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 agentmods add skills/beita6969/scienceclaw/census-datanpx skills add beita6969/ScienceClaw --skill census-datagit clone --depth 1 https://github.com/beita6969/ScienceClawWrote 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/beita6969/scienceclaw/census-data)<a href="https://agentmods.dev/skills/beita6969/scienceclaw/census-data"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/census-data.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00699 |
| Opus 5 | $0.00020 | $0.00349 |
| Sonnet 5 | $0.00008 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
census-data scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
metadata: { "openclaw": { "emoji": "📋", "requires": { "bins": ["curl"], "env": ["CENSUS_API_KEY"] } } } How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
US Census Data Skill
Query the US Census Bureau API for demographics, population, and economic data.
When to Use
- "What's the population of Texas?"
- "Show demographic breakdown by county"
- "Get median household income for California"
- "Compare poverty rates across states"
When NOT to Use
- Non-US data (use world-bank-data)
- Real-time economic data (use financial APIs)
- Historical pre-1790 data
Setup
Get a free API key at https://api.census.gov/data/key_signup.html
export CENSUS_API_KEY=your_key_here
API Base
https://api.census.gov/data/
Common Commands
ACS 5-Year Estimates (Most Used)
# Total population by state
curl -s "https://api.census.gov/data/2022/acs/acs5?get=NAME,B01001_001E&for=state:*&key=$CENSUS_API_KEY"
# Median household income by state
curl -s "https://api.census.gov/data/2022/acs/acs5?get=NAME,B19013_001E&for=state:*&key=$CENSUS_API_KEY"
# Population by county in California (state FIPS=06)
curl -s "https://api.census.gov/data/2022/acs/acs5?get=NAME,B01001_001E&for=county:*&in=state:06&key=$CENSUS_API_KEY"
# Poverty rate by state
curl -s "https://api.census.gov/data/2022/acs/acs5?get=NAME,B17001_001E,B17001_002E&for=state:*&key=$CENSUS_API_KEY"
Decennial Census
# 2020 total population by state
curl -s "https://api.census.gov/data/2020/dec/pl?get=NAME,P1_001N&for=state:*&key=$CENSUS_API_KEY"
Common Variables
| Variable | Description |
|---|---|
| B01001_001E | Total population |
| B19013_001E | Median household income |
| B17001_002E | Population below poverty |
| B25077_001E | Median home value |
| B15003_022E | Bachelor's degree holders |
| B02001_002E | White alone population |
Notes
- Free API key required for most queries
- ACS 5-year estimates are most reliable for small geographies
- FIPS codes identify states (e.g., 06=CA, 36=NY, 48=TX)
- Rate limit: 500 requests/day without key, more with key
- Variables list: https://api.census.gov/data/2022/acs/acs5/variables.html
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.
- 4d ago First seen · 81 lines · 41 tokens per session scan A 683527bb3708
census-data is a skill published in the GitHub repository beita6969/ScienceClaw (891 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 699 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
biomcp
Search and retrieve biomedical data - genes, variants, clinical trials, diagnostic tests, articles, drugs, diseases, pathways, proteins, adverse events, pharmacogenomics, and phenotype-disease matching. Use for gene function, variant pathogenicity, trials, diagnostics, drug safety, pathway context, disease workups…
biomcp-research
Do biomedical literature and variant research with the BioMCP CLI, and file what you learn about the tool itself as issues in the biomcp repo.
shidi
科研/工作中的"师弟"——用户给想法和方向，师弟负责把想法拆解、执行、交付：文献调研（多角度检索+评分标注+输出报告）、设计/验证实验方案（含文献支撑）、科研作图、精读论文、数据整理等脏活累活。触发词：师弟、脏活、跑腿活、文献调研、查文献、综述、帮我查资料、实验方案、做图、画图、帮我读论文。.
grounded
Write a scientific review of a topic or research question — small, medium (default), or large; in scientific, popsci (default), bullets, or ELI5 style; delivered as inline chat, a journal-styled PDF with generated figures (default), or, on explicit request only, an experimental 16:9 slide deck — built solely on…
agents
Drop-in instructions for any AI agent connected to the foragekit MCP server (uvx foragekit serve --mcp). Paste this into your agent's instructions, or install it as a skill. It teaches the loop; the tools enforce the rules.
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…