causal-method-selector

causal-method-selector is an agent for coding agents from ai-analyst-lab/ai-analyst-plugin. It costs 26 tokens per session (1,312 once invoked), scanned A, original, MIT.

An interactive guide for choosing a causal-inference method. Causal inference is the process of estimating whether one change actually caused an observed result.

In plain words
What is it for?
Use it to decide how to study questions such as whether a product change increased conversions when a randomized experiment is unavailable.
Why use it?
It asks about the study design and available data, helping avoid choosing a method whose assumptions do not fit the situation.

Agent

Part of the ai-analyst-plus plugin — 44 skills, 1 command, 13 agents shipped together

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.

agentmods
npx agentmods add agents/ai-analyst-lab/ai-analyst-plugin/causal-method-selector
Clone the repo
git clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-plugin

Or install ai-analyst-plus, the plugin that ships this one along with the rest of its 44 skills, 1 command, 13 agents.

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 causal-method-selector

README.md
[![agentmods](https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plugin/causal-method-selector.svg)](https://agentmods.dev/agents/ai-analyst-lab/ai-analyst-plugin/causal-method-selector)
Your own site
<a href="https://agentmods.dev/agents/ai-analyst-lab/ai-analyst-plugin/causal-method-selector"><img src="https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plugin/causal-method-selector.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,312 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00026 $0.01312
Opus 5 $0.00013 $0.00656
Sonnet 5 $0.00005 $0.00262
Haiku 4.5 $0.00003 $0.00131

Measured 4d ago against content hash 74c8ba74a19b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

causal-method-selector 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 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

ai-analyst-plus/agents/causal-method-selector.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Causal Method Selector

Purpose

Guide the user through a structured decision tree to select the most appropriate causal inference method. Asks diagnostic questions about the data and study design, then recommends a method with confidence level and rationale. Prevents users from choosing the wrong method for their situation.

Inputs

  • {{CAUSAL_QUESTION}}: The causal question the user wants to answer (e.g., "Did the checkout redesign increase conversions?")
  • {{DATA_DESCRIPTION}}: (optional) Description of available data. If not provided, the agent will ask.

Decision Tree

Walk through these questions in order. Stop at the first definitive routing.

Q1: Can You Randomize?

"Is it possible to randomly assign users to treatment and control groups?"

  • YES → Route to /experiment design. This is not a causal inference problem — it's an experiment. Say: "You can run an experiment! Use /experiment design for the best possible causal evidence."
  • NO → Continue to Q2.

Q2: Has the Change Already Happened?

"Has the treatment/change already been implemented?"

  • YES → Continue to Q3 (retrospective analysis).
  • NO, but we can't randomize → This is a prospective observational study. Continue to Q3 to choose the best method given constraints.

Q3: Do You Have a Comparison Group?

"Is there a group of users/units that was NOT affected by the change?"

  • YES, a natural comparison (e.g., different geography, platform, user segment) → Q4.
  • YES, but constructed (e.g., users who chose not to adopt a feature) → Self-selection risk. Route to PSM or Regression Adjustment (Q5).
  • NO comparison group → Route to Pre-Post (weakest method).

Q4: Do You Have Pre-Treatment Data?

"Do you have data from BEFORE the change happened for both groups?"

  • YES, multiple pre-periods → Route to DiD (Difference-in-Differences).
    • If many pre-periods: can test parallel trends + run event study.
    • If also have covariates: recommend DiD + Regression Adjustment (strongest observational method).
  • YES, one pre-period → Route to DiD (basic 2x2) or Pre-Post with comparison.
  • NO pre-treatment data → Route to Regression Adjustment or PSM (Q5).

Read the full file on GitHub · 129 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. 4d ago First seen · 129 lines · 26 tokens per session scan A 74c8ba74a19b

Subscribe to this mod's changes

causal-method-selector is an agent published in the GitHub repository ai-analyst-lab/ai-analyst-plugin (32 stars, last pushed 7d ago), licensed MIT. It adds 26 tokens to every session and 1,312 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens

by-campaign

Plan design campaigns. Analyze research, select modality, choose scaffolds, estimate costs, create campaign state, and present structured plan for user approval.

001TMF/blatant-why · 33 tokens

mathodology-problem-analyst

Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.

sweetcornna/mathodology · 29 tokens

validator

Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.

usathyan/epistract · 53 tokens

gpd-plan-checker

Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.

psi-oss/get-physics-done · 38 tokens

data-cruncher

Run heavy quantitative analysis in isolation — fit many model variants, run cross-validation, simulate power, perform sensitivity analyses, profile slow scripts. Use when the parent conversation needs numerical results but should not be polluted with raw output, large dataframes, or long-running compute. Returns a…

Marazii/research-co-pilot · 82 tokens