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 agentmods add commands/ramsbaby/jarvis/crisisgit clone --depth 1 https://github.com/Ramsbaby/jarvisWrote 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/commands/ramsbaby/jarvis/crisis)<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>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 | $0.00060 | $0.00812 |
| Opus 5 | $0.00030 | $0.00406 |
| Sonnet 5 | $0.00012 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
crisis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
긴급 상황 대응 (Crisis Response)
서비스 중단/외부 의존성 변경/크리티컬 버그 등 긴급 상황 대응 프로세스를 시작합니다.
1단계: 상황 파악 (5분 내)
# 현재 시스템 상태 빠른 확인
openclaw status
launchctl list | grep ai.openclaw
tail -50 ~/.openclaw/logs/watchdog.log
tail -50 ~/.openclaw/logs/gateway.log
파악 항목:
- 어떤 서비스가 영향받는가?
- 언제부터 발생했는가?
- 외부 의존성 변경인가 vs 내부 버그인가?
- 유저 영향 범위는?
2단계: 리포트 작성 (에이전트 간 통신 패턴)
/tmp/crisis-report.md 파일로 상황 공유:
# Crisis Report - [날짜 시간]
## 상황
- 증상: ...
- 발생 시각: ...
- 영향 범위: ...
## 시도한 것
- [ ] 서비스 재시작
- [ ] 로그 확인
- [ ] ...
## 필요한 것
- 백엔드에서 필요한 정보: ...
- 예상 해결책: ...
3단계: 격리 & 즉시 대응
# 문제 서비스 격리
launchctl stop ai.openclaw.gateway
# 로그 상세 캡처
journalctl -u ai.openclaw 2>/dev/null || \
cat ~/.openclaw/logs/*.log | tail -200 > /tmp/crisis-logs.txt
# 백업 (수정 전 필수)
cp -r ~/openclaw ~/openclaw.crisis-backup-$(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)
-
.bak백업 후 수정 -
/review스킬로 코드 검토 - 단계적 배포
Gateway/Watchdog 관련
-
openclaw doctor --fix실행 -
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
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.
- 6d ago First seen · 96 lines · 60 tokens per session scan A 41e1f0fd8768
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 $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
bm-doctor
Diagnose and recover basemind when it isn't working (MCP tools missing/erroring, "no index", dead server) — runs CLI checks and gives the client-specific way to reconnect the server.
step-research
Always research before proposing a fix. The Untether bug you're chasing is often a known upstream engine quirk, a previously-fixed regression, or a documented config gotcha.
iterate-feature
Iterate on the feature "$ARGUMENTS" to fix issues and address feedback.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
fix
Universal debugging and fix application with semantic code analysis.