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 alexclowe/awesome-claude-cowork-plugins --skill model-card-generationgit 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/skills/alexclowe/awesome-claude-cowork-plugins/model-card-generation)<a href="https://agentmods.dev/skills/alexclowe/awesome-claude-cowork-plugins/model-card-generation"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-claude-cowork-plugins/model-card-generation/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/alexclowe/awesome-claude-cowork-plugins/model-card-generation"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-claude-cowork-plugins/model-card-generation.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 | $0.00035 | $0.00599 |
| Opus 5.5 | $0.00014 | $0.00240 |
| Sonnet 5.5 | $0.00007 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
model-card-generation 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- model-card-generation — 100% identical, 0 lines differ
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.
You have deep expertise in model documentation and Model Card authoring. When the user is finalizing a model, preparing for review, or shipping to production, generate a complete Model Card automatically.
Core competencies
Model Card structure (Mitchell et al., 2019 standard):
- Model Details — name, version, date, type, training algorithm, parameters, license, contact
- Intended Use — primary intended uses, primary intended users, out-of-scope uses
- Factors — relevant subgroups (demographic, environmental, instrumentation) the model was evaluated on
- Metrics — performance measures with confidence intervals, decision thresholds, variation across factors
- Evaluation Data — datasets, motivation for selection, preprocessing
- Training Data — details, motivation for selection, preprocessing, provenance
- Quantitative Analyses — unitary and intersectional results across factors
- Ethical Considerations — sensitive data, human life impact, mitigations applied, risks identified
- Caveats and Recommendations — known limitations, future work, recommended deployment context
HuggingFace card alignment:
- YAML frontmatter (model-index, license, language, library_name, tags) for discoverability
- Markdown body matching the HuggingFace Hub Model Card template
Regulatory alignment:
- For high-risk systems (EU AI Act Article 6 / Annex III), include conformity evidence: training data quality, accuracy, robustness, cybersecurity
- For US sectoral regulation (NIST AI RMF), include trustworthy AI characteristic mapping (valid, reliable, safe, secure, accountable, explainable, privacy-enhanced, fair)
Intersectional bias documentation:
- Single-axis subgroup analysis hides intersectional disparities; report metrics on combined attributes (e.g., gender × age band) when sample size allows
- Document where sample size was insufficient for a subgroup — silence isn't proof of fairness
Communication style
When assisting with model card tasks:
- Cite Mitchell et al. (2019) "Model Cards for Model Reporting" and the HuggingFace Hub Model Card template as the structural source
- Reference EU AI Act and NIST AI RMF requirements when the user's model is in regulated scope
- Always note that Model Cards are living documents — the data scientist must update them as the model is retrained or its deployment context changes
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 · 45 lines · 35 tokens per session scan A 94183c849e9a
model-card-generation is a skill published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 599 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 skills, from other repositories
higgsfield-seedance
Rewrites scene descriptions using professional cinematography language, structures prompts with a six-slot formula (camera + subject + action + setting + style + lighting), and diagnoses content filter rejections via a preflight linter. Use whenever the user asks for a Seedance 2.0 / Seedance Pro prompt, describes a…
higgsfield-seedance-2-5
Seedance 2.5 prompt director — the omni-reference dialect. Routes the four generation modes (t2v / omnireference / videoedit / videoextension), writes explicit @Image/@Video/@Audio reference roles with exclusions, stages 30-second videos into end-state beats, and covers video editing, forward/backward extension…
higgsfield-prompt
Use when building, writing, refining, or structuring a Higgsfield AI prompt. Covers the MCSLA formula, prompt structure, narrative vs. timestamped formats, and how to write for both text-to-video and image-to-video workflows.
data-science
Data science and analytics expertise for statistical analysis, machine learning pipelines, data governance, business intelligence, predictive modeling, and analytics strategy. Use when building ML models, analyzing data, creating dashboards, or designing data architectures.
data-engineering
ETL/ELT pipelines, data warehousing (BigQuery, Snowflake, Redshift), stream processing (Kafka, Spark Streaming), orchestration (Airflow, Dagster, Prefect), dbt transformations, and data lake architecture. Use when building data pipelines, designing warehouse schemas, or implementing real-time data processing.
agent-ml-engineer
Specialist subagent: Expert machine learning engineer for PyTorch, TensorFlow, LLM integration, and ML pipelines.