AIOps Manager — Development agent for Claude Code
Owns AIOps — anomaly detection and correlation over observability telemetry, alert-noise reduction (grouping, dedup, inhibit), and safe auto-remediation with blast-radius ceilings and circuit breakers.
How to install AIOps Manager
Installs to ~/.claude/agents/vidhya101-k8s-ai-operator-aiops-manager.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/vidhya101/k8s-ai-operator/HEAD/.claude/agents/aiops-manager.md -o ~/.claude/agents/vidhya101-k8s-ai-operator-aiops-manager.md Restart Claude Code, or start a new session, for it to be picked up.
What AIOps Manager does
name: aiops-manager description: Owns AIOps — anomaly detection and correlation over observability telemetry, alert-noise reduction (grouping, dedup, inhibit), and safe auto-remediation with blast-radius ceilings and circuit breakers. NOT a replacement for good SRE fundamentals — AIOps sits ON TOP of a working SLI/SLO/alerting foundation. Trigger on "our alerts are too noisy", "add anomaly detection for X", "should we auto-remediate Y", "correlate alerts across systems".
Context:Alternatives in Development
- Correlator — Finding correlation engine 812 ★
- General Code Quality Debugger — Use this agent proactively when you need systematic code review, debugging assistance, refactoring guidance, o 248 ★
- Clawmem Curator — Maintains ClawMem memory health — lifecycle triage (pin/snooze/forget), retrieval health checks, dedup sweeps 201 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Infra Telemetry
Observability and IR specialist. SIEM (Wazuh-class) management, agent enrollment, alert triage, telemetry corr
Sstack Dependency Failure Attacker
Dependency failure lens attacker. Attacks every mapped surface for upstream timeouts, network partitions, circ
Media Librarian
Autonomous media library cataloger and organiser. Use when the user wants hands-off processing of a mixed medi
Sstack Resource Exhaustion Attacker
Resource-exhaustion lens attacker. Attacks every mapped surface for connection pool exhaustion, rate limits, m
Performance Critic
Performance Critic — مُراجع الأداء وجودة الكود المستقل في بوابة الإجماع (البند 7)، يستخدمه /consensus-gate لفح
Osint Linker
The Linker, the pattern recognition specialist. Entity resolution and cross-platform correlation that surfaces
Related Skills
Llmix
Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with
Health Audit
Maintainer-only autonomous health audit + auto-heal loop. Runs N=3 fresh-team audit-fix-audit cycles with circ
Errors
Establish error handling patterns and resilience strategy — classification, retries, timeouts, circuit breaker