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/christopherlouet/claude-baseWrote 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/commands/christopherlouet/claude-base/ops-monitoring)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/ops-monitoring"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/ops-monitoring/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/commands/christopherlouet/claude-base/ops-monitoring"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/ops-monitoring.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 | $0.00000 | $0.00634 |
| Opus 5 | $0.00000 | $0.00317 |
| Sonnet 5 | $0.00000 | $0.00127 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
ops-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 9d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MONITORING Agent
Code instrumentation for monitoring/logging/alerting and deploying the observability stack.
Request context
$ARGUMENTS
Objective
Set up the 3 pillars of observability (logs, metrics, traces) with error tracking, health checks and alerting rules — then, when needed, deploy the backing stack (Prometheus, Grafana, Loki, Alertmanager).
Workflow — instrument the code
- Analyze the technical stack and existing tools
- Configure error tracking (Sentry)
- Implement structured logging (Pino, structlog, zap)
- Expose Prometheus metrics (/metrics)
- Configure OpenTelemetry for distributed tracing (optional)
- Add health checks (/health/live, /health/ready)
- Define alerting rules (error rate, latency, CPU, memory)
- Mask sensitive data in logs (GDPR)
Workflow — deploy the observability stack
- Identify the deployment mode (Docker Compose for dev/staging, Kubernetes + Helm for prod, Victoria Metrics, managed)
- Configure Prometheus (scrape configs, alert rules) and Alertmanager (routes, Slack/PagerDuty/email receivers)
- Configure Grafana (provisioning datasources + dashboards) and Loki + Promtail (log aggregation)
- Add node-exporter and cAdvisor for system metrics
- Document the deployment and verification commands
- Persistent storage for metrics; never expose Prometheus/Alertmanager without auth in production
Expected output
- Error tracking configured (Sentry or equivalent)
- Logger structured with sensitive data redaction
- Prometheus metrics exposed, health checks (liveness/readiness), alert rules
- Stack deployment (when requested): docker-compose.yml or Helm values, prometheus.yml + alert.rules.yml, alertmanager.yml, Loki/Promtail configs, Grafana provisioning
Related agents
| Agent | Usage |
|---|---|
/ops:ops-k8s |
Deploy the stack on Kubernetes |
/ops:ops-docker |
Containerize the services |
/ops:ops-health |
Quick health check |
/qa:qa-perf |
Performance analysis |
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.
- 9d ago First seen · 65 lines · 0 tokens per session scan A ace74608fc6b
ops-monitoring is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 634 tokens. 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 commands, from other repositories
migrate
Generate and manage database migrations.
context-stats
Display context window usage and token statistics.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.
cancel-ralph
Cancel active Ralph Wiggum loop.
log-decision
Append an architectural decision to the persistent decision log.
update-docs
Scan for recently modified files and update corresponding documentation.