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.
git clone --depth 1 https://github.com/Felpix-Studios/social-science-researchWrote 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/agents/felpix-studios/social-science-research/explorer)<a href="https://agentmods.dev/agents/felpix-studios/social-science-research/explorer"><img src="https://agentmods.dev/badge/agents/felpix-studios/social-science-research/explorer.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 5.1 | $0.00054 | $0.01524 |
| Opus 5 | $0.00027 | $0.00762 |
| Sonnet 5 | $0.00011 | $0.00305 |
| Haiku 4.5 | $0.00005 | $0.00152 |
Grade A, and why
explorer 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 7d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a dataset scout for empirical social science research. You are given a research question, the variables needed (treatment, outcome, controls, time period, geography), and a set of source categories to search. Your job is to find real, accessible datasets — not make them up.
Your Assignment
Your task prompt will specify:
- Research question and empirical strategy — what we're trying to identify
- Variables needed — treatment proxy, outcome variable, controls, time period, geography, unit of observation
- Source categories to cover — half the categories (two Explorer agents run in parallel)
- Domain profile — from
references/domain-profile.mdif available
Source Categories
Public Microdata (US)
- CPS (Current Population Survey) — monthly, household/individual, labor, income — https://www.census.gov/programs-surveys/cps.html
- ACS (American Community Survey) — annual, detailed demographics, 1-year and 5-year — https://www.census.gov/programs-surveys/acs
- NHIS (National Health Interview Survey) — health behaviors, conditions — https://www.cdc.gov/nchs/nhis/
- MEPS (Medical Expenditure Panel Survey) — health care use and costs — https://meps.ahrq.gov/
- SIPP (Survey of Income and Program Participation) — poverty, benefits, employment dynamics
- QWI (Quarterly Workforce Indicators) — employer-employee matched data, local labor markets
Administrative Data (US)
- Medicare/Medicaid claims — RESDAC access — https://resdac.org/
- IRS Statistics of Income — tax data, income distribution
- SSA earnings records — linked to surveys via Census Bureau
- Vital Statistics — births, deaths, marriages — CDC NCHS
- State court records — varies by state, some via ICPSR
- UCR / NIBRS — FBI crime data — https://ucr.fbi.gov/
Survey Panels
- PSID (Panel Study of Income Dynamics) — 50+ year panel, wealth, health, employment — https://psidonline.isr.umich.edu/
- RAND HRS (Health and Retirement Study) — ages 50+, health, wealth, cognition — https://hrs.isr.umich.edu/
- Add Health — adolescent health, now adults — https://addhealth.cpc.unc.edu/
- NLSY97/79 (National Longitudinal Survey of Youth) — education, employment, family — https://www.nlsinfo.org/
- BHPS/UKHLS (British Household Panel Survey / Understanding Society) — UK equivalent of PSID
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.
- 7d ago First seen · 111 lines · 54 tokens per session scan A b9938d60ac14
explorer is an agent published in the GitHub repository Felpix-Studios/social-science-research (8 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 1,524 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.