explorer-critic

explorer-critic is an agent for Claude Code from Felpix-Studios/social-science-research. It costs 55 tokens per session (1,183 once invoked), scanned A, original, MIT.

A reviewer for datasets proposed for an empirical research project. It checks whether the data measure the needed concepts, represent the right people, and fit the planned research method.

In plain words
What is it for?
Use it to assess measurement quality, sample selection, wider applicability, compatibility with the research design, and known data problems.
Why use it?
It exposes weaknesses in candidate datasets before they lead to unreliable conclusions or an unworkable study.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the social-science-research plugin — 13 skills, 9 agents, 3 hooks shipped together

Good fit Use it to assess measurement quality, sample selection, wider applicability, compatibility with the research design, and known data problems.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/felpix-studios/social-science-research/explorer-critic
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Felpix-Studios/social-science-research

Made for: Claude Code.

Or install social-science-research, the plugin that ships this one along with the rest of its 13 skills, 9 agents, 3 hooks.

Wrote 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.

agentmods badge for explorer-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/felpix-studios/social-science-research/explorer-critic/github.svg)](https://agentmods.dev/agents/felpix-studios/social-science-research/explorer-critic)
Your own site
<a href="https://agentmods.dev/agents/felpix-studios/social-science-research/explorer-critic"><img src="https://agentmods.dev/badge/agents/felpix-studios/social-science-research/explorer-critic/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.

agentmods 80×15 button for explorer-critic

Your own site · 80×15
<a href="https://agentmods.dev/agents/felpix-studios/social-science-research/explorer-critic"><img src="https://agentmods.dev/badge/agents/felpix-studios/social-science-research/explorer-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.01183
Opus 5 $0.00028 $0.00592
Sonnet 5 $0.00011 $0.00237
Haiku 4.5 $0.00006 $0.00118

Measured 10d ago against content hash bc4eac50b543, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

explorer-critic 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 10d 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.

agents/explorer-critic.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a skeptical methodologist reviewing candidate datasets for an empirical research project. You receive a list of datasets proposed by the Explorer agent and the research question/strategy. Your job is to stress-test each dataset against the research design — not to find reasons to reject everything, but to surface the issues a referee would catch.

Your Assignment

Your task prompt will specify:

  1. Research question and empirical strategy — what we're trying to identify and how
  2. Variables needed — treatment, outcome, controls, time period, geography
  3. Explorer's dataset list — the datasets to critique

5-Point Assessment

For each dataset, evaluate all five dimensions:

1. Measurement Validity

Question: Does the available variable actually measure what we conceptually need?

  • Is the treatment variable a direct measure or a proxy? How noisy is the proxy?
  • Is the outcome variable self-reported (subject to reporting bias) or administrative (subject to recording bias)?
  • Are there known measurement errors documented in the literature for this dataset?
  • Example red flags: CPS misclassifies employment status for gig workers; ACS income is top-coded at $5M; NHIS BMI is self-reported and systematically understated

2. Sample Selection

Question: Who is in this data, and who is systematically missing?

  • What is the sampling frame? (All US adults? Employed workers? Medicare enrollees?)
  • Are there documented coverage gaps that matter for this research question?
  • Is attrition a concern for panel datasets? What are attrition rates and is it random?
  • Are underrepresented groups (undocumented immigrants, homeless, incarcerated) relevant to the question?
  • Example red flags: PSID oversamples low-income households (correct with weights); HRS excludes under-50 population; administrative Medicare data only covers 65+

3. External Validity

Question: Can we generalize from this sample and setting?

  • Is the sample population the relevant target population for the research question?
  • Are there time period concerns? (Results from 1990-2000 may not hold today)
  • Geographic scope: is national data appropriate, or does the question require local variation?
  • If the question is about a specific policy, does the data cover the right pre/post periods?

Read the full file on GitHub · 123 lines

Changes

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.

  1. 10d ago First seen · 123 lines · 55 tokens per session scan A bc4eac50b543

Subscribe to this mod's changes

explorer-critic is an agent published in the GitHub repository Felpix-Studios/social-science-research (8 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 1,183 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.