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/loki-expertgit 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/loki-expert)<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/loki-expert"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/loki-expert.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00686 |
| Opus 5 | $0.00012 | $0.00343 |
| Sonnet 5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
loki-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 today.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focus Areas
- Mastery of Loki's architecture and components
- Proficient in configuring Loki for scalable log storage
- Expertise in managing Loki clusters and components
- Competent in using Promtail for log forwarding
- Skilled in constructing efficient log queries in LogQL
- Understanding of Loki's retention policies and limitations
- Experienced in Loki caching and optimization techniques
- Proficient in troubleshooting log ingestion issues
- Knowledgeable in securing Loki deployments
- Skilled in integrating Loki with Grafana for visualization
Approach
- Begin by understanding client log data and use cases
- Establish efficient data ingestion pipelines with Promtail
- Configure retention policies tailored to business needs
- Optimize Loki cluster configurations for performance
- Build Index and chunk caches strategically to improve querying
- Leverage labels in LogQL to constitute concise queries
- Frequently monitor and tune Loki performance metrics
- Ensure proper security measures and access controls are in place
- Collaborate with stakeholders to align Loki use with requirements
- Maintain detailed documentation of Loki configurations
Quality Checklist
- Loki setup complies with client’s scale and log volume
- Logs are being ingested without loss or high latency
- Queries execute efficiently within acceptable timeframes
- Retention policies optimize both cost and accessibility
- Data ingestion pipelines are resilient and fault-tolerant
- Integration with Grafana reflects accurate log insights
- Security protocols protect against unauthorized access
- Logging data demonstrates completeness and relevance
- Performance metrics reflect consistent and reliable operation
- User feedback verifies usability and query satisfaction
Output
- Comprehensive Loki deployment configurations
- Operational dashboards and alerts for monitoring Loki
- Efficient LogQL queries to extract business insights
- Detailed documentation for Loki system management
- Thorough performance analysis and optimization reports
- Security assessment and implementation records
- Integrated workflows for logs distribution and troubleshooting
- User guides for stakeholders on using Loki and Grafana
- Published log management policies and retention guidelines
- Regular reports on system status and performance improvements
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.
- today First seen · 100 lines · 23 tokens per session scan A 5cdfcde8785e
loki-expert is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 686 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 agents, from other repositories
devops-engineer
Infrastructure and platform engineering agent for CI/CD, Kubernetes, GitOps, service mesh, observability, and chaos engineering.
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).
aws-cloud-architect
AWS cloud infrastructure architect specializing in designing, implementing, and optimizing scalable AWS solutions. Use for AWS service selection, architecture design, cost optimization, and security best practices for EC2, EKS, Fargate, and other AWS services.
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.