POST /api/v2/search/spending_by_award/ — search awards by keyword, vendor, NAICS, PSC, agency, fiscal year, and award type
  • GET /api/v2/awards/{award_id}/ — retrieve full details for a specific award by internal award ID or PIID
  • POST /api/v2/references/recipients/ — look up recipient (vendor) details and award history by UEI or name
  • POST /api/v2/agency/{toptier_code}/budget_function/ — get agency spending by budget function and fiscal year
  • GET /api/v2/references/naics/ — retrieve NAICS code hierarchy for category filtering
  • POST /api/v2/download/awards/ — request a bulk download of award data matching filter criteria

Notes

  • No authentication is required; the API is fully public and rate-limited by IP.
  • Default rate limit: 100 requests/minute per IP; bulk download requests count separately.
  • Data in USASpending reflects reported obligations; there is typically a 30-90 day lag in sub-award reporting.
  • Always note the fiscal year scope when presenting spending figures; partial-year comparisons can be misleading.

Read the full file on GitHub · 38 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.

  1. 11d ago First seen · 38 lines · 29 tokens per session scan A 85220bb7005e

Subscribe to this mod's changes

usaspending is a skill published in the GitHub repository iblai/government-agents (10 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 582 once invoked, about $0.0001 per session on Opus 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.