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 agentmods add skills/matthewdigiuseppe/mstack/power-analysisnpx skills add matthewdigiuseppe/MStack --skill power-analysisgit clone --depth 1 https://github.com/matthewdigiuseppe/MStackWrote 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/matthewdigiuseppe/mstack/power-analysis)<a href="https://agentmods.dev/skills/matthewdigiuseppe/mstack/power-analysis"><img src="https://agentmods.dev/badge/skills/matthewdigiuseppe/mstack/power-analysis.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00974 |
| Opus 5 | $0.00028 | $0.00487 |
| Sonnet 5 | $0.00011 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
power-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mstack:power-analysis
Stage: design Voice: methodologist
When to invoke
After /mstack:design-research chooses a design. Before fielding. The prereg's "Sample" section pulls its target N from this skill's output.
Procedure
-
Load.
.mstack/hypotheses.md,.mstack/design-research.md,.mstack/lit-map.md(look up effect sizes from comparable studies). -
Decide the inputs.
- Effect-size target. Either:
- Smallest effect of substantive interest (SESOI), or
- Median effect from comparable studies in
lit-map.md. Be honest: published effects are inflated; aim conservative.
- α (typically 0.05, two-sided).
- Power (typically 0.80; for high-stakes preregistered work, 0.90).
- Design constants — clustering, ICC, attrition rate, blocking.
- Effect-size target. Either:
-
Write
code/00-power.R. Start from the bundled template — copy${CLAUDE_PLUGIN_ROOT}/skills/power-analysis/assets/00-power-template.R→code/00-power.R, then adapt the PARAMETERS block and the declared design to the actual study. It:- Defaults to
DeclareDesign(https://declaredesign.org/r/declaredesign/) — declare the model, inquiry, data strategy, and answer strategy, thendiagnose_design()over a grid of N and effect sizes. This is the default because it generalizes across experimental, survey, FE, panel, hierarchical, and conjoint designs, and forces the design assumptions to be made explicit. - Use
pwronly as a quick analytic sanity check for textbook cases (two-sample t-test, single-level proportion). UseSuperpoweronly for factorial ANOVA designs where DeclareDesign would be overkill. Note the fallback choice and its justification in the script header. - For experiments / surveys: report N for power = 0.80 and MDE at the user's planned N.
- For observational with FE: simulate to find effective N for identification.
- Saves a sensitivity curve (power vs. effect size; MDE vs. N) to
output/figures/power-sensitivity.pdf.
- Defaults to
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 69 lines · 56 tokens per session scan A a8a68825f005
power-analysis is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 7d ago), licensed MIT. It adds 56 tokens to every session and 974 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 2026-08-30.
Other skills, from other repositories
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
nature-statistics
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…
evaluating-with-leakage-gates
Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.