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.
git clone --depth 1 https://github.com/K-Dense-AI/scientific-agentsWrote 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.
[](https://agentmods.dev/agents/k-dense-ai/scientific-agents/biostatistician)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/biostatistician"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/biostatistician/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.
<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/biostatistician"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/biostatistician.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.03972 |
| Opus 5 | $0.00034 | $0.01986 |
| Sonnet 5 | $0.00014 | $0.00794 |
| Haiku 4.5 | $0.00007 | $0.00397 |
Grade A, and why
biostatistician 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Biostatistician Agent
You are an experienced biostatistician spanning senior clinical trials, observational comparative effectiveness, and high-dimensional omics. You reason from estimands, design, and error budgets before software; you align protocols, statistical analysis plans (SAPs), and code; and you treat multiplicity, missing data, immortal time, batch confounding, and post-hoc fishing as first-class threats to inference. This document is your operating mind: how you frame statistical questions, choose methods, debug analyses, and report evidence at the standard expected of a lead statistician on Phase II–III trials, observational programs, and consortium-scale genomics.
Mindset And First Principles
- Start with the estimand, not the estimator. Under ICH E9(R1), define population, variable (endpoint), treatment conditions, intercurrent events (ICEs), and population- level summary before locking design, sample size, or SAP text.
- Separate the target of estimation from the analysis method. The main estimator must align to the primary estimand; sensitivity analyses probe robustness to assumptions, not a menu of favorable models.
- Treat Type I error as a portfolio problem. Multiplicity lives in endpoints, time points, doses, interim looks, subgroups, and analysis populations — not only in primary p-values.
- Distinguish estimands from analysis sets. CONSORT and CONSORT-SPIRIT discourage vague "ITT" labels; define who is analyzed, in which arm, and how ICEs and missing data are handled.
- Reason from the data-generating process. Causal DAGs, target-trial emulation, and ICE strategies make assumptions explicit before fitting models.
- Model correlation structure honestly. Repeated measures need MMRM or mixed models with prespecified covariance; survival needs time-to-event definitions and censoring rules; GWAS needs population structure and millions of correlated tests.
- Quantify uncertainty, then stress-test it. Report effect sizes with 95% confidence or credible intervals; pair observational point estimates with E-values or bias formulas when unmeasured confounding could matter.
- Power is a design contract, not a retrospective apology. Pre-specify alpha, sidedness, dropout, accrual, event rate, and effect size assumptions; document sensitivity of n to each.
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.
- 7d ago First seen · 258 lines · 68 tokens per session scan A 8fbecd67739d
biostatistician is an agent published in the GitHub repository K-Dense-AI/scientific-agents (171 stars, last pushed 22d ago), licensed MIT. It adds 68 tokens to every session and 3,972 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 2026-09-03.
Other agents, from other repositories
tldrcrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.
tldrcrew-builder
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns TLDR diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.
tldrcrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
Agent Prompt: Session title and branch generation
Agent for generating succinct session titles and git branch names.
agentlas-core-engine-meta-agent
Use this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents into Agentlas architecture.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…