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.
git clone --depth 1 https://github.com/PolicyEngine/policyengine-claudeWrote 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/plugins/policyengine/policyengine-claude/country-models)<a href="https://agentmods.dev/plugins/policyengine/policyengine-claude/country-models"><img src="https://agentmods.dev/badge/plugins/policyengine/policyengine-claude/country-models/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/plugins/policyengine/policyengine-claude/country-models"><img src="https://agentmods.dev/badge/plugins/policyengine/policyengine-claude/country-models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
country-models 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 3d 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.
What it actually says
{
"name": "country-models",
"description": "Complete multi-agent workflow for implementing government benefit programs in PolicyEngine country packages",
"category": "development",
"version": "4.0.1",
"keywords": [
"tax",
"benefits",
"microsimulation",
"country-models",
"rules",
"testing"
],
"author": {
"name": "PolicyEngine",
"url": "https://github.com/PolicyEngine"
},
"license": "MIT",
"skills": [
"./skills/policyengine-user-guide",
"./skills/policyengine-us",
"./skills/policyengine-uk",
"./skills/policyengine-healthcare",
"./skills/policyengine-model-development",
"./skills/policyengine-data",
"./skills/policyengine-standards",
"./skills/policyengine-writing",
"./skills/encode-policy-v2",
"./skills/review-program",
"./skills/fix-pr"
],
"commands": [
"./commands/backdate-program.md",
"./commands/encode-reform.md",
"./commands/create-pr.md",
"./commands/write-tests.md"
],
"agents": [
"./agents/country-models/ci-fixer.md",
"./agents/country-models/document-collector.md",
"./agents/country-models/edge-case-generator.md",
"./agents/country-models/implementation-validator.md",
"./agents/country-models/issue-manager.md",
"./agents/country-models/model-worker.md",
"./agents/country-models/pr-pusher.md",
"./agents/country-models/program-reviewer.md",
"./agents/country-models/review-worker.md",
"./agents/country-models/rules-engineer.md",
"./agents/country-models/structural-implementer.md",
"./agents/country-models/test-creator.md",
"./agents/reference-validator.md"
],
"source": "./"
}What it installs
The manifest is a name and a version. 11 skills travel with it, and installing the plugin installs all of them — 1,782 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill policyengine-writing A 147 tokens
- Skill policyengine-data A 253 tokens
- Skill policyengine-us A 251 tokens
- Skill policyengine-standards A 144 tokens
- Skill policyengine-uk A 241 tokens
- Skill policyengine-healthcare A 246 tokens
- Skill policyengine-model-development A 215 tokens
- Skill encode-policy-v2 A 75 tokens
- Skill review-program A 61 tokens
- Skill fix-pr A 46 tokens
- Skill policyengine-user-guide A 103 tokens
What ships with it
1 file beside marketplace.json#country-models in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed · -1 lines f22b15debe85
- 6d ago First seen · 55 lines scan A dfe8e7c94b81
country-models is a plugin published in the GitHub repository PolicyEngine/policyengine-claude (32 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data through MCP. STDIO & Streamable HTTP.
datarails-financeos
Datarails Finance OS integration - analyze financial data, detect anomalies, and generate insights.
financial-evidence
Read-only evidence for money markets, capital markets, China economy, bank risk, and market liquidity across LiquiLens, Undertow, Seiche, and Palimpsest.
lendwise
Unified view for lending markets, one standard. Compare and optimize DeFi supply/borrow across Aave, Morpho and Compound. Read-only; it never signs a transaction.
headless
Headless browser automation for site comparison, E2E testing, and anti-bot-aware web research.
claude-md-management
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.