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/danielrosehill/claude-data-analyst-plugin/standard-deviationnpx skills add danielrosehill/Claude-Data-Analyst-plugin --skill standard-deviationgit clone --depth 1 https://github.com/danielrosehill/Claude-Data-Analyst-pluginWrote 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/danielrosehill/claude-data-analyst-plugin/standard-deviation)<a href="https://agentmods.dev/skills/danielrosehill/claude-data-analyst-plugin/standard-deviation"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-data-analyst-plugin/standard-deviation.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 | $0.00064 | $0.01332 |
| Opus 5 | $0.00032 | $0.00666 |
| Sonnet 5 | $0.00013 | $0.00266 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
standard-deviation 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standard Deviation
Compute standard deviation for one or more numeric columns, plus the context needed to actually use the number: sample vs. population formula, comparison to related spread measures, and warnings when SD is the wrong summary.
Inputs
- Path to a dataset (CSV / Parquet / Excel / DuckDB table).
- Optional: specific columns. Default: all numeric columns.
- Optional: grouping column — compute SD within each group.
- Optional: formula —
sample(n-1 denominator, default) orpopulation(n denominator). Default is sample, because almost all real data is a sample of something.
Recommended CLI tooling
duckdb— built-instddev_samp(),stddev_pop(),variance(),quantile_cont().uv run --with pandas --with scipy python -c '...'— MAD, trimmed SD, bootstrap CI for SD.
Procedure
Step 1 — Pick the right columns
For each candidate numeric column:
- Skip if it's an ID, code, or row index (monotonic increasing, all-unique integer). SD is meaningless.
- Skip if it's a boolean-coded 0/1 column unless the user asks (SD = sqrt(p(1-p)), rarely the useful summary).
- Include continuous measurements, counts, ratios, currency, scores.
Report any column you skipped and why.
Step 2 — Compute the core statistics
For each column (and each group, if grouping):
| Statistic | What it tells you |
|---|---|
n (non-null count) |
Sample size the SD is based on. |
mean, median |
Centre. If they differ substantially, distribution is skewed. |
stddev_samp |
Standard deviation, n-1 denominator. Default report value. |
variance_samp |
Square of SD. Report if user explicitly wants it. |
min, max |
Range. Flag if max is >10× the 99th percentile — outlier pulling SD up. |
q25, q75, IQR |
Robust spread — compare to SD. |
mad (median absolute deviation) |
Robust SD analogue. MAD × 1.4826 ≈ SD if data is normal. |
cv (coefficient of variation) = SD / mean |
Dimensionless spread. Only meaningful when mean > 0 and the column has a natural zero (not temperatures-in-C). |
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 · 98 lines · 64 tokens per session scan A 6a72db61fbea
standard-deviation is a skill published in the GitHub repository danielrosehill/Claude-Data-Analyst-plugin (11 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 1,332 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
ppt-analysis
PPT (.pptx/.ppt) 全量解析。覆盖：所有 slide 文本/表格/图表提取、嵌入图片 caption、纯图片 slide 渲染识别、数据标签提取。.
large-file-conditional-formatting
根据Excel总行数自动切换Parquet加速读取，计算特定维度的时间序列平均值，并使用openpyxl输出带有条件格式（如低于均值标绿）和自定义样式的分析报告。.
trend-analysis
基于多维度数据进行分级评估与趋势预测，通过设定差异化增长率计算预测值，并生成对比可视化图表，适用于绩效评估、目标设定等场景。.
outlier-detection-and-quality-assessment
执行全面的异常值检测与数据质量评估，利用 IQR 方法识别异常值并结合偏度、峰度分析数据分布特征，适用于非正态分布数据的预处理阶段。.
pie-chart-data-analysis
Step1 读取文件并统计所有 Sheet 的行数，确认数据规模以决定处理策略。.
multi-sheet-reading-and-analysis
用于读取多工作表Excel文件，动态评估数据量以启用Parquet大文件优化，并执行正则清洗、分类汇总、线性拟合及生成带格式的图表与结果文件。.