crisis

crisis is a command for Claude Code from Ramsbaby/jarvis. It costs 60 tokens per session (812 once invoked), scanned A, original, MIT.

A crisis-response procedure for software incidents such as an outage, a stopped bot, a critical bug, or a changed external dependency. It is written in Korean.

In plain words
What is it for?
Use it to inspect service status and logs, create an incident report, stop or restart affected services, handle dependency changes, and prepare a monitored deployment.
Why use it?
It gives a structured way to identify the affected service, record evidence, isolate the problem, make backups, and check the fix during an urgent incident.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions CLAUDE.md; built for openclaw.

Install

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.

agentmods
npx agentmods add commands/ramsbaby/jarvis/crisis
Clone the repo
git clone --depth 1 https://github.com/Ramsbaby/jarvis

Made for: Claude Code.

Wrote 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.

agentmods badge for crisis

README.md
[![agentmods](https://agentmods.dev/badge/commands/ramsbaby/jarvis/crisis.svg)](https://agentmods.dev/commands/ramsbaby/jarvis/crisis)
Your own site
<a href="https://agentmods.dev/commands/ramsbaby/jarvis/crisis"><img src="https://agentmods.dev/badge/commands/ramsbaby/jarvis/crisis.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 812 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.00812
Opus 5 $0.00030 $0.00406
Sonnet 5 $0.00012 $0.00162
Haiku 4.5 $0.00006 $0.00081

Measured 6d ago against content hash 41e1f0fd8768, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

crisis 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 6d 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.

dotfiles/claude/commands/crisis.md · 96 lines

What it actually says

긴급 상황 대응 (Crisis Response)

서비스 중단/외부 의존성 변경/크리티컬 버그 등 긴급 상황 대응 프로세스를 시작합니다.

1단계: 상황 파악 (5분 내)

# 현재 시스템 상태 빠른 확인
openclaw status
launchctl list | grep ai.openclaw
tail -50 ~/.openclaw/logs/watchdog.log
tail -50 ~/.openclaw/logs/gateway.log

파악 항목:

  • 어떤 서비스가 영향받는가?
  • 언제부터 발생했는가?
  • 외부 의존성 변경인가 vs 내부 버그인가?
  • 유저 영향 범위는?

2단계: 리포트 작성 (에이전트 간 통신 패턴)

/tmp/crisis-report.md 파일로 상황 공유:

# Crisis Report - [날짜 시간]

## 상황
- 증상: ...
- 발생 시각: ...
- 영향 범위: ...

## 시도한 것
- [ ] 서비스 재시작
- [ ] 로그 확인
- [ ] ...

## 필요한 것
- 백엔드에서 필요한 정보: ...
- 예상 해결책: ...

3단계: 격리 & 즉시 대응

# 문제 서비스 격리
launchctl stop ai.openclaw.gateway

# 로그 상세 캡처
journalctl -u ai.openclaw 2>/dev/null || \
  cat ~/.openclaw/logs/*.log | tail -200 > /tmp/crisis-logs.txt

# 백업 (수정 전 필수)
cp -r ~/openclaw ~/openclaw.crisis-backup-$(date +%Y%m%d-%H%M%S)

4단계: 해결 체크리스트

외부 의존성 변경 시 (책: 콩콩프렌즈 사례 - 3일 내 해결)

  • 의존성 완전 제거 or 자체 구현 결정
  • 최소 동작 버전 먼저 구현 (MVP)
  • E2E 테스트로 검증
  • 배포 후 24시간 모니터링

내부 버그 시

  • 원인 코드 격리 (최소 재현 케이스)
  • .bak 백업 후 수정
  • /review 스킬로 코드 검토
  • 단계적 배포

Gateway/Watchdog 관련

  • openclaw doctor --fix 실행
  • openclaw daemon install --force (토큰 불일치 시)
  • launchd-guardian.sh 재시작 확인
  • Grace Period 30초 대기 후 재확인

5단계: 사후 처리

# 복구 확인
openclaw status
# Discord 알림 전송
~/.openclaw/scripts/alert.sh "crisis-resolved" "서비스 복구 완료: [원인] / [해결책]"

사후 문서화: CLAUDE.md 주요 변경사항 섹션 업데이트

참고

  • 자가복구 문서: ~/openclaw/docs/self-healing-system.md
  • 응급 복구: ~/openclaw/scripts/emergency-recovery.sh
  • 알림 스크립트: ~/.openclaw/scripts/alert.sh
Changes

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.

  1. 6d ago First seen · 96 lines · 60 tokens per session scan A 41e1f0fd8768

Subscribe to this mod's changes

crisis is a command published in the GitHub repository Ramsbaby/jarvis (16 stars, last pushed 13d ago), licensed MIT. It adds 60 tokens to every session and 812 once invoked, about $0.0003 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.