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 berba-q/faostat-skills --skill scientific-papergit clone --depth 1 https://github.com/berba-q/faostat-skillsWrote 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/berba-q/faostat-skills/scientific-paper)<a href="https://agentmods.dev/skills/berba-q/faostat-skills/scientific-paper"><img src="https://agentmods.dev/badge/skills/berba-q/faostat-skills/scientific-paper/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/berba-q/faostat-skills/scientific-paper"><img src="https://agentmods.dev/badge/skills/berba-q/faostat-skills/scientific-paper.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 | $0.00218 | $0.04819 |
| Opus 5 | $0.00109 | $0.02410 |
| Sonnet 5 | $0.00044 | $0.00964 |
| Haiku 4.5 | $0.00022 | $0.00482 |
Grade A, and why
faostat-scientific-paper 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 11d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FAOSTAT Scientific Paper
Build a peer-reviewable research paper from FAOSTAT data. Audience is researchers, reviewers and methodologists — not policymakers, not general readers. Length target 3,000–8,000 words, 6–12 numbered figures/tables, 15–40 references. Deliverable bundle: .docx manuscript + .xlsx data appendix + .bib BibTeX file.
Prerequisites
Before starting, confirm FAOSTAT MCP tools are available: faostat_get_data, faostat_search_codes, faostat_list_groups, faostat_list_domains, faostat_get_rankings, faostat_get_metadata. If not, stop and tell the user the skill requires the FAOSTAT MCP server.
Python packages needed for output: python-docx, openpyxl, pandas, scipy (for scipy.stats.kendalltau and Mann–Kendall test — install pymannkendall if available, otherwise implement from scipy.stats). Install with --break-system-packages in the sandbox.
Invariants
Cross-skill invariants (all six — violations are skill bugs):
- FILTER vs DISPLAY codes.
faostat_get_datatakes FILTER codes (e.g.,2510Production).faostat_get_rankingstakes DISPLAY codes (e.g.,5510). Never invert. - Year syntax. Comma-separated lists only (
'2010,2011,...,2023'). Colon ranges return empty in practice. - Element filter required on every
faostat_get_datacall. - TCL for national trade aggregates, TM only for partner breakdowns. Never sum TM rows to reconstruct national totals.
- China composite default (Apr 2026 user preference). Country-level numbers and rankings default to composite
China(area 351).China, mainland(41) is available as an opt-in — do not substitute 41 unless the user explicitly asks. Flag the choice in the Methods section with the FAOSTAT-default-41 caveat. Map carve-out: if the paper embeds a choropleth, the map uses disaggregation (41 on CHN polygon + HKG 96 + MAC 128 + TWN 214) while narrative rankings and tables use 351. faostat_get_rankingsHTTP-500 fallback. On failure, reconstruct by pullingfaostat_get_dataacross all reporting countries and sorting client-side. Note the fallback in Methods.
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.
- 11d ago First seen · 246 lines · 218 tokens per session scan A 1c4da3ff8aab
faostat-scientific-paper is a skill published in the GitHub repository berba-q/faostat-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 218 tokens to every session and 4,819 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
food-systems-data
Use this Skill to analyze food systems data from FAOSTAT: production/trade/food balance sheets, food security indicators, dietary diversity, and trade flow Sankey diagrams.
scientific-slides
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and…
LQF_Machine_Learning_Expert_Guide
LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, prediction, training, classification, regression, clustering, deep learning, neural network, model evaluation, feature engineering, hyperparameter tuning, overfitting…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
paper-2-web
Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, or Paper2Poster conference posters from LaTeX or PDF sources.
get-available-resources
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to…