sample-size

A workflow for finding how many participants or events a study needs to reach a chosen probability of detecting a real treatment effect.

In plain words
What is it for?
Use it to define study requirements, search for a suitable participant or event count, validate the result with simulation, compare scenarios, and produce reproducible R code.
Why use it?
It avoids relying on a guessed sample size by testing candidate sizes against the required power across one or more possible treatment effects.

Command

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 commands/choxos/biostatagent/sample-size
Clone the repo
git clone --depth 1 https://github.com/choxos/BiostatAgent
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 625 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 $0.00014 $0.00625
Opus 5 $0.00007 $0.00313
Sonnet 5 $0.00003 $0.00125
Haiku 4.5 $0.00001 $0.00063

Measured 2d ago against content hash a6884667e8ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sample-size 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.

plugins/clinical-trial-simulation/commands/sample-size.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sample Size Determination Workflow

Overview

Find the minimum sample size (or event count) required to achieve target power across specified treatment effect scenarios.

Workflow Phases

Phase 1: Requirements

Phase 2: Search Strategy

Methods:

  • Binary search: Efficient for single scenario
  • Grid search: Better for multiple scenarios
  • Compound criteria: Min power across scenarios ≥ target

Phase 3: Validation

Success Criteria

  • Sample size found meeting target power
  • Results validated with high-precision simulation
  • Sensitivity across scenarios documented
  • Clear recommendation with rationale

Final Deliverables

  1. Recommended sample size with justification
  2. Power at recommended N for all scenarios
  3. Sample size sensitivity table
  4. Optimal interval analysis
  5. R code for replication

Read the full file on GitHub · 94 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 · 94 lines · 14 tokens per session scan A a6884667e8ad

Subscribe to this mod's changes

sample-size is a command published in the GitHub repository choxos/BiostatAgent (11 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 625 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.