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/rana/skillsWrote 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/rana/skills/operator)<a href="https://agentmods.dev/agents/rana/skills/operator"><img src="https://agentmods.dev/badge/agents/rana/skills/operator/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/rana/skills/operator"><img src="https://agentmods.dev/badge/agents/rana/skills/operator.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 | $0.00039 | $0.00969 |
| Opus 5.5 | $0.00016 | $0.00388 |
| Sonnet 5.5 | $0.00008 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
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 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.
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:
- Project context — CLAUDE.md, README, or equivalent. Stack, deployment targets, operational tooling.
- Deployment config — Terraform, CloudFormation, Docker, Kubernetes manifests, Vercel/Netlify config, CI/CD workflows (
.github/workflows/,.gitlab-ci.yml). - Monitoring — Sentry config, logging setup, health endpoints, dashboard definitions, alerting rules.
- Dependency manifests — package.json, lockfiles, Dockerfile. Note version freshness and known vulnerabilities.
- Scripts directory — Operational tooling: deploy scripts, database scripts, backup scripts, health checks.
- Environment references — Grep for
process.env,os.environ, config loading. Map what the system expects at runtime. - Error handling — Sample entry points and trust boundaries for error handling patterns, retry logic, circuit breakers.
- 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?
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 · 93 lines · 39 tokens per session scan A 8280209ab635
operator is an agent published in the GitHub repository rana/skills (1 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 969 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
smart-contract-auditor
Use when Solidity/EVM contracts exist — after web3 implementation, or /review --contracts (--package before an external audit). Runs Slither, Aderyn, Solhint, Foundry; proves each finding via four gates with file:line and a PoC; writes docs/security/AUDIT-{slug}.md. --package adds a threat model, invariants, a Foundry…
README
Sub-agent definitions for Claude Code delegation.
gas-optimizer
Finds gas-saving opportunities with concrete patches and estimated savings. Use from /gas.
sequant-implementer
Implementation agent for sequant /exec parallel groups. Handles component creation, type definitions, CLI scripts, and refactoring tasks. Use when spawned by the /exec skill to implement a specific subtask in a feature worktree.
code-explorer
Fast, read-only code search and exploration subagent. Locates files by pattern, greps for symbols or keywords, answers "where is X defined / which files reference Y" with file:line citations and short excerpts. Spawn it to protect the orchestrator's context window from large search results — it reads excerpts, not…
code-reviewer
A code-review agent that checks changes against a project's design patterns, ADRs, and recommended practices. ADRs are short records explaining important architecture decisions.