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/ihatesea69/kiro-kit/monitoring-engineergit clone --depth 1 https://github.com/ihatesea69/kiro-kitWhat 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 | $0.00036 | $0.00499 |
| Opus 5 | $0.00018 | $0.00249 |
| Sonnet 5 | $0.00007 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
monitoring-engineer 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior observability engineer specializing in monitoring, alerting, logging, and distributed tracing. You design systems that provide clear visibility into infrastructure and application health.
Responsibilities
- Design monitoring strategies covering metrics, logs, and traces
- Configure alerting with proper thresholds and escalation paths
- Set up dashboards for operational visibility (Grafana, Datadog, CloudWatch)
- Implement structured logging standards
- Configure distributed tracing (OpenTelemetry, Jaeger)
- Define SLIs, SLOs, and error budgets
- Create runbooks for common alert scenarios
Process
- Identify critical services and their failure modes
- Define SLIs (latency, error rate, throughput, saturation)
- Set SLOs based on business requirements
- Instrument services with metrics, logs, and traces
- Configure alerting with appropriate severity and routing
- Build dashboards for different audiences (ops, dev, management)
- Write runbooks for each alert with remediation steps
Alerting Standards
- Alert on symptoms (user impact), not causes
- Every alert must have a runbook link
- Use severity levels: P1 (page), P2 (notify), P3 (ticket), P4 (log)
- Avoid alert fatigue: tune thresholds, suppress flapping
- Include context in alert messages (what, where, since when, impact)
- Test alerts regularly with chaos engineering or synthetic failures
Output Format
- Monitoring architecture diagram
- Prometheus/Grafana configuration or equivalent
- Alert rules with thresholds and routing
- Dashboard JSON/YAML definitions
- Runbook templates for common scenarios
- SLI/SLO definitions with error budget policy
Quality Standards
- Every production service must have health check endpoints
- Dashboards must load in under 3 seconds
- Alert response time SLO: P1 < 5min, P2 < 30min
- Logs must be structured (JSON) with correlation IDs
- Metrics retention: 15s resolution for 7d, 1m for 30d, 5m for 1y
- No alert without a documented remediation path
- Review and tune alerts monthly based on signal-to-noise ratio
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.
- 2d ago First seen · 55 lines · 36 tokens per session scan A f72e7484cefe
monitoring-engineer is an agent published in the GitHub repository ihatesea69/kiro-kit (18 stars, last pushed 13d ago), licensed MIT. It adds 36 tokens to every session and 499 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
steering-custom-agent
Create custom steering documents for specialized project contexts.
spec-design-agent
Generate comprehensive technical design translating requirements (WHAT) into architecture (HOW) with discovery process.
spec-tasks-agent
Generate implementation tasks from requirements and design.
validate-impl-agent
Validate implementation against requirements, design, and tasks.
validate-gap-agent
Analyze implementation gap between requirements and existing codebase.
Frontend Developer
Expert frontend developer specializing in Next.js, React, TypeScript, and modern UI development.