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.
npx skills add choxos/BiostatAgent --skill maic-methodologygit clone --depth 1 https://github.com/choxos/BiostatAgentWrote 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/skills/choxos/biostatagent/maic-methodology)<a href="https://agentmods.dev/skills/choxos/biostatagent/maic-methodology"><img src="https://agentmods.dev/badge/skills/choxos/biostatagent/maic-methodology/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/skills/choxos/biostatagent/maic-methodology"><img src="https://agentmods.dev/badge/skills/choxos/biostatagent/maic-methodology.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 | $0.00037 | $0.02175 |
| Opus 5.5 | $0.00015 | $0.00870 |
| Sonnet 5.5 | $0.00007 | $0.00435 |
| Haiku 4.5 | $0.00004 | $0.00217 |
Grade A, and why
maic-methodology 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 1mo 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MAIC Methodology
Comprehensive methodological guidance for conducting rigorous Matching-Adjusted Indirect Comparisons following NICE DSU TSD 18.
When to Use This Skill
- Deciding whether to use MAIC vs other ITC methods
- Selecting covariates for matching
- Interpreting weight diagnostics and ESS
- Choosing between anchored and unanchored MAIC
- Reviewing MAIC code or results
Fundamental Assumptions
Key Assumption: Conditional Constancy of Relative Effects
For Anchored MAIC:
- The relative treatment effect (vs common comparator) is the same across populations AFTER adjusting for effect modifiers
- This is untestable - relies on clinical judgment
- Requires all effect modifiers to be included in matching
No Unmeasured Effect Modifiers
Critical: MAIC assumes that adjusting for measured covariates
removes all population differences that modify treatment effects.
If there are unmeasured effect modifiers:
├── Anchored MAIC: Biased indirect comparison
└── Unanchored MAIC: Even more biased
There is NO WAY to test this assumption with available data.
Unanchored MAIC: Additional Assumptions
- All prognostic factors (not just effect modifiers) must be adjusted
- Absolute treatment effects are transportable across populations
- Much stronger, often implausible assumptions
- Should be avoided if anchored is possible
When to Use MAIC
MAIC is Appropriate When:
- IPD available for one trial (index trial)
- Only AgD available for comparator trial
- Important population differences exist between trials
- Effect modifiers are known and measured
- Sufficient overlap in covariate distributions
MAIC May Not Be Best When:
- Populations are very similar → Standard ITC may suffice
- Little covariate overlap → ESS will be very low
- Effect modifiers unknown → Cannot ensure adjustment
- Connected network exists → Consider NMA first
Covariate Selection
Selection Criteria
Include covariates that are:
├── Effect modifiers (interact with treatment effect)
│ - Based on clinical evidence
│ - Biological plausibility
│ - Subgroup analyses from trials
├── Available in both trials
│ - IPD: Individual-level data
│ - AgD: Published summary statistics
└── Different between trial populations
- Check if actually imbalanced
- No need to match on similar values
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.
- 1mo ago First seen · 325 lines · 37 tokens per session scan A bf54ff82ea90
maic-methodology is a skill published in the GitHub repository choxos/BiostatAgent (12 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 2,175 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
imaging-data-commons
Queries and downloads public cancer imaging data from NCI Imaging Data Commons. Supports IDC collection discovery, DICOM access, radiology (CT, MR, PET) and pathology AI datasets, metadata SQL, visualization, licensing, and citations. Uses public metadata and download routes without authentication; optional BigQuery…
lab-hardware-cad
Designs custom laboratory hardware as parametric build123d models and exports fabrication artifacts as STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a…
onekgpd
Queries the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which…
statistical-analysis
Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required…
experimental-design
Designs experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. Use whenever someone is planning a study, asks how to assign subjects/samples to groups, mentions randomization, blocking, stratification, controls…
hypothesis-generation
Formulates evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Used when turning observations or preliminary findings into transparent, testable research plans without…