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/djfksjd/ir-searchWrote 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/djfksjd/ir-search/ir-search)<a href="https://agentmods.dev/plugins/djfksjd/ir-search/ir-search"><img src="https://agentmods.dev/badge/plugins/djfksjd/ir-search/ir-search/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/djfksjd/ir-search/ir-search"><img src="https://agentmods.dev/badge/plugins/djfksjd/ir-search/ir-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ir-search 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 1mo 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "ir-search",
"version": "0.5.0",
"description": "한국 정부·공공기관 지원사업 전수조사 스킬 — K-Startup·기업마당·NIPA·KOCCA·SMTECH 공고를 크롤링해 프로젝트 프로필에 맞는 사업을 즉시/로드맵/변형 3분류하고 상세공고 원문으로 자격요건을 검증해 보고서를 만든다. 사용자가 '지원사업 찾아줘', '정부지원', '창업지원 사업', 'K-Startup/기업마당 조사' 등을 요청하면 이 스킬을 사용한다. 한국 지원사업 전용.",
"author": {
"name": "djfksjd",
"url": "https://github.com/djfksjd"
},
"homepage": "https://github.com/djfksjd/ir-search",
"repository": "https://github.com/djfksjd/ir-search",
"license": "MIT",
"keywords": [
"korea",
"government-grants",
"startup",
"crawler",
"claude-skill"
],
"skills": "./skills/",
"hooks": {
"SessionStart": [
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "python3 -c \"import curl_cffi\" 2>/dev/null || pip3 install 'curl_cffi>=0.15' >/dev/null 2>&1 || true"
}
]
}
]
}
}
What it installs
The manifest is a name and a version. 1 skill, 1 hook travel with it, and installing the plugin installs all of them — 0 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json 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.
- 1mo ago First seen · 35 lines scan A 03a56fd6de55
ir-search is a plugin published in the GitHub repository djfksjd/ir-search (393 stars, last pushed 2mo 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 2026-08-30.
Other plugins, from other repositories
sole-search
A Korea-only research tool for finding support programs for small businesses, including grants, vouchers, government-backed loans, guarantees, training, and consulting. It searches Korean government sources and checks eligibility against a shop profile.
0xarchive
Agent-ready 0xArchive market data skill for coding-agent clients across two venues: Hyperliquid and Lighter. Hyperliquid includes HIP-3 builder perps, HIP-4 outcome markets, and Hyperliquid Spot; Lighter has two deployments, mainnet and Robinhood Chain. Covers account positions by Hyperliquid wallet or Lighter account.
ghostswap-partners-api
Integrate the GhostSwap Partners API to add no-KYC crypto swaps (1,600+ coins, 0–4% partner fee, USDT payouts) into wallets, dApps, exchanges, payment flows, or affiliate sites. Covers Bearer auth, live quotes, idempotent swap creation, status polling, address validation, float and fixed-rate modes, error handling…
market-research-skills
A collection of workflows for market research, company analysis, investment research, fact checking, topic briefs, and searching a local Markdown knowledge base.
fn2 marketplace
FN2 AI research-agent integrations for terminal assistants.
fn2
Start, monitor, and schedule FN2 AI autonomous research agents for public markets from your terminal assistant.