Observability plugins

Integration playbook for the @darkhunt-security/telemetry SDK — wires LLM tracing, generations, and spans into a Node/TypeScript service. Auto-invokes when you ask Claude to add Darkhunt telemetry / observability to a service.

1 skill

Operational skills for Splunk Platform, Splunk Cloud Platform, Splunk Enterprise, collectors, and data-source integrations.

87 skills

Observability suite — metrics: Prometheus, Grafana Mimir, and Grafana reference for agents querying metrics, writing PromQL, building and fixing dashboards, and reasoning about SLOs, KPIs, and burn-rate alerting, plus the community, air-gapped mimir-distributed Helm upgrade methodology (chart↔app co-pinned ladder, the classic-vs-ingest-storage/Kafka decision, the nginx→gateway rename that silently moves the proxy's DNS name, rollout-operator sequencing and abort levers, per-hop verification, and air-gap image/CRD/egress staging); and logs: the kube-logging logging-operator (16-CRD Fluent Bit→fluentd/syslog-ng pipeline, JSON/CRI parsing, routing, buffers, upgrade floor 6.7.0) plus rancher-logging-exit — the air-gap-first migration off Rancher's frozen bundled rancher-logging chart (CVE-2026-54680, release-secret cutover, CR compatibility); and hardware metrics: snmp-exporter — Prometheus snmp_exporter v0.30.x best practices (generator.yml module curation, the never-walk-a-whole-enterprise-subtree rule, SNMPv2c/v3 auth, timeout math, Kubernetes Probe/ScrapeConfig deployment, local docker testing, worked device references for Dell iDRAC 9/10, Cisco CBS/Catalyst, NVIDIA/Mellanox Onyx, Ubiquiti UniFi).

77 skills

Operational skills for Splunk Observability Cloud, Galileo, Lemonade, and telemetry integrations.

36 skills

Operational skills for AppDynamics platform administration, agents, monitoring, and integrations.

20 skills

Graylog MCP server: log search, distributed tracing, surrounding-context lookups, and composite incident analysis.

4 skills · 1 agent · 1 MCP server

Automatically trace Claude Code sessions to Orq. Captures sessions, turns, tool calls, and LLM responses as hierarchical OTLP spans.

A timeline pane of every tool call with duration, status and input summary.

A pane of every file read, edited or created in the session, with counts.

/session-stats shows a dashboard of turns, tools, tokens, cost, duration and files.

Chrome DevTools Network-tab-style waterfall visualizer for AI coding agent workflows — supports Claude Code, Codex CLI, and GitHub Copilot Chat

5 skills · 1 MCP server · hooks

Agent session telemetry for Claude Code — captures structured events from 14 hook lifecycle events with msgpack compression, optional encryption, and a real-time terminal dashboard.

1 skill · 1 command · hooks

Integration playbook for the darkhunt-telemetry Python SDK — wires LLM tracing, generations, and spans into a Python service. Auto-invokes when you ask Claude to add Darkhunt telemetry / observability to a Python service.

1 skill

Observability hook that appends one sanitized JSON line per tool call to a local log, with secret redaction and payload truncation.

hooks

Claude Code の hook 経由で圧縮プラグイン (rtk/headroom) の効きを観測・記録する計測機構。caveman は prompt mode で観測不可だが /token-report で transcript 推定値として併記

5 skills

Tsuga observability plugin: querying Tsuga data (TQL, aggregation bodies, PromQL, docs lookup) and running the `tsuga` CLI; investigation of incidents, service health, errors, latency and traces; configuration audits; building dashboards, monitors, SLOs, routing and other assets; getting telemetry in with OpenTelemetry SDKs, the Collector and OTTL; designing what to measure and how to verify it; and meta-skills for building and validating skill bundles.

10 skills

Observe and author Claude Code Workflow runs. Bundles an MCP server (list/inspect runs, read declared designs, draft workflows into the human's builder) and a /workflow-studio:dashboard command to open the visual dashboard.

1 skill · 1 command · 1 MCP server

Query audit logs, investigate incidents, and author ActivityPolicies using the Milo Activity service

7 skills · 2 agents

Query project logs, export metrics to Grafana Cloud, and read the status metrics Datum publishes for your resources

3 skills

Streams Claude Code session, tool-call and subagent activity to a Tracery Graph hub for live graph visualization.

1 skill · hooks

Datadog CLI skill for debugging and triaging with logs, metrics, and dashboards

1 skill

Langfuse observability - query traces, debug exceptions, analyze sessions, manage prompts and datasets via MCP tools. First LLM observability skill for Claude Code and Codex.

1 skill

Trace Codex sessions to Braintrust (session, turn, and tool spans).

hooks

Lower your Splunk, Datadog, Elastic, CloudWatch or ClickHouse log bill and keep every line. The 10x engine runs beside the log forwarder you already have and compacts, tiers down or offloads logs pattern by pattern; this plugin gives Claude the controls: what each pattern costs and where it goes. Log data never reaches log10x.

1 skill

Automatically trace Claude Code conversations to PromptLayer. Captures user messages, assistant responses, and tool calls as structured spans.

hooks

A fuel gauge above the prompt: context fill, tokens, dollars, dollars per hour, your plan's window, a sparkline of the last turns.

AX 2012 R3 performance advisor that correlates SQL Server, AOS, batch, and AX table evidence into explainable recommendations.

80 skills · 1 MCP server · app connector

Skills for managing Grepr jobs and pipelines, building grok parsers, querying log data, and debugging log reduction. Requires the Grepr CLI (npm install -g @grepr/cli).

29 skills

Instrument Python LLM applications with the neatlogs SDK — tracing, semantic spans, supported wrappers and framework integrations for OpenAI, Anthropic, LangChain, CrewAI, and more.

23 skills

Instrument TypeScript/Node.js LLM applications with the neatlogs SDK — semantic spans, supported wrappers and framework integrations for OpenAI, Anthropic, LangChain, Mastra, Vercel AI SDK, and more.

23 skills