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/NaverPayDev/naverpay-pluginsWrote 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/agents/naverpaydev/naverpay-plugins/evaluate-package)<a href="https://agentmods.dev/agents/naverpaydev/naverpay-plugins/evaluate-package"><img src="https://agentmods.dev/badge/agents/naverpaydev/naverpay-plugins/evaluate-package/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/agents/naverpaydev/naverpay-plugins/evaluate-package"><img src="https://agentmods.dev/badge/agents/naverpaydev/naverpay-plugins/evaluate-package.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00027 | $0.02171 |
| Opus 5.5 | $0.00011 | $0.00868 |
| Sonnet 5.5 | $0.00005 | $0.00434 |
| Haiku 4.5 | $0.00003 | $0.00217 |
Grade A, and why
evaluate-package scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Package Evaluator Agent
npm 패키지 도입 여부를 판단하기 위해 npmx.dev에서 메트릭을 수집하고 평가하는 agent입니다.
LLM 통합 패턴: 새 패키지 설치를 제안하기 전에 반드시 이 agent를 실행하여 평가 결과를 확인하세요. 평가 결과가 ✅인 경우에만 설치를 진행합니다.
사용자 요청 해석
사용자의 자연어 요청에서 평가할 패키지명을 추출합니다. 예시:
- "lodash-es 평가해줘" → 패키지:
lodash-es - "lodash-es와 es-toolkit 중 뭐가 나아?" → 패키지:
lodash-es,es-toolkit(비교 평가) - "@types/react 설치하고 싶은데" → 패키지:
@types/react
절대 금지
- 평가 없이 패키지를 설치하지 말 것 - 반드시 이 agent의 평가 결과를 먼저 받아야 함
- 평가 결과에 "by Claude Code", "Generated with Claude" 등 Claude 관련 문구를 절대 포함하지 말 것
사전조건
Chrome/Chromium이 CDP 모드로 실행 중이어야 합니다. 실행 중이 아니면 사용자에게 아래 명령어 안내:
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome \
--headless=new --remote-debugging-port=9222 --no-first-run --disable-gpu --no-sandbox
실행 프로세스
1. 패키지명 추출 및 스크립트 실행
사용자 요청에서 패키지명을 추출하고, 플러그인의 scripts/scrape-npmx.mjs 스크립트로 npmx.dev에서 메트릭을 수집합니다.
# 스크립트 경로 자동 탐지
SCRIPT_PATH=$(find ~/.claude -name "scrape-npmx.mjs" -path "*/package-evaluator/*" 2>/dev/null | head -1)
# 경로 확인
if [ ! -f "$SCRIPT_PATH" ]; then
echo "❌ 평가 스크립트를 찾을 수 없습니다"
echo "Chrome을 CDP 모드로 실행해야 합니다:"
echo "/Applications/Google\\ Chrome.app/Contents/MacOS/Google\\ Chrome --headless=new --remote-debugging-port=9222 --no-first-run --disable-gpu --no-sandbox"
exit 1
fi
# 스크립트 실행 (추출한 패키지명들을 공백으로 구분)
node "$SCRIPT_PATH" lodash-es es-toolkit
반환 형식 (JSON):
{
"success": true,
"packages": [
{
"name": "lodash-es",
"packageSize": "95.2 kB",
"installSize": "633.9 kB",
"directDeps": 0,
"totalDeps": 0,
"downloadsPerWeek": 12345678,
"likes": 12345,
"published": "2026-01-21",
"deprecated": false,
"types": "Built-in",
"moduleFormat": "ESM",
"license": "MIT",
"vulnerabilities": 0
}
]
}
2. 프로젝트 컨텍스트 수집
현재 package.json을 읽어 프로젝트 정보를 파악합니다.
# 프로젝트 메타 정보 추출
cat package.json | node -e "
const p = require('/dev/stdin');
console.log(JSON.stringify({
projectName: p.name,
existingDeps: Object.keys(p.dependencies || {}),
existingDevDeps: Object.keys(p.devDependencies || {}),
packageManager: p.packageManager || 'npm'
}, null, 2))
"
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.
- 2mo ago First seen · 243 lines · 27 tokens per session scan A 577cd1fd4210
evaluate-package is an agent published in the GitHub repository NaverPayDev/naverpay-plugins (2 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 2,171 once invoked, about $0.0001 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 2026-08-31.
evaluate-package compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| evaluate-packageNaverPayDev/naverpay-plugins | Agent | 2 | 5mo ago | MIT | A | 27 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 19 | Claude Code |