Borrowing it
Nothing to install: this file belongs to kangraemin/claude-inspector. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kangraemin/claude-inspector/main/.claude/skills/e2e/SKILL.mdgit clone --depth 1 https://github.com/kangraemin/claude-inspectorWrote 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/skills/kangraemin/claude-inspector/e2e)<a href="https://agentmods.dev/skills/kangraemin/claude-inspector/e2e"><img src="https://agentmods.dev/badge/skills/kangraemin/claude-inspector/e2e/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/skills/kangraemin/claude-inspector/e2e"><img src="https://agentmods.dev/badge/skills/kangraemin/claude-inspector/e2e.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.00938 |
| Opus 5 | $0.00012 | $0.00469 |
| Sonnet 5 | $0.00005 | $0.00188 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
e2e 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 9d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Inspector 테스트 실행
Unit tests (파싱 로직)
npm run test:unit
parseClaudeMdSections— CLAUDE.md system-reminder 섹션 파싱parseUserText— 사용자 메시지 내 injected block 감지detectMechanisms— 5가지 메커니즘 감지 로직
E2E tests (Electron UI)
npm run test:e2e
# headed 모드 (브라우저 보이게)
npm run test:e2e -- --headed
# 특정 테스트만
npm run test:e2e -- --grep "탭 클릭"
# 디버그 모드 (step-by-step)
npm run test:e2e -- --debug
- 앱이 실행 중이면 먼저 종료:
pkill -x "Electron"
전체 실행
npm test
현재 상태
- 브랜치: !
git branch --show-current - 변경 파일: !
git diff --name-only HEAD 2>/dev/null | head -10
Playwright 핵심 패턴
셀렉터 우선순위
// ✅ 권장: role, label, data-testid 순
page.getByRole('button', { name: '프록시 시작' })
page.getByLabel('API Key')
page.locator('[data-testid="proxy-toggle"]')
page.locator('[data-m="claude-md"]') // 이 프로젝트 convention
// ❌ 금지: CSS 클래스, nth-child
page.locator('.btn.active')
page.locator('div > span:nth-child(2)')
대기 전략
// ❌ 금지: 고정 타임아웃
await page.waitForTimeout(3000);
// ✅ 권장: 상태/요소 기반
await page.waitForLoadState('domcontentloaded');
await expect(page.locator('[data-m="claude-md"]')).toHaveClass(/active/);
await expect(page.getByText('Copied!')).toBeVisible();
Page Object Model (복잡한 테스트에서 활용)
// tests/e2e/pages/MechanismPage.ts
export class MechanismPage {
constructor(private page: Page) {}
tab(name: string) {
return this.page.locator(`[data-m="${name}"]`);
}
async switchTo(name: string) {
await this.tab(name).click();
await expect(this.tab(name)).toHaveClass(/active/);
}
}
네트워크/IPC 모킹 (프록시 테스트)
// Anthropic API 응답 모킹
await page.route('**/api.anthropic.com/**', route => {
route.fulfill({
status: 200,
contentType: 'application/json',
body: JSON.stringify({ id: 'msg_test', content: [{ type: 'text', text: 'ok' }] }),
});
});
실패 시 트레이스 수집
// playwright.config.ts에 추가
use: {
trace: 'on-first-retry',
screenshot: 'only-on-failure',
video: 'retain-on-failure',
}
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.
- 9d ago First seen · 129 lines · 24 tokens per session scan A 3e50fdfb0607
e2e is a skill published in the GitHub repository kangraemin/claude-inspector (131 stars, last pushed 8d ago), licensed MIT. It adds 24 tokens to every session and 938 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 2026-08-30.
Other skills, from other repositories
refactor-ops
Safe refactoring patterns - extract, rename, restructure with test-driven methodology and dead code detection. Use for: refactor, refactoring, extract function, extract component, rename, move file, restructure, dead code, unused imports, code smell, duplicate code, long function, god object, feature envy, DRY…
backpropagation
Trace runtime bugs back to spec gaps — identify missing acceptance criteria, update specs, generate regression tests, and detect patterns.
pair-programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.