Observe Metrics
- 644 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
observe-metrics is a ruflo Claude skill that aggregates counters, gauges, and histograms with anomaly detection for developers who monitor live multi-agent swarm health and token consumption.
About
observe-metrics is an observability skill in ruvnet/ruflo that pulls metrics from the observability namespace via claude-flow MCP tools including memory_search, memory_store, and agentdb_pattern-search. It accepts an optional --period argument such as 1h and aggregates counters, gauges, and histograms while flagging anomalies. Developers use it for snapshots of task completion rates, error rates, active agent counts, memory usage, and token consumption when monitoring swarm performance during live operation.
- Real-time metric observation for running agents
- Structured logging of performance signals
- Automatic surfacing of anomalies and trends
- Compatible with Claude Code, Cursor, and custom agent loops
- Reduces blind spots in long-running autonomous workflows
Observe Metrics by the numbers
- 644 all-time installs (skills.sh)
- +6 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #1,519 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill observe-metricsAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 644 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you monitor multi-agent swarm performance metrics?
Let their agents automatically track, log, and surface key performance signals during live operation.
Who is it for?
Developers running ruflo or claude-flow agent swarms who need periodic health snapshots with anomaly detection.
Skip if: Single-request debugging of one task's tool-call sequence—use observe-trace instead.
When should I use this skill?
The user asks for system health, swarm metrics, error rates, or token consumption over a time period.
What you get
Aggregated metric snapshot with anomaly flags for completion rates, errors, agent counts, memory, and tokens.
- Metric aggregation report
- Anomaly flags
- Time-period health snapshot
By the numbers
- Tracks counters, gauges, and histograms as three metric types
Files
Observe Metrics
Aggregate counters, gauges, and histograms from the observability namespace and flag anomalies.
When to use
When you need a snapshot of system health -- task completion rates, error rates, active agent counts, memory usage, and token consumption. Useful for monitoring swarm performance and detecting degradation.
Steps
1. Retrieve metrics -- call mcp__claude-flow__memory_search --namespace observability (or memory_list) to fetch metric records for the specified period (default: 1 hour). The memory_* tool family routes by namespace; agentdb_hierarchical-* does NOT, so use memory_* here. 2. Aggregate -- compute:
- Counters: sum totals (tasks_completed, errors, token_usage)
- Gauges: current values (active_agents, memory_usage_bytes)
- Histograms: p50, p95, p99 (task_duration_ms, span_duration_ms)
3. Compute baselines -- call mcp__claude-flow__agentdb_pattern-search (ReasoningBank-routed; don't pass a namespace argument — pattern- tools ignore it) to establish baseline values for each metric. 4. Flag anomalies -- mark metrics deviating >2 standard deviations from baseline with direction (above/below) and severity 5. Store patterns* -- two paths (per ruflo-cost-tracker ADR-0001 dual-path pattern):
- Pattern store (typed, recommended):
mcp__claude-flow__agentdb_pattern-storewithtype: 'metric-snapshot'. No namespace arg. - Plain store (namespace-routable):
mcp__claude-flow__memory_store --namespace observabilityfor the snapshot tied to a timestamp.
6. Report -- display: metric name, current value, baseline, deviation, trend (up/down/stable), anomaly flag; overall health score (green/yellow/red)
CLI alternative
npx @claude-flow/cli@latest memory search --query "system metrics for last hour" --namespace observabilityRelated skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What metrics does observe-metrics collect?
observe-metrics aggregates counters, gauges, and histograms covering task completion rates, error rates, active agent counts, memory usage, and token consumption from the claude-flow observability namespace.
How do you set the observation time window?
observe-metrics accepts an optional --period argument such as 1h to scope aggregation and anomaly detection to a specific time range before displaying the health snapshot.