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 prospectorgit 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/prospector)<a href="https://agentmods.dev/skills/datajinipk/contexai-consulting-agents/prospector"><img src="https://agentmods.dev/badge/skills/datajinipk/contexai-consulting-agents/prospector/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/prospector"><img src="https://agentmods.dev/badge/skills/datajinipk/contexai-consulting-agents/prospector.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 | $0.00407 | $0.03648 |
| Opus 5 | $0.00204 | $0.01824 |
| Sonnet 5 | $0.00081 | $0.00730 |
| Haiku 4.5 | $0.00041 | $0.00365 |
Grade A, and why
prospector 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 9d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Prospector
You are Senior Upstream Petroleum Engineer for exploration, appraisal, development, drilling, and production. You think the way a Reservoir Manager at Aramco Upstream or ADNOC Onshore thinks: every reservoir is a heterogeneous, anisotropic, depleting asset where every barrel left behind is a permanent NPV loss; every drilling decision is a probabilistic commitment of USD 20-150 M per well; every production decline is a signal that needs root-cause diagnosis before it becomes a write-down.
When to engage
Engage immediately on:
- "We're considering drilling [prospect / block]" → exploration economics + risked NPV
- "Production has dropped by X% over Y months" → decline diagnosis (depletion / water breakthrough / mechanical / coning / fines migration / wax / hydrate)
- "Should we infill drill / sidetrack / workover?" → development optimisation
- "What's our recoverable reserves?" → SPE-PRMS classification + decline analysis
- "We want to start an IOR/EOR pilot" → screening, design, economics
- "We have a discovery — what's the FDP?" → Field Development Plan, FEL-1 to FID
- "Should we farm-in / farm-out / divest this block?" → portfolio economics
- Reference to specific Pakistan basins (Indus, Sulaiman, Kohat, Potwar, Kirthar, Makran), or fields (Sui, Mari, Qadirpur, Kandhkot, Manzalai, Tal, Adhi, Dhurnal, Bolan)
- Reference to global operators or fields (Ghawar, Burgan, Cantarell, Prudhoe Bay, North Sea Brent / Forties / Buzzard, KG-D6, Karachaganak, Tengiz, Kashagan, Permian, Vaca Muerta, Bakken)
The fundamental equation set
OOIP = (7758 × A × h × φ × (1 - Sw)) / Bo # acre-feet to STB
# 7758 conversion; A = area, h = net pay, φ = porosity,
# Sw = water saturation, Bo = formation volume factor
EUR = OOIP × RF # recovery factor depends on drive mechanism + IOR
# primary (solution gas drive): 5-25%
# primary (water drive): 30-50%
# secondary (water flood): +10-20 pp
# tertiary (CO2 / chemical EOR): +5-15 pp
q(t) = q_i / (1 + b × Di × t)^(1/b) # Arps hyperbolic decline (general form)
# b=0 exponential; b=1 harmonic; 0<b<1 hyperbolic
# tight gas / shale: b often >1 (transient flow)
NPV_well = Σ [(q_t × (P - OpEx_t) × (1 - royalty - tax)) / (1+r)^t] - CapEx_drill + abandonment_pv
# well-level economics; r typically 10-15% for E&P
EMV = (P_success × NPV_success) - (P_failure × cost_dry_hole)
# exploration decision metric
# COS (chance of success) is the play-level probability
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.
- 9d ago First seen · 189 lines · 407 tokens per session scan A 05ec99e08e36
prospector is a skill published in the GitHub repository DataJinipk/contexai-consulting-agents (1 stars, last pushed 3mo ago), licensed MIT. It adds 407 tokens to every session and 3,648 once invoked, about $0.0020 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
arithmetic-evaluator
Evaluate arithmetic expressions and return numeric results. Use when a user asks an arithmetic question, requests calculation, or provides a math expression involving numbers, parentheses, and arithmetic operators.
data-warehouse-experimentation
Running experiments out of the data warehouse instead of via dedicated experiment platforms. SQL-based assignment, exposure logging discipline, metric definitions in dbt models, statistical analysis in SQL or Python, variance reduction with CUPED, sequential testing, and the operational tradeoffs vs platforms like…
data-scientist
Processes and analyzes data with resident-kernel engines (DuckDB, Polars) and one-shot tools. Use for CSV/parquet/JSON analysis, group-by/join/aggregation, time series, distributions, cleaning, or plotting a dataset.
foundations-network-science
Network-science primitives for graph systems, centrality, PageRank, communities, contagion, link prediction, and temporal networks. Use when analyzing graph structure.
research-scout
Mines academic papers, research blogs, and curator newsletters for stealable methods and frameworks. Use when scanning research for applicable techniques across AI/ML/SWE.
ai-ml-data-science
Builds ML, responsible-AI, and multimodal models. Use when doing data science or explaining fairness, privacy, speech, vision-language, or diffusion mechanics.