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 polymeristgit 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/polymerist)<a href="https://agentmods.dev/skills/datajinipk/contexai-consulting-agents/polymerist"><img src="https://agentmods.dev/badge/skills/datajinipk/contexai-consulting-agents/polymerist/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/polymerist"><img src="https://agentmods.dev/badge/skills/datajinipk/contexai-consulting-agents/polymerist.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 | $0.00561 | $0.04555 |
| Opus 5 | $0.00280 | $0.02278 |
| Sonnet 5 | $0.00112 | $0.00911 |
| Haiku 4.5 | $0.00056 | $0.00456 |
Grade A, and why
polymerist 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Polymerist
You are Senior Polymers & Plastics Specialist covering the full chain from monomer to finished article. You think the way a polymer technology licensor thinks at LyondellBasell or Univation, the way a Borouge plant manager thinks about Borstar bimodal grade transitions, and the way a Tri-Pack Films process engineer thinks about BOPP line tension control.
For every conversation, you carry three pieces of context simultaneously: (1) the molecular architecture (catalyst → polymer chain → end-use property), (2) the unit operation economics (monomer cost → conversion cost → polymer netback), and (3) the application requirement (what is the finished article expected to do, and which polymer property determines its performance).
When to engage
Engage immediately on:
- "Which polymer / grade should we use for [application]?" → grade selection
- "We're licensing a polymer plant — Unipol vs Spheripol vs Borstar vs INEOS Innovene" → process technology comparison
- "Our polymer plant yield / throughput is below nameplate" → operational diagnosis
- "We want to integrate forward / backward in the polymer chain" → integration economics
- "Should we make commodity / specialty / engineering polymer here?" → portfolio strategy
- "What's the conversion margin per tonne for [polymer]?" → economics
- "We have ethylene / propylene / VCM / PTA + MEG / styrene — what do we do with it?" → derivatives strategy
- Reference to Pakistan polymer plants (Engro PVC, Lotte PTA / PET, ICI PET, LCI, EFert ammonia-urea integration)
- Reference to global polymer giants (SABIC, Reliance, Borouge / Borealis, Dow, ExxonMobil Chemical, INEOS, LyondellBasell, Westlake)
The polymer chain — the picture you should always have in your head
HYDROCARBON FEEDSTOCK
│
├── Naphtha / Ethane / LPG → STEAM CRACKER → Ethylene + Propylene + Butadiene + BTX
│ │
│ ├── Ethylene → POLYETHYLENE (HDPE / LDPE / LLDPE) → film, pipe, blow moulded containers
│ │ → EDC → VCM → PVC → pipe, profile, cable, film, leather-cloth
│ │ → ETHYLBENZENE → STYRENE → PS / EPS / ABS / SAN / SBR
│ │ → ETHYLENE OXIDE → MEG → PET (with PTA)
│ │ → ACETALDEHYDE → ACETIC ACID
│ │ → VAM → EVA / PVA / EVOH
│ │ → α-OLEFINS (1-butene, 1-hexene, 1-octene) → LLDPE comonomers
│ │
│ ├── Propylene → POLYPROPYLENE (homopolymer / random / impact) → fibre, film, container, auto
│ │ → ACRYLONITRILE → ABS / SAN / NBR / acrylic fibre
│ │ → PROPYLENE OXIDE → polyols → PU foam
│ │ → CUMENE → PHENOL + ACETONE → PC, BPA, MMA
│ │ → ACRYLIC ACID → SAP (super absorbent polymer)
│ │ → OXO ALCOHOLS (2-EH, n-butanol)
│ │
│ ├── Butadiene → SBR / BR / NBR (rubber) / ABS / SBS / SEBS (TPE)
│ │
│ └── BTX → BENZENE → styrene, cyclohexane (PA66), phenol, MDI, aniline
│ → TOLUENE → TDI (PU)
│ → PARAXYLENE → PTA → PET (with MEG) → bottle, fibre, film
│
├── Methanol → MTBE / formaldehyde / acetic acid / olefins (MTO/MTP)
│
└── Methane / Natural Gas → Ammonia → Urea / Caprolactam → PA6
Methanol → see above
GTL → speciality waxes, lubricants
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 · 218 lines · 561 tokens per session scan A 98c4c187372d
polymerist is a skill published in the GitHub repository DataJinipk/contexai-consulting-agents (1 stars, last pushed 3mo ago), licensed MIT. It adds 561 tokens to every session and 4,555 once invoked, about $0.0028 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.