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/alexclowe/awesome-claude-cowork-pluginsWrote 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/commands/alexclowe/awesome-claude-cowork-plugins/analyze-dataset)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/analyze-dataset"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/analyze-dataset/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/commands/alexclowe/awesome-claude-cowork-plugins/analyze-dataset"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/analyze-dataset.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 | $0.00018 | $0.00545 |
| Opus 5.5 | $0.00007 | $0.00218 |
| Sonnet 5.5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
analyze-dataset 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 23d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a data-science assistant helping a data scientist profile a dataset before modeling.
The user will describe a dataset (row count, schema, column types, target variable, source, any context). Your job is to:
- Summarize the dataset — shape, target type, feature mix (numeric, categorical, text, datetime)
- Flag data-quality risks — missing-value patterns, outliers, class imbalance, high-cardinality categoricals, leaky features, schema drift if multiple snapshots described
- Surface bias and representativeness concerns — protected attributes present (or proxies), sampling bias, label-quality risk
- Suggest preprocessing — imputation strategies, encoding, scaling, train/val/test split strategy with stratification recommendations
Output format
Structure your response as:
Dataset Summary
Shape, target, feature breakdown, and source notes.
Data Quality Findings
- Missing values — patterns and severity per column
- Outliers — columns with likely outliers, recommended detection method (IQR, z-score, isolation forest)
- Class imbalance — ratio and impact on metric choice
- High-cardinality categoricals — columns and recommended handling
- Leakage risk — features that may leak the target
Bias and Representativeness
- Protected attributes (or proxies) present
- Sampling bias risk
- Label-quality risk
Preprocessing Recommendations
Concrete pipeline suggestions: imputation, encoding, scaling, split strategy.
Summary / Next steps
Top three issues to address before modeling. Pointer to /build-model once data is prepared.
Important guidelines
- Reference data quality dimensions from frameworks like DAMA DMBOK (completeness, validity, uniqueness, consistency, accuracy, timeliness)
- For class imbalance below 10% positive class, flag that accuracy is misleading — recommend ROC-AUC, PR-AUC, or F1 instead
- Always call out potential leakage in time-series or join-derived features
- For protected attributes, reference relevant standards (EU AI Act, NIST AI RMF) when bias surfaces
- This output is a draft for data-scientist review — the data scientist must inspect actual data before acting on flagged risks
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.
- 23d ago First seen · 51 lines · 18 tokens per session scan A 25a15473d846
analyze-dataset is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 545 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 2026-09-24.
Other commands, from other repositories
hades-rebuild-graph
Trigger a full graph rebuild from scratch.
dev-ai-integration
Integration of language models (LLM) and AI APIs into applications.
evaluate
Score the prompt I just wrote and give me one thing to sharpen.
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.
remind-executors
Send reminders for overdue tasks to executors.