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 commoditygit 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/commodity)<a href="https://agentmods.dev/skills/berba-q/faostat-skills/commodity"><img src="https://agentmods.dev/badge/skills/berba-q/faostat-skills/commodity/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/commodity"><img src="https://agentmods.dev/badge/skills/berba-q/faostat-skills/commodity.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 | $0.00124 | $0.03809 |
| Opus 5.5 | $0.00050 | $0.01524 |
| Sonnet 5.5 | $0.00025 | $0.00762 |
| Haiku 4.5 | $0.00012 | $0.00381 |
Grade A, and why
faostat-commodity 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 1mo 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commodity Deep Dive
Produce a comprehensive global briefing for a specific agricultural commodity using FAOSTAT data. The output is a structured, data-driven document a reader can consume in ~2 minutes and come away with the essential picture: where it's produced, how efficiently, where it flows, and what's changing.
Prerequisites
This skill uses these FAOSTAT MCP tools:
faostat_search_codesfaostat_get_datafaostat_get_rankings(sometimes unreliable — see Step 3)
If the MCP is not connected, tell the user: "This skill requires the FAOSTAT MCP server to be connected."
Orientation — the shape of the end product
Before following the steps, hold the target in mind. The briefing has four required sections plus up to two optional sections, determined by what kind of commodity it is:
- Required: Global Production Overview, Yield Trajectories, Trade Flows, Historical Context & Outlook
- Optional, depending on commodity type: Consumption & Food Security (for food staples), Price Dynamics (for volatile cash crops), Use Breakdown (for feed grains/oilseeds)
Knowing the shape up front helps you decide how much depth each data pull needs and avoid over-fetching.
Workflow
Step 1: Identify and resolve the commodity
Extract the commodity name from the user's request, or ask if not specified. Accept common names ("wheat", "coffee", "palm oil", "cocoa beans").
Call faostat_search_codes(domain_code='QCL', dimension_id='item', query='<commodity_name>').
Handle the response based on context:
-
Single match (
requires_confirmation: false) — proceed with the returned item code. -
Multiple matches (
requires_confirmation: true) — how you resolve depends on whether a user is available:- Interactive flow (a user can reply): present all matching options and ask the user to choose. Wait for their answer. This is the correct behavior for slash-command / chat use.
- Unattended flow (running inside an agent, script, or pipeline with no interactive user): pick the canonical item — usually the bare commodity name (e.g., "Rice, paddy" over "Rice, milled"; "Wheat" over "Buckwheat"; "Cocoa beans" over a cocoa derivative). Record the choice you made and surface it in the methodology footer of the final briefing so the reader knows. Do not silently assume.
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.
- 1mo ago First seen · 257 lines · 124 tokens per session scan A df097e95ecf4
faostat-commodity is a skill published in the GitHub repository berba-q/faostat-skills (9 stars, last pushed 6mo ago), licensed MIT. It adds 124 tokens to every session and 3,809 once invoked, about $0.0005 per session on Opus 5.5. 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.
godot-optimization
Use when optimizing Godot games — profiler, draw calls, physics tuning, memory management, and common bottlenecks.
scienceworld-measurement-taker
Use when the agent needs to measure a quantitative property (temperature, weight, pH) of a target object or substance using a measurement tool. This skill covers acquiring the tool, preparing both tool and target with focus actions, executing the measurement via "use [TOOL] on [TARGET]", and interpreting the resulting…
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…