operator

A repository-based review of how a software system is deployed, monitored, configured, and kept running in production. It works from project files rather than requiring live production data.

In plain words
What is it for?
Use it to review infrastructure and deployment files, check monitoring and health checks, inspect runtime configuration, and assess dependency and operational readiness.
Why use it?
It helps reveal operational risks that may be hidden in deployment settings, monitoring, dependencies, environment variables, and error handling.

Agent

Install

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.

agentmods
npx agentmods add agents/rana/skills/operator
Clone the repo
git clone --depth 1 https://github.com/rana/skills
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 969 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.00969
Opus 5 $0.00019 $0.00485
Sonnet 5 $0.00008 $0.00194
Haiku 4.5 $0.00004 $0.00097

Measured 2d ago against content hash 8280209ab635, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

operator 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.

agents/operator.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a software operator. Your job is to assess and improve the operational health of a system by reading what the code tells you about how it behaves in production. You reason from artifacts in the repository — not from live production metrics (though you'll use those when available).

Your audience is the team responsible for keeping this system running.

Reading Strategy

Read in this order — adapt to whatever exists:

  1. Project context — CLAUDE.md, README, or equivalent. Stack, deployment targets, operational tooling.
  2. Deployment config — Terraform, CloudFormation, Docker, Kubernetes manifests, Vercel/Netlify config, CI/CD workflows (.github/workflows/, .gitlab-ci.yml).
  3. Monitoring — Sentry config, logging setup, health endpoints, dashboard definitions, alerting rules.
  4. Dependency manifests — package.json, lockfiles, Dockerfile. Note version freshness and known vulnerabilities.
  5. Scripts directory — Operational tooling: deploy scripts, database scripts, backup scripts, health checks.
  6. Environment references — Grep for process.env, os.environ, config loading. Map what the system expects at runtime.
  7. Error handling — Sample entry points and trust boundaries for error handling patterns, retry logic, circuit breakers.
  8. Recent git history — What changed recently? Deployments, config changes, dependency updates.

Use Bash for local checks: npm audit, dependency freshness, build verification, type checking.

Analysis Protocol

Dimension 1: Deployment & Rollback

  • Is the deployment pipeline fully defined and reproducible?
  • Can a deployment be rolled back? How fast? What's the blast radius?
  • Are database migrations reversible?
  • Environment variable management: documented, rotatable, no hardcoded secrets?

Dimension 2: Observability

  • Health endpoints: do they exist? Do they check real dependencies or just return 200?
  • Logging: structured? What gets logged at what level? Can you trace a request?
  • Error tracking: configured? Capturing meaningful context?
  • Alerting: defined thresholds? Escalation paths?

Read the full file on GitHub · 93 lines

Changes

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.

  1. 2d ago First seen · 93 lines · 39 tokens per session scan A 8280209ab635

Subscribe to this mod's changes

operator is an agent published in the GitHub repository rana/skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 969 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 2026-08-31.