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.
npx skills add humanerd-drew/opencode-drewgent --skill n8n-self-hosted-diagnosticsgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/n8n-self-hosted-diagnostics)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/n8n-self-hosted-diagnostics"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/n8n-self-hosted-diagnostics.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01559 |
| Opus 5 | $0.00000 | $0.00779 |
| Sonnet 5 | $0.00000 | $0.00312 |
| Haiku 4.5 | $0.00000 | $0.00156 |
Grade B, and why
n8n-self-hosted-diagnostics scanned grade B with 2 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 7d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
**확인**: `curl -X POST -H 'Content-Type: application/json' -d '{"content":"test"}' <webhook_url>` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w "%{http_code}" http://localhost:5678 How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
title: n8n Self-Hosted Diagnostics name: n8n-self-hosted-diagnostics description: npm으로 설치된 n8n 셀프호스트 상태 진단 + launchd 관리 스킬 type: skill space: outcome tags: [skill, n8n, self-hosted, diagnostics] created: 2026-06-01 updated: 2026-06-01 links:
- "[[@action/skills/SKILL-INDEX]]"
- "[[skills/automation/DESCRIPTION]]"
- "[[@identity/brain/rules]]"---
n8n Self-Hosted Diagnostics
npm으로 설치된 n8n 셀프호스트의 상태를 진단하고 launchd로 관리하는 스킬.
환경 (2026-06-01 기준)
- 설치: npm global (
/opt/homebrew/lib/node_modules/n8n) - 실행 경로:
/opt/homebrew/bin/n8n→ symlink to npm package - 데이터 경로:
~/.n8n/ - DB:
~/.n8n/database.sqlite(SQLite) - 설정:
~/.n8n/config(JSON — encryptionKey 포함) - 포트: 5678
- launchd plist:
~/Library/LaunchAgents/ai.{{AGENT_NAME_LOWER}}.n8n.plist - 로그:
~/P6-prefrontal/logs/n8n.log,n8n.error.log - launchd label:
ai.{{AGENT_NAME_LOWER}}.n8n - 업데이트:
npm update -g n8n(Homebrew formula 없음)
launchd 관리
# 상태 확인
launchctl list | grep n8n
# 수동 시작
launchctl start ai.{{AGENT_NAME_LOWER}}.n8n
# 수동 정지
launchctl stop ai.{{AGENT_NAME_LOWER}}.n8n
# 재시작
launchctl stop ai.{{AGENT_NAME_LOWER}}.n8n && sleep 2 && launchctl start ai.{{AGENT_NAME_LOWER}}.n8n
# plist reload
launchctl unload ~/Library/LaunchAgents/ai.{{AGENT_NAME_LOWER}}.n8n.plist
launchctl load ~/Library/LaunchAgents/ai.{{AGENT_NAME_LOWER}}.n8n.plist
재부팅 시 RunAtLoad: true로 자동 시작됩니다.
진단 체크리스트
# 1. launchd 상태
launchctl list | grep n8n
# 2. 프로세스 확인
ps aux | grep n8n | grep -v grep
# 3. 포트 LISTEN 확인
lsof -i :5678
# 4. HTTP 응답 확인
curl -s -o /dev/null -w "%{http_code}" http://localhost:5678
# 5. 데이터 디렉토리
ls -la ~/.n8n/
# 6. 로그 확인
tail -20 ~/P6-prefrontal/logs/n8n.log
tail -20 ~/P6-prefrontal/logs/n8n.error.log
계정 복구 — SQLite 직접 초기화 (bcrypt 해시 교체)
n8n은 bcrypt 해시 사용. UI "Forgot my password"가 작동하지 않는 경우 SQLite에서 직접 bcrypt 해시를 교체.
핵심: bcrypt 해시 — $2b$ vs $2a$
최신 n8n (2025~2026)은 $2b$ prefix도 인식함.
import bcrypt, sqlite3, os
DB = os.path.expanduser('~/.n8n/database.sqlite')
new_password = '새비밀번호'
# bcrypt 해시 생성
salt = bcrypt.gensalt(rounds=10)
hashed_str = bcrypt.hashpw(new_password.encode(), salt).decode()
# 유저 확인
conn = sqlite3.connect(DB)
cur = conn.execute('SELECT id, email FROM "user"')
for row in cur.fetchall():
print(row)
# 비밀번호 업데이트
conn.execute('UPDATE "user" SET password = ? WHERE email = ?', (hashed_str, '대상@이메일.com'))
conn.commit()
# 검증
row = conn.execute('SELECT password FROM "user" WHERE email = ?', ('대상@이메일.com',)).fetchone()
print(f'해시 검증: {bcrypt.checkpw(new_password.encode(), row[0].encode())}')
conn.close()
print('완료 — http://localhost:5678 에서 로그인 시도')
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.
- 7d ago First seen · 173 lines · 0 tokens per session scan B 9b5b57832347
n8n-self-hosted-diagnostics is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,559 tokens. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.