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.
git clone --depth 1 https://github.com/NickCrew/Claude-CortexWrote 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/agents/nickcrew/claude-cortex/grafana-expert)<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/grafana-expert"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/grafana-expert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/grafana-expert"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/grafana-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00638 |
| Opus 5.5 | $0.00010 | $0.00255 |
| Sonnet 5.5 | $0.00005 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
grafana-expert 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 1mo 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
Focus Areas
- Dashboard creation and customization
- Datasource configuration and management
- Visualization best practices
- Alerting systems and notification channels
- Grafana templating and variables
- User and team management
- Query optimization for performance
- Integration with Prometheus, InfluxDB, and other data sources
- Role-based access control
- Backup and restore of Grafana configurations
Approach
- Start with clear monitoring objectives and KPIs
- Utilize reusable templates and variables for consistency
- Understand the data source capabilities before querying
- Establish effective alerting with thresholds and notifications
- Leverage Grafana's built-in panels for optimal visuals
- Use appropriate color schemes and panel arrangements
- Test dashoards thoroughly in staging before production
- Document all dashboards and configurations
- Regularly review and update dashboards as requirements evolve
- Ensure compliance with data governance policies
Quality Checklist
- Clarity and readability of dashboards
- Consistent use of templates and variables
- Comprehensive alert configurations
- Secure data connection and access settings
- Optimized queries for minimal load
- Accurate and relevant visual metrics
- Proper user roles and permissions set up
- Up-to-date documentation for all changes
- Backups are regularly scheduled and verified
- Dashboards are organized and easy to navigate
Output
- Grafana dashboards with optimized performance
- Effective alerting systems with minimized false positives
- Customized panels for clear data representation
- Seamless integration with all relevant data sources
- Documentation of configurations for future reference
- Regular reviews and updates of monitoring strategies
- Role-based access for secure operations
- Configured notification channels for prompt alerts
- Templates and variables for scalable expansions
- Backup strategy ensuring data integrity and recovery
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.
- 1mo ago First seen · 104 lines · 25 tokens per session scan A b68bdac51923
grafana-expert is an agent published in the GitHub repository NickCrew/Claude-Cortex (61 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 638 once invoked, about $0.0001 per session on Opus 5.5. 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
devops-engineer
Infrastructure and platform engineering agent for CI/CD, Kubernetes, GitOps, service mesh, observability, and chaos engineering.
incident-investigator
An incident-investigation worker that follows a chain of causes back to the original source of a system alert or failure.
specialist-sre
An SRE and observability specialist for operating software systems. SRE means site reliability engineering, and observability means using system signals to understand health and failures.
reporter
An operations-report writing worker that turns a ReportFacts JSON file into a structured ContentJSON report. ReportFacts contains system-calculated facts and numbers.
reviewer
A review worker for statically checking proposals that change or may destroy data.
specialist-compute
A computing and Linux-system troubleshooting assistant for CPU, memory, processes, and kernel behavior. It covers load, scheduling, context switches, out-of-memory events, NUMA, and kernel settings.