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 ChrisGVE/localdata-mcp --skill hypothesis-testgit clone --depth 1 https://github.com/ChrisGVE/localdata-mcpWrote 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/chrisgve/localdata-mcp/hypothesis-test)<a href="https://agentmods.dev/skills/chrisgve/localdata-mcp/hypothesis-test"><img src="https://agentmods.dev/badge/skills/chrisgve/localdata-mcp/hypothesis-test/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/chrisgve/localdata-mcp/hypothesis-test"><img src="https://agentmods.dev/badge/skills/chrisgve/localdata-mcp/hypothesis-test.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 | $0.00031 | $0.00657 |
| Opus 5 | $0.00015 | $0.00329 |
| Sonnet 5 | $0.00006 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
hypothesis-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hypothesis Test
Select and run the appropriate statistical test based on data characteristics, with full assumption checking and effect size reporting.
Steps
-
Explore the data. Call
describe_databasewith the database name from$ARGUMENTS. Identify the columns to compare and the grouping variable. Callget_data_quality_reportto check for missing values that could bias results. -
Extract and inspect. Call
execute_queryto pull the relevant columns. Determine:- Number of groups (2 vs 3+)
- Sample size per group
- Whether observations are paired or independent
- Whether the outcome is continuous or categorical
-
Check assumptions. Call
execute_queryto compute summary statistics per group (mean, median, sd, skewness). Assess:- Normality: skewness beyond +/-1 or small samples (n < 30) suggest non-parametric tests
- Variance homogeneity: ratio of largest to smallest group SD above 2 suggests unequal variances
- Sample balance: highly unequal group sizes affect test power
-
Select and run the test. Based on the assessment:
- 2 groups, normal, equal variance: call
analyze_hypothesis_testwith independent t-test - 2 groups, normal, unequal variance: call
analyze_hypothesis_testwith Welch's t-test - 2 groups, non-normal: call
analyze_hypothesis_testwith Mann-Whitney U - 2 groups, paired: call
analyze_hypothesis_testwith paired t-test or Wilcoxon signed-rank - 3+ groups: call
analyze_anovawith appropriate post-hoc tests - Categorical outcome: call
analyze_hypothesis_testwith chi-squared test
- 2 groups, normal, equal variance: call
-
Compute effect sizes. Call
analyze_effect_sizeswith the same data. Report Cohen's d (two groups), eta-squared (ANOVA), or Cramer's V (chi-squared). Classify as small, medium, or large. -
Interpret results. Present:
- Hypotheses stated in plain language
- Test selected and why (citing assumption check results)
- Test statistic, degrees of freedom, p-value
- Effect size with confidence interval
- One-sentence conclusion: what this means for the question at hand
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.
- 12d ago First seen · 45 lines · 31 tokens per session scan A 398e8d5dad7f
hypothesis-test is a skill published in the GitHub repository ChrisGVE/localdata-mcp (4 stars, last pushed 28d ago), licensed Apache-2.0. It adds 31 tokens to every session and 657 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
wingman-mcp
Add persistent, interactive task plan management to your agent. Wingman tracks plans and tasks across a long conversation — Claude creates plans, ticks tasks after completing work, and a live panel renders inline in the chat. Install the MCP server first, then use these tools to manage plans and tasks throughout any…
statistical-analyzer
Run statistical analyses — hypothesis tests, regressions, ANOVA, confidence intervals, and power calculations.
skills-installer
Install, list enabled, validate, or package LiveAgent skills. Use when you need to inspect the skills enabled in the current conversation, import a local skill directory or package, search/install from ClawHub, install from a GitHub repo/tree URL, or reconcile conflicts during an upgrade.
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
environmental-analysis
Research climate, sun, flood, seismic, soil, contamination, and topography for a site. Use for environmental site analysis or hazard questions tied to a location.
liucixin-perspective
A science-fiction writing aid focused on using scientific ideas to imagine large-scale consequences for people and civilizations. It combines technical detail with stories spanning different time periods, places, and levels of society.