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 skills add girijashankarj/cursor-handbook --skill monitoringgit clone --depth 1 https://github.com/girijashankarj/cursor-handbookWrote 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.
[](https://agentmods.dev/skills/girijashankarj/cursor-handbook/monitoring)<a href="https://agentmods.dev/skills/girijashankarj/cursor-handbook/monitoring"><img src="https://agentmods.dev/badge/skills/girijashankarj/cursor-handbook/monitoring.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.00411 |
| Opus 5 | $0.00013 | $0.00205 |
| Sonnet 5 | $0.00005 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
monitoring 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 4d 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.
What it actually says
Skill: Set Up Monitoring
Trigger
When the user needs to set up or improve service monitoring.
Steps
Step 1: Define Metrics
- Request rate (throughput)
- Error rate (4xx, 5xx)
- Latency (p50, p95, p99)
- Resource utilization (CPU, memory, disk)
- Business metrics (domain-specific)
Step 2: Implement Structured Logging
- JSON format for all logs
- Required fields: timestamp, level, correlationId, service
- No PII in logs
- Appropriate log levels (error, warn, info, debug)
Step 3: Set Up Tracing
- Add OpenTelemetry or provider-specific SDK
- Instrument HTTP requests
- Instrument database queries
- Instrument external service calls
- Configure sampling rate
Step 4: Create Dashboards
- Service health overview
- Request rate and error rate
- Latency percentiles
- Resource utilization
- Business KPIs
Step 5: Configure Alerts
- Error rate > 1% → P3
- Error rate > 5% → P1
- p99 latency > 2s → P3
- CPU > 80% → P3
- Health check failure → P1
- Set notification channels
Step 6: Create Runbooks
- For each alert, write a runbook:
- What the alert means
- Investigation steps
- Resolution steps
- Escalation path
Completion
Monitoring, alerting, and runbooks are in place.
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.
- 4d ago First seen · 57 lines · 25 tokens per session scan A 05768cb163c2
monitoring is a skill published in the GitHub repository girijashankarj/cursor-handbook (30 stars, last pushed 8d ago), licensed MIT. It adds 25 tokens to every session and 411 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
deploy-verify
Post-deploy smoke test across browser, Sentry, Supabase, Langfuse, and the public web. Use when "verify deploy", "smoke test production", "post-release check", or "ship or rollback". Deploy + observation loop → workflow-ship-and-observe. npm package release → deploy-npm.
backend-patterns
Apply backend patterns — queues, caching, rate limits, serverless/edge. Use when "queue jobs", "caching layer", "rate limiting", "server actions", or "edge function". Which architecture to pick → audit-backend-architecture.
audit-env-parity
Read-only audit of config/env parity across dev, staging, and prod — missing or misnamed vars, drifted flags, hardcoded values, secrets reused across environments. Use when "works locally but not in prod", "audit our environments", or "config drift". Local runnability → workflow-environment-ready.
audit-infra-cost
Read-only audit of hosting, database, storage, egress, and serverless spend (Supabase, Vercel, S3/R2, edge). Use when "hosting bill is high", "cut infra costs", or a bill jumps. CI minutes → audit-cicd. Model tokens → plan-llm-cost-guardrails. Consumes test-load numbers.
plan-backup-dr
Audit whether a project can actually recover from data loss — not just whether backups exist — then emit a phased DR plan. Use when "can we recover if the DB dies", "audit our backups", "what's our RPO/RTO", or "disaster recovery". Plan only. Destructive-op gates stay on plan-data-integrity.
nginx-config-optimizer
Optimizes Nginx configurations for performance, security, caching, and load balancing with modern best practices. Use when users request "Nginx setup", "reverse proxy", "load balancer", "web server config", or "Nginx optimization".