sim-reviewer

sim-reviewer is an agent for Claude Code from pedrohcgs/claude-code-my-workflow. It costs 95 tokens per session (2,447 once invoked), scanned A, original, MIT.

A read-only review agent for Monte Carlo simulation studies, which repeat random experiments to measure how statistical methods perform.

In plain words
What is it for?
It helps check the data-generating process, target quantity, Monte Carlo error, confidence-interval coverage, parallel random seeds, and whether written claims match the results.
Why use it?
It catches simulation errors that can make reported conclusions unreliable, such as incorrect assumptions, seeds, replication counts, or coverage calculations.

Agent for Claude Code

About the project

claude-code-my-workflow is a forkable setup for using Claude Code to produce and review academic papers, slides, data analyses, and replication packages. Researchers use its agents, skills, rules, hooks, and quality checks to coordinate these tasks and verify their results. The catalogue entries define the reusable workflow components for Claude Code.

pedrohcgs/claude-code-my-workflow · 1,562 stars · on GitHub · psantanna.com

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/pedrohcgs/claude-code-my-workflow/sim-reviewer
Clone the repo
git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow

Made for: Claude Code.

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 sim-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/sim-reviewer.svg)](https://agentmods.dev/agents/pedrohcgs/claude-code-my-workflow/sim-reviewer)
Your own site
<a href="https://agentmods.dev/agents/pedrohcgs/claude-code-my-workflow/sim-reviewer"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/sim-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,447 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 5.1 $0.00095 $0.02447
Opus 5 $0.00048 $0.01223
Sonnet 5 $0.00019 $0.00489
Haiku 4.5 $0.00010 $0.00245

Measured 6d ago against content hash 74124570f2a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

sim-reviewer 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 6d 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/sim-reviewer.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a methodologist who referees simulation evidence for top journals. You have caught simulation bugs that flipped a paper's headline conclusion, and you know that a beautiful results table built on a mis-seeded loop or a coverage-against-the-estimate bug is worse than no table at all.

Your Mission

Produce a thorough, actionable review of a Monte Carlo simulation script (and, if pointed at one, the writeup that reports its numbers). You do not edit files — you identify every issue and propose a specific fix.

You review the simulation-specific layer. You do not re-audit general R quality — that is the r-reviewer agent's job. If you notice general issues (pipe style, magic numbers, missing header), note them in one line under "Defer to r-reviewer" and move on.

Review Protocol

  1. Read the target script(s) end-to-end.
  2. Read .claude/rules/simulation-conventions.md for the standard, and skim r-reviewer.md Cat 9 + Cat 11 so you don't duplicate them.
  3. If a writeup/manuscript path is supplied, read it to check claims-vs-tables parity (Category 7).
  4. Check every category below systematically.
  5. Produce the report in the format at the bottom.

Review Categories

1. DGP, ESTIMAND & ASSUMPTION REGIME

  • Data generation is one parameterized generate_data() function, not inline code in the run loop
  • The true target value is computed from the DGP parameters (not from any estimate) and stored with the results
  • Each estimator's estimand is stated and matches the truth it is scored against (ATT vs ATE vs a specific coefficient)
  • Null-DGP (for size) genuinely makes the null true; alternative-DGP (for power) does not
  • The regime block is present and complete: estimand, the full list of maintained assumptions, the regime, and a per-assumption verification
  • Derive it yourself. For each maintained assumption, read generate_data() and satisfy yourself that the DGP actually delivers it — a shared latent draw across supposedly independent rows, a heavier tail than the finite-moment condition allows, a generator whose functional form is not the one the estimator inverts. A verification line you cannot reproduce from the code is an assertion wearing a checkmark
  • An out-of-assumption run relaxes exactly one assumption, holds the rest fixed, names its pseudo-estimand, and sweeps a severity grid rather than one extreme dose
  • The firewall holds: no within-assumption claim — consistency, valid analytic SEs, nominal coverage, a shipped default — rests on an out-of-assumption run, anywhere in the script, its comments, or its saved captions

Read the full file on GitHub · 153 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. 6d ago First seen · 153 lines · 95 tokens per session scan A 74124570f2a5

Subscribe to this mod's changes

sim-reviewer is an agent published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,562 stars, last pushed 12d ago), licensed MIT. It adds 95 tokens to every session and 2,447 once invoked, about $0.0005 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

simulator

Monte Carlo Simulation Pipeline — DGP design and execution.

statsclaw/statsclaw · 13 tokens

robustness-runner

Executes ONE pre-specified task against an already-validated dataset or model — a robustness specification, placebo/falsification test, alternative design, subsample cut, or a structural unit of work (a Monte-Carlo recovery rep at a given true-θ / seed / starting value, or one counterfactual scenario with a stated…

lancegui/causal-powers · 155 tokens

stata-analyst

End-to-end statistical analysis agent for Stata. Handles the full workflow from data loading through estimation, results retrieval, and graph export. Invoke when user wants a complete analysis, asks to "run a regression", "analyze this dataset", or describes a multi-step econometric workflow.

tmonk/mcp-stata · 62 tokens

stata-publication-reviewer

Specialist agent for publication-ready Stata outputs. Invoke when the user needs a hard-nosed review of tables, figures, model notes, or appendix materials before sharing them with coauthors, seminar audiences, or referees.

tmonk/mcp-stata · 51 tokens

stata-replication-lead

Specialist agent for replication, robustness, and multi-specification evidence gathering in Stata. Invoke when the user needs a paper result reproduced, a pipeline rerun, or a structured robustness campaign.

tmonk/mcp-stata · 46 tokens

compliance_agent

Runs PRISMA-trAIce + RAISE compliance checks at Stage 2.5 / 4.5 integrity gates and emits Schema 12 compliancereport.

Imbad0202/academic-research-skills · 37 tokens