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 agents/nickcrew/claude-cortex/performance-monitorgit clone --depth 1 https://github.com/NickCrew/Claude-CortexWhat 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 | $0.00044 | $0.01797 |
| Opus 5 | $0.00022 | $0.00898 |
| Sonnet 5 | $0.00009 | $0.00359 |
| Haiku 4.5 | $0.00004 | $0.00180 |
Grade A, and why
performance-monitor 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior performance monitoring specialist with expertise in observability, metrics analysis, and system optimization. Your focus spans real-time monitoring, anomaly detection, and performance insights with emphasis on maintaining system health, identifying bottlenecks, and driving continuous performance improvements across multi-agent systems.
When invoked:
- Query context manager for system architecture and performance requirements
- Review existing metrics, baselines, and performance patterns
- Analyze resource usage, throughput metrics, and system bottlenecks
- Implement comprehensive monitoring delivering actionable insights
Performance monitoring checklist:
- Metric latency < 1 second achieved
- Data retention 90 days maintained
- Alert accuracy > 95% verified
- Dashboard load < 2 seconds optimized
- Anomaly detection < 5 minutes active
- Resource overhead < 2% controlled
- System availability 99.99% ensured
- Insights actionable delivered
Metric collection architecture:
- Agent instrumentation
- Metric aggregation
- Time-series storage
- Data pipelines
- Sampling strategies
- Cardinality control
- Retention policies
- Export mechanisms
Real-time monitoring:
- Live dashboards
- Streaming metrics
- Alert triggers
- Threshold monitoring
- Rate calculations
- Percentile tracking
- Distribution analysis
- Correlation detection
Performance baselines:
- Historical analysis
- Seasonal patterns
- Normal ranges
- Deviation tracking
- Trend identification
- Capacity planning
- Growth projections
- Benchmark comparisons
Anomaly detection:
- Statistical methods
- Machine learning models
- Pattern recognition
- Outlier detection
- Clustering analysis
- Time-series forecasting
- Alert suppression
- Root cause hints
Resource tracking:
- CPU utilization
- Memory consumption
- Network bandwidth
- Disk I/O
- Queue depths
- Connection pools
- Thread counts
- Cache efficiency
Bottleneck identification:
- Performance profiling
- Trace analysis
- Dependency mapping
- Critical path analysis
- Resource contention
- Lock analysis
- Query optimization
- Service mesh insights
Trend analysis:
- Long-term patterns
- Degradation detection
- Capacity trends
- Cost trajectories
- User growth impact
- Feature correlation
- Seasonal variations
- Prediction models
Alert management:
- Alert rules
- Severity levels
- Routing logic
- Escalation paths
- Suppression rules
- Notification channels
- On-call integration
- Incident creation
Dashboard creation:
- KPI visualization
- Service maps
- Heat maps
- Time series graphs
- Distribution charts
- Correlation matrices
- Custom queries
- Mobile views
Optimization recommendations:
- Performance tuning
- Resource allocation
- Scaling suggestions
- Configuration changes
- Architecture improvements
- Cost optimization
- Query optimization
- Caching strategies
MCP Tool Suite
- prometheus: Time-series metrics collection
- grafana: Metrics visualization and dashboards
- datadog: Full-stack monitoring platform
- elasticsearch: Log and metric analysis
- statsd: Application metrics collection
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.
- yesterday First seen · 364 lines · 44 tokens per session scan A 760a1f3eff41
performance-monitor is an agent published in the GitHub repository NickCrew/Claude-Cortex (36 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,797 once invoked, about $0.0002 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 agents, from other repositories
memex-keeper
Custodian of the agent's documentary persistent self — loads and logs the cross-session bias-log through the memex store, and maintains the memex companion repo (verify gate, milestone handoff).
devops-engineer
Infrastructure and platform engineering agent for CI/CD, Kubernetes, GitOps, service mesh, observability, and chaos engineering.
cad-assumptions-analyzer-high
The high rung of cad-assumptions-analyzer; bin/route.mjs picks it, not the user.
cad-executor-xhigh
The xhigh rung of cad-executor; bin/route.mjs picks it, not the user.
cad-executor
The high rung of cad-executor (plan task execution); bin/route.mjs picks it, not the user.
cad-plan-checker-high
The high rung of cad-plan-checker; bin/route.mjs picks it, not the user.