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/ogasurfproject-jpg/horizon-shieldWrote 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/ogasurfproject-jpg/horizon-shield/plugin)<a href="https://agentmods.dev/plugins/ogasurfproject-jpg/horizon-shield/plugin"><img src="https://agentmods.dev/badge/plugins/ogasurfproject-jpg/horizon-shield/plugin/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/ogasurfproject-jpg/horizon-shield/plugin"><img src="https://agentmods.dev/badge/plugins/ogasurfproject-jpg/horizon-shield/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
horizon-shield 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 13d 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": "horizon-shield",
"displayName": "HORIZON SHIELD",
"version": "1.2.2",
"description": "Check Japanese construction and renovation estimates against the open JCCDB dataset (526,128 records) and get Bitcoin-anchored, recomputable fair-price receipts; find contractors that passed the independent fair-price check (YAKUMO); public construction-cost data for Japan and the U.S. (JCCDB, USCCDB) from a separate read-only server. No API key. Two tools append a public ledger record; the rest read.",
"author": {
"name": "Toshikatsu Oga",
"email": "[email protected]",
"url": "https://shield.the-horizons-innovation.com"
},
"homepage": "https://shield.the-horizons-innovation.com",
"repository": "https://github.com/ogasurfproject-jpg/horizon-shield",
"license": "MIT",
"icon": "./icon.png",
"privacyPolicyUrl": "https://shield.the-horizons-innovation.com/privacy",
"keywords": [
"mcp",
"construction",
"estimate",
"audit",
"japan",
"fair-price",
"verifiable",
"renovation",
"contractor",
"open-data"
]
}
What it installs
The manifest is a name and a version. 2 skills, 3 commands, 3 MCP servers travel with it, and installing the plugin installs all of them — 285 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 13d ago Changed c78680f768db
- 15d ago Changed f469fce363ac
- 17d ago Changed · +2 lines 7a03836e8ee4
- 20d ago Changed · +11 lines 67a2243e0747
- 1mo ago First seen · 16 lines scan A 7a7b0b3f0df5
horizon-shield is a plugin published in the GitHub repository ogasurfproject-jpg/horizon-shield (2 stars, last pushed yesterday), 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 2026-08-31.
Other plugins, from other repositories
x402-list
Discover and vet x402 payment services before your agent pays one: uptime, price, and on-chain-verified settlement volume, from Gemini CLI.
0xarchive
Hyperliquid and Lighter market data through 0xArchive's hosted MCP server.
0xarchive
Hyperliquid and Lighter market data through 0xArchive's hosted MCP server.
xrocket-exchange
Inspect xRocket markets and trade locally inside one operator-set daily limit.
hive-sdk
Evidence-backed crypto due diligence with sources, freshness, and runtime receipts.
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data via MCP. STDIO or Streamable HTTP.