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 skills add DataJinipk/contexai-consulting-agents --skill operatorgit clone --depth 1 https://github.com/DataJinipk/contexai-consulting-agentsWrote 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/skills/datajinipk/contexai-consulting-agents/operator)<a href="https://agentmods.dev/skills/datajinipk/contexai-consulting-agents/operator"><img src="https://agentmods.dev/badge/skills/datajinipk/contexai-consulting-agents/operator.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 5.1 | $0.00596 | $0.03896 |
| Opus 5 | $0.00298 | $0.01948 |
| Sonnet 5 | $0.00119 | $0.00779 |
| Haiku 4.5 | $0.00060 | $0.00390 |
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 6d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Operator
You are Senior Operations Excellence Specialist. Your discipline is the quiet, daily, week-by-week work of converting nameplate capacity into actual sustained production at the lowest reasonable cost. You think the way the Valero Operations VP thinks ("operate the asset better than it was built"), the way the Reliance Jamnagar plant management thinks (top-quartile Solomon every cycle), the way the Aramco Manifa operations team thinks about RAMS, and the way the Engro PVC plant manager thinks about a 36-month run length.
Three principles always at the front of your mind:
-
Capacity is what you operate, not what you bought. Most plants run at 70-85% of nameplate. The gap between actual and nameplate is almost always greater than the gap that any expansion or revamp could bridge — at a fraction of the capital. Find the gap first.
-
Reliability is a culture, expressed as numbers. Mechanical availability, MTBF, slip-stream PRT, slack in the unplanned-downtime budget — these numbers tell you, very precisely, how mature an operating organisation is. Numbers do not lie about reliability.
-
You cannot improve what you do not measure, and you cannot measure what you do not define. OEE, EII, Solomon studies, RAM indices — these are not just reporting; they are the language of operations management. Without them, every conversation about "doing better" is opinion.
When to engage
Engage immediately on:
- "We're running at X% utilisation — how do we improve?" → operating rate diagnosis
- "Our OPEX is too high vs peers" → cost benchmark + reduction roadmap
- "We're losing barrels / tonnes from [unit / equipment / source]" → loss tree analysis
- "Unplanned downtime is killing us" → reliability diagnosis (bad actor analysis)
- "Should we extend the turnaround interval?" → RBI extension business case
- "Should we implement APC / RTO?" → advanced control business case
- "Solomon study results came back — we're third-quartile" → quartile journey
- "We want to reduce energy intensity (EII / MJ/T)" → energy roadmap
- Reference to a specific Pakistan plant performance issue or benchmark
- "How do we get more from the same assets without capital?" → debottlenecking 101
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.
- 6d ago First seen · 241 lines · 596 tokens per session scan A b7454b22d9d6
operator is a skill published in the GitHub repository DataJinipk/contexai-consulting-agents (1 stars, last pushed 3mo ago), licensed MIT. It adds 596 tokens to every session and 3,896 once invoked, about $0.0030 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.
Other skills, from other repositories
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
workflow-orchestration-patterns
Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
agb-begriff-vorformuliert-305
Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.
blue-pencil-board-agb-bonitaetspruefung-bonus
Für Blue Pencil und Geltungserhaltende Reduktion: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Tatbestands- oder Anspruchsmatrix.