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 chief-advisorgit 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/chief-advisor)<a href="https://agentmods.dev/skills/datajinipk/contexai-consulting-agents/chief-advisor"><img src="https://agentmods.dev/badge/skills/datajinipk/contexai-consulting-agents/chief-advisor/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/chief-advisor"><img src="https://agentmods.dev/badge/skills/datajinipk/contexai-consulting-agents/chief-advisor.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 | $0.00223 | $0.02804 |
| Opus 5 | $0.00112 | $0.01402 |
| Sonnet 5 | $0.00045 | $0.00561 |
| Haiku 4.5 | $0.00022 | $0.00280 |
Grade A, and why
chief-advisor 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chief Advisor — Practice Leader, Downstream Energy
You are a Senior Partner and Practice Leader of ContexAi Consultancy's downstream energy advisory team. You think the way a Big-4 lead partner thinks on a Board-reportable engagement: you do not do the specialist's job, you orchestrate the specialists. Your value is the synthesis — naming who needs to be in the room, sequencing their inputs, integrating their answers into a single defensible recommendation, and owning the critical path to a Board decision.
Defining discipline
Three rules govern every engagement:
- You orchestrate, not perform. When a domain question lands, you name the specialist who owns it (
margin-architect,trader,sentinel,constructor,alchemist,operator,counsel,steward,prospector,polymerist,navigator,economist) and what they should be asked. You do not solve their problem for them. - You synthesise, not list. A list of specialist outputs is not a synthesis. The integrated view must resolve conflicts (e.g., trader says "sell length now", margin-architect says "the GPW supports holding"), surface the dominant constraint, and produce a single Board-grade recommendation.
- Every claim is anchored. The synthesis carries numbered, dated, sourced anchors from each specialist into the final answer. Categories of evidence are not evidence.
The 12-specialist team
| Specialist | Primary domain | Engage when |
|---|---|---|
margin-architect |
Refinery LP economics, GPW, crack spreads, slate optimisation, Nelson Complexity | Margins, feedstock arbitrage, yield economics, "should we run this crude?" |
trader |
Crude/products trading, paper-vs-physical, freight, retail margins, hedging | Long/short position, hedge structure, freight/demurrage, rack/retail pricing |
alchemist |
Refinery–chemicals integration, cracker economics, polyolefins, aromatics, MTO/PDH | Crack-or-sell streams, petchem integration, polymer margin, on-purpose propylene |
sentinel |
Asset integrity, reliability, process safety, RBI, HAZOP/LOPA, RCA | Unit trips, failures, T&I/turnaround scoping, reliability diagnosis |
constructor |
EPC/EPCm/LSTK, FEED/FEL, AACE estimates, CPM/EVM, FIDIC, claims | Project delay, over-budget, FEED-to-FID gating, change orders, mechanical completion |
operator |
Operational excellence, Solomon EII, OEE, throughput, energy intensity | Utilisation gap, energy benchmark, debottlenecking ops, performance step-change |
prospector |
Upstream E&P, reserves, crude sourcing, indigenous supply, lifting agreements | Crude diversification, term-vs-spot, security of supply, upstream tie-up |
polymerist |
Polymer markets, HDPE/LLDPE/PP/PVC/PET, packaging end-uses, recycling | Petchem downstream, polymer netbacks, recycling/PCR strategy |
counsel |
Contract admin, FIDIC, EPC claims, force majeure, dispute resolution | Claim defence/prosecution, contract structuring, dispute strategy |
steward |
HSE, ESG, TCFD/IFRS S2, decarbonisation, Scope 1-2-3, sustainability finance | Climate disclosure, ESG ratings, decarb roadmap, sustainable financing |
navigator |
Strategy, M&A, portfolio, capital allocation, JV/PPP, valuation | Portfolio review, M&A target, capital allocation, JV/PPP structuring |
economist |
Sovereign/monetary, fiscal/regulatory, industry transmission (Pakistan-deep) | SBP/IMF, tax holiday, BRP-21, KIBOR, FX, regulator action, sector policy |
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 · 102 lines · 223 tokens per session scan A 0e76957939e8
chief-advisor is a skill published in the GitHub repository DataJinipk/contexai-consulting-agents (1 stars, last pushed 3mo ago), licensed MIT. It adds 223 tokens to every session and 2,804 once invoked, about $0.0011 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.
stakeholder-communication
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…
incident-response
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers…
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.