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 datacommonsorg/agent-toolkit --skill data-commons-researchergit clone --depth 1 https://github.com/datacommonsorg/agent-toolkitWrote 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/datacommonsorg/agent-toolkit/data-commons-researcher)<a href="https://agentmods.dev/skills/datacommonsorg/agent-toolkit/data-commons-researcher"><img src="https://agentmods.dev/badge/skills/datacommonsorg/agent-toolkit/data-commons-researcher/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/datacommonsorg/agent-toolkit/data-commons-researcher"><img src="https://agentmods.dev/badge/skills/datacommonsorg/agent-toolkit/data-commons-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 104 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00040 | $0.02880 |
| Opus 5.5 | $0.00016 | $0.01152 |
| Sonnet 5.5 | $0.00008 | $0.00576 |
| Haiku 4.5 | $0.00004 | $0.00288 |
Grade A, and why
data-commons-researcher 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foundational Knowledge: Data Commons Graph Structure
Data Commons organizes data into two main structural hierarchies. Understanding these is key to choosing your place names and variables:
- Topics (Variable Hierarchy): A taxonomy of categories (e.g.,
Health->Clinical Data->Medical Conditions). Topics contain sub-topics and individual variables. - Places (Geographic Hierarchy): A taxonomy of spatial containment (e.g.,
World->Continent->Country->State->County).
Data Availability & Efficiency Tips:
- Country-Level Priority: Data coverage is always highest and most complete at the
Countrylevel. If a variable is missing at sub-national levels, fall back to checking country-level scope. - Child Places Routing: If the user's query asks for statistics across child places or within a geographic containment hierarchy (e.g., "unemployment rate in all counties of California" or "GDP of countries in Africa"), you MUST read the specialized skill resource at 'skill://data-commons-child-places-researcher/SKILL.md' instead.
1. The Three-Step Tool Pipeline
When researching statistics for specific places, always separate your work into three distinct phases to avoid context bloat:
- Discovery (
search_indicators): Use this to find candidate variables matching the user's concept. - Assessment (
get_variable_metadata): Pass candidate variables and target locations to retrieve structural metadata, ensuring the dataset matches the required temporal range, granularity, and source trust. - Retrieval (
get_observations): Fetch the actual timeseries arrays once the variables and facets have been qualified.
CRITICAL: Always validate variable-place combinations first
- You MUST call
search_indicatorsfirst to verify that the variable exists for the specified place. - You MUST call
get_variable_metadatato verify dataset facets (source, dates, coverage) before retrieving heavy observation arrays. - Only use DCIDs returned by
search_indicators- never guess or assume variable-place combinations. - This ensures data availability and prevents errors from invalid combinations.
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 · 251 lines · 40 tokens per session scan A 1caf3c170514
data-commons-researcher is a skill published in the GitHub repository datacommonsorg/agent-toolkit (148 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 2,880 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…