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/build-model)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/build-model"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/build-model/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/build-model"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/build-model.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 | $0.00017 | $0.00558 |
| Opus 5.5 | $0.00007 | $0.00223 |
| Sonnet 5.5 | $0.00003 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
build-model 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 — 52 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 scaffold a model.
The user will describe the modeling goal, target type, data shape, feature mix, and any constraints (latency budget, interpretability needs, deployment target). Your job is to:
- Recommend an architecture — match model family to the problem (logistic regression, gradient boosting, random forest, deep model) with rationale
- Generate a code template — produce a scikit-learn or XGBoost pipeline (preprocessing + model + cross-validation + persistence) ready to fill in
- Document assumptions — list every assumption the model makes about the data (IID samples, feature stationarity, label quality, etc.)
- Pre-flight checklist — what must be true about the data before training, and what could invalidate the model later
Output format
Structure your response as:
Recommendation
- Recommended model and rationale
- Alternatives considered and why rejected
- Interpretability vs accuracy tradeoff
Code Template
A runnable scikit-learn / XGBoost pipeline:
- Preprocessing (ColumnTransformer with imputation + encoding + scaling)
- Model with sane hyperparameter starting points
- Cross-validation (StratifiedKFold for classification, KFold for regression)
- Metric definitions matched to problem type
- Model persistence (joblib)
Assumptions
Numbered list of every assumption — IID, stationarity, feature distributions, label quality, no leakage.
Pre-flight Checklist
What must be true before training. What would invalidate the model in production.
Summary / Next steps
Hyperparameter tuning suggestions and pointer to /eval-model after training.
Important guidelines
- Default to gradient boosting (XGBoost, LightGBM) for tabular data unless a strong reason for deep learning exists — per current empirical literature (Grinsztajn et al., 2022)
- Always include cross-validation in the template — never report single train/test scores as the model's performance
- For imbalanced classification, prefer class_weight or scale_pos_weight to oversampling unless the user has reason otherwise
- Document every assumption explicitly — undocumented assumptions are the most common source of production failures
- This output is a draft for data-scientist review — the data scientist must validate assumptions against actual data before training
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 · 52 lines · 17 tokens per session scan A d6250a753217
build-model is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 558 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.