ai-diagnostic

ai-diagnostic is a skill for Claude Code from modu-ai/moai-cowork. It costs 151 tokens per session (2,608 once invoked), scanned A, original, Apache-2.0.

A diagnostic framework that examines a problem across technology, processes, people, and business causes.

In plain words
What is it for?
Use it to investigate errors, slow performance, bottlenecks, process problems, system issues, and other complex troubleshooting cases.
Why use it?
It looks beyond visible symptoms to organize possible root causes and rank suggested actions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the moai-coworker plugin — 32 skills shipped together

Good fit Use it to investigate errors, slow performance, bottlenecks, process problems, system issues, and other complex troubleshooting cases.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/modu-ai/moai-cowork/ai-diagnostic
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.

Any agent
npx skills add modu-ai/moai-cowork --skill ai-diagnostic
Clone the repo
git clone --depth 1 https://github.com/modu-ai/moai-cowork

Made for: Claude Code.

Or install moai-coworker, the plugin that ships this one along with the rest of its 32 skills.

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 ai-diagnostic

README.md
[![agentmods](https://agentmods.dev/badge/skills/modu-ai/moai-cowork/ai-diagnostic/github.svg)](https://agentmods.dev/skills/modu-ai/moai-cowork/ai-diagnostic)
Your own site
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/ai-diagnostic"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/ai-diagnostic/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.

agentmods 80×15 button for ai-diagnostic

Your own site · 80×15
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/ai-diagnostic"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/ai-diagnostic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00151 $0.02608
Opus 5 $0.00076 $0.01304
Sonnet 5 $0.00030 $0.00522
Haiku 4.5 $0.00015 $0.00261

Measured 12d ago against content hash febd39a0976f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-diagnostic 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 12d 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.

plugins/moai-coworker/skills/ai-diagnostic/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ai-diagnostic

AI 기반 다차원 진단 분석 스킬입니다. Supervisor 패턴으로 기술, 프로세스, 사람, 비즈니스 4차원을 병렬 진단합니다.

개요

단순한 증상 기반 해결을 넘어 근본 원인(Root Cause)을 식별하기 위한 체계적인 진단 프레임워크를 제공합니다. 4개 차원(기술, 프로세스, 사람, 비즈니스)을 동시에 분석하고 결과를 통합하여 전체적인 진단 보고서를 생성합니다.

핵심 기능

  • 다차원 병렬 진단: 기술, 프로세스, 사람, 비즈니스 4차원 동시 분석
  • 근본 원인 식별: 5 Whys, Fishbone Diagram, Iceberg Model 기법 활용
  • 가설 기반 진단: 검증 가능한 가설 수립과 우선순위 부여
  • 실행 가능한 해결책: 우선순위별 Action Items과 ROI 추정

트리거 키워드

  • 진단, diagnostic, 문제 분석, 트러블슈팅, 원인 분석
  • 근본 원인, 시스템 진단, 현황 점검, 문제 해결
  • 성능 저하, 오류 원인, 병목 파악, 이슈 분석

워크플로우

1단계: 문제 수집

증상과 컨텍스트를 체계적으로 수집합니다:

  • 증상 파악: 오류 메시지, 성능 지표, 사용자 불만
  • 영향도 파악: 영향받는 사용자 수, 비즈니스 영향, 긴급성
  • 타임라인: 문제 발생 시점, 변화 추이, 패턴
  • 환경 정보: 시스템 사양, 구성, 최근 변경사항

2단계: 가설 생성

증상을 바탕으로 검증 가능한 가설을 생성합니다:

  • 차원별 가설: 기술, 프로세스, 사람, 비즈니스 차원별 가능성
  • 우선순위 부여: 발생 가능성과 영향도 기반 정렬
  • 검증 방법 수립: 각 가설을 검증할 방법론 정의

3단계: 병렬 진단

4개 차원을 병렬로 진단합니다:

차원 1: 기술 진단

  • 인프라: 서버, 네트워크, 데이터베이스, 서드파티 API
  • 코드: 버그, 성능 병목, 리소스 누수, 예외 처리
  • 아키텍처: 확장성, 가용성, 복잡도, 기술 부채
  • 보안: 취약점, 권한 관리, 데이터 보호

차원 2: 프로세스 진단

  • 워크플로우: 업무 프로세스, 승인 체계, 핸드오버
  • 자동화: 반복 작업 자동화 여부, CI/CD 파이프라인
  • 모니터링: 로그, 알림, 대응 절차
  • 문서화: Runbook, 장애 보고서, 지식 베이스

차원 3: 사람 진단

  • 역량: 기술 스택, 도메인 지식, 문제 해결 능력
  • 커뮤니케이션: 팀 협업, 정보 공유, 의사결정
  • 워크로드: 번아웃, 리소스 배분, 온콜 부담
  • 문화: 책임감, 학습 문화, 실패 허용

차원 4: 비즈니스 진단

  • KPI: 성과 지표, SLA, 목표 달성률
  • 비용: 인프라 비용, 개발 비용, 기회 비용
  • 고객: NPS, 이탈률, 불만 사항
  • 전략: 비즈니스 목표와 기술 목표 정렬성

4단계: 근본 원인 식별

다양한 기법을 활용하여 근본 원인을 도출합니다:

  • 5 Whys: "왜?"를 5번 반복하여 근본 원인 도달
  • Fishbone Diagram: 원인을 카테고리별로 분류 (Man, Machine, Material, Method, Environment)
  • Iceberg Model: 수면 아래 잠재적 원인 탐색

5단계: 해결책 제안

근본 원인별 실행 가능한 해결책을 제시합니다:

  • 단기 조치: 즉시 실행 가능한 완화 조치 (24-72시간)
  • 중기 해결: 근본 원인 해결을 위한 구조적 개선 (1-4주)
  • 장기 예방: 재발 방지를 위한 시스템적 개선 (1-3개월)
  • 우선순위: ROI (투자 대비 효과)와 긴급성 기반 정렬

사용 예시

예시 1: 웹 서비스 응답 시간 저하 진단

증상:
- 지난 2주간 API 평균 응답 시간 200ms → 800ms로 악화
- 오후 2시~4시에 심각 (최대 3초)
- 사용자 불만 50건/일 접수

컨텍스트:
- 2주 전 신규 기능 배포 (검색 엔진 변경)
- AWS, RDS MySQL 사용
- 온콜 엔지니어 1명, 번아웃 위험

Read the full file on GitHub · 200 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 200 lines · 151 tokens per session scan A febd39a0976f

Subscribe to this mod's changes

ai-diagnostic is a skill published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 9d ago), licensed Apache-2.0. It adds 151 tokens to every session and 2,608 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

ci-log-interpretation

Use this skill when reading or analyzing CI logs from a Shopware GitHub Actions workflow to figure out why a build failed — phrases like "why did CI fail", "what broke the build", "check the pipeline", "interpret these logs", "debug this red build" — or whenever raw run logs, job logs, or check annotations from a…

shopwareLabs/ai-coding-tools · 154 tokens

debug

Analyze errors and apply fixes. Use when you have an error message, traceback, or failing log to diagnose.

This-HW/claude-code-kit · 24 tokens

github-actions-silent-failures

Diagnose GitHub Actions workflows that fail silently — a reusable-workflow run that shows zero jobs and no logs (startupfailure), a gh-aw cross-repo import that mis-resolves when the source repo is literally named .github, and self-hosted-runner traps (a shared-tmp race across containers, docker exec landing as an…

dryvist/claude-code-plugins · 113 tokens

troubleshoot-worktree

Troubleshoot git worktree, branch, and refname issues.

dryvist/claude-code-plugins · 19 tokens

debugging

The scientific debugging loop — reproduce first, pull the real event from the repo's observability stack, one hypothesis → one change → one observation, revert failed attempts, escalate instead of thrash. INVOKE PROACTIVELY when diagnosing any bug, error, stack trace, failing or flaky test, crash, regression, or…

PrabhdeepSingh/claude-plugins · 100 tokens

bug-finder

Hunt for one real, previously unreported defect and file it as a well-evidenced ticket — proactive discovery, not reactive diagnosis. INVOKE when asked to sweep code for bugs or hunt risky areas, and when /sonu:factory runs a bug-hunt pass. A known symptom is [[debugging]]; a pending diff is [[self-review]]. It files…

PrabhdeepSingh/claude-plugins · 94 tokens