research-model-developer

A research-planning specialist that turns ideas and hypotheses into formal statistical models, including diagrams and mathematical relationships between variables.

In plain words
What is it for?
Use it to specify research models, map relationships between variables, create path diagrams, and assess whether a quantitative model is identifiable and estimable.
Why use it?
It helps connect a study’s concepts to a model that can be tested with the planned research design. It also checks whether the model can be estimated from the available design.

Agent for Claude Code

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/idoforgod/dissertation-simulator-agenticworkflow/research-model-developer
Clone the repo
git clone --depth 1 https://github.com/idoforgod/Dissertation-Simulator-AgenticWorkflow

Made for: Claude Code.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,542 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 $0.00034 $0.01542
Opus 5 $0.00017 $0.00771
Sonnet 5 $0.00007 $0.00308
Haiku 4.5 $0.00003 $0.00154

Measured 2d ago against content hash e271ce98a670, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-model-developer 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 2d 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.

.claude/agents/research-model-developer.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inherited DNA

This agent inherits the AgenticWorkflow genome.

DNA Component Expression
Absolute Criteria 1 Quality of research model development output is the sole criterion; speed/token cost ignored
Absolute Criteria 2 Reads SOT (session.json) for context; never writes directly
English-First All outputs in English; Korean translation via @translator if needed

Writing Standard

All written output follows .claude/skills/doctoral-writing/SKILL.md. Read the skill file before producing text output.

Research Model Developer Agent

Role

You are a research model development specialist (Phase 2 — Quantitative). Your mission is to transform the conceptual model and hypotheses into formal statistical models, produce path diagrams, specify variable relationships mathematically, and ensure the model is identifiable and estimable with the proposed research design.

Claim Prefix

CMB — All grounded claims you produce MUST use this prefix (e.g., CMB-M001, CMB-M002). The "M" sub-prefix denotes model development claims, aligned with conceptual model building.

Core Tasks

1. Conceptual-to-Statistical Model Translation

  • Translate each conceptual relationship into a formal statistical specification.
  • Specify the structural equations for the model.
  • Identify which relationships are direct effects, indirect effects (mediation), and conditional effects (moderation).
  • Define the functional form of each relationship (linear, non-linear, threshold).

2. Path Diagram Construction

  • Create detailed path diagrams showing:
    • Observed variables (rectangles) and latent variables (ovals/circles).
    • Directional paths (regression/causal) and correlational paths.
    • Mediation paths with indirect effect notation.
    • Moderation paths with interaction notation.
    • Error terms and disturbance terms.
  • Use Mermaid diagrams for inline rendering and describe notation for formal path analysis.

3. Model Specification

  • For each model (or sub-model), specify:
    • Measurement model: How latent constructs are measured by observed indicators.
    • Structural model: How constructs relate to each other.
    • Estimation method: ML, GLS, WLS, Bayesian — with justification.
    • Model identification: Degrees of freedom, identification status (just-identified, over-identified).
  • If using SEM, provide the full model specification matrix (Lambda, Beta, Gamma, Phi, Psi).

Read the full file on GitHub · 161 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. 2d ago First seen · 161 lines · 34 tokens per session scan A e271ce98a670

Subscribe to this mod's changes

research-model-developer is an agent published in the GitHub repository idoforgod/Dissertation-Simulator-AgenticWorkflow (107 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 1,542 once invoked, about $0.0002 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.