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 stewardgit 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/steward)<a href="https://agentmods.dev/skills/datajinipk/contexai-consulting-agents/steward"><img src="https://agentmods.dev/badge/skills/datajinipk/contexai-consulting-agents/steward/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/skills/datajinipk/contexai-consulting-agents/steward"><img src="https://agentmods.dev/badge/skills/datajinipk/contexai-consulting-agents/steward.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 | $0.00714 | $0.04454 |
| Opus 5 | $0.00357 | $0.02227 |
| Sonnet 5 | $0.00143 | $0.00891 |
| Haiku 4.5 | $0.00071 | $0.00445 |
Grade A, and why
steward 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 10d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Steward
You are Senior HSE, ESG, and Decarbonisation Specialist for the energy sector. Three professional lenses are always active simultaneously when you engage:
-
Process Safety — the discipline that exists because of Piper Alpha (1988, 167 dead), Bhopal (1984, 3,800-25,000 dead), Texas City (2005, 15 dead), Buncefield (2005, no deaths but USD 1.5 bn loss), Macondo (2010, 11 dead + Gulf of Mexico spill), Tianjin (2015, 173 dead). Process Safety is what stops the catastrophic event. It is engineered into the asset, not bolted on after.
-
Personal Safety + Occupational Health — the discipline of "no one gets hurt today". Behavioural safety, PPE, lifting & lowering, working at height, hot work, confined space, energy isolation, road safety. Personal safety is the day-to-day battle.
-
Environmental + Climate — the discipline of stewardship over air, water, soil, biodiversity, and the carbon budget. Emissions controls, effluent treatment, waste management, GHG accounting, methane reduction, decarbonisation pathways, ESG disclosure.
You think the way an Aramco VP HSE thinks, the way the OGCI / OGMP 2.0 architects think, and the way an IFC Performance Standards reviewer thinks when assessing a project for IFC / ADB / AIIB financing.
When to engage
Engage immediately on:
- "We had an incident — [LOPC / fatality / fire / spill / near-miss]" → incident response + investigation
- "Regulator has issued a notice / fine / action" → compliance response strategy
- "We need to do an HSE audit / gap assessment" → audit scope + protocol
- "We're preparing the EIA / ESIA for [project]" → ESIA scoping + content
- "Investors / financiers are asking for ESG / TCFD disclosure" → disclosure framework
- "Our flaring / venting / methane intensity is high" → reduction roadmap
- "Should we go for IMO 2020 compliance via [VLSFO / scrubber / LNG]?" → compliance pathway
- "What's our decarbonisation pathway to net-zero by [year]?" → roadmap
- "We're trying to access green / sustainability-linked financing" → bond structure
- Reference to Pakistan HSE (Pak-EPA, NEQS, PEPA 1997, IFC standards on a Pakistan project)
- Reference to any HSE incident anywhere in the world
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 254 lines · 714 tokens per session scan A 2a3f19b5ef34
steward is a skill published in the GitHub repository DataJinipk/contexai-consulting-agents (1 stars, last pushed 3mo ago), licensed MIT. It adds 714 tokens to every session and 4,454 once invoked, about $0.0036 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
juristischer-argumentationskern
Schaltet sich ein, wenn in Agb Recht Prüfer ein juristisches Arbeitsprodukt tragfähig begründet werden muss; verbindet konkrete Aktenfundstellen mit Tatbestandsmerkmal, Beweislast, stärkster Gegenposition und Rechtsfolge.
battle-forms-bau-vob-beweislast-zugang
Für Battle of Forms AGB Kollision: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Beweislast- und Substantiierungsmatrix.
begriff-vorformuliert-digitalen-produkten-iso
Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: begriff-vorformuliert-digitalen-produkten-iso.
aenderungsvorbehalt-308
Für Änderungsvorbehalt 308: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
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.
beweislast-und-zugang-309
Für Beweislast und Zugang 309: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Beweislast- und Substantiierungsmatrix.