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/gonzalezpazmonica/pm-workspaceWrote 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/gonzalezpazmonica/pm-workspace/banking-mlops-audit)<a href="https://agentmods.dev/commands/gonzalezpazmonica/pm-workspace/banking-mlops-audit"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/pm-workspace/banking-mlops-audit/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/gonzalezpazmonica/pm-workspace/banking-mlops-audit"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/pm-workspace/banking-mlops-audit.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 | $0.00028 | $0.01228 |
| Opus 5.5 | $0.00011 | $0.00491 |
| Sonnet 5.5 | $0.00006 | $0.00246 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
banking-mlops-audit 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 1mo 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:
- banking-mlops-audit — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/banking-mlops-audit [--project {nombre}] [--focus pipeline|risk|xai|scoring]
🏦 Audita tu pipeline MLOps bancario: versionado, drift, explicabilidad, riesgo de modelos.
Cargar perfil y skill
Grupo: Architecture & Tech — cargar identity.md + projects.md + preferences.md.
Skill: @.opencode/skills/banking-architecture/SKILL.md
Parámetros
--project {nombre}— Proyecto (default: activo)--focus {area}— Focalizar:pipeline|risk|xai|scoring(default: all)
Flujo
Paso 1 — Detectar stack MLOps
Buscar en config, deps y código:
- Model registry: MLflow, Weights & Biases, SageMaker, Vertex AI
- Training: PyTorch, TensorFlow, scikit-learn, XGBoost, LightGBM
- Monitoring: Evidently, WhyLabs, NannyML, Great Expectations
- Serving: Seldon, KServe, TorchServe, SageMaker Endpoint
- GenAI: LangChain, LlamaIndex, vector DBs (Pinecone, Weaviate, pgvector)
- Orchestration: Airflow, Kubeflow, Prefect
Paso 2 — Auditar CI/CD/CT Pipeline
| Check | Esperado | Criticidad |
|---|---|---|
| Model versioning | Cada modelo versionado con metadata | CRITICAL |
| Data versioning | Dataset snapshots reproducibles | CRITICAL |
| Automated training (CT) | Retrain trigger definido | WARNING |
| Automated testing | Unit + integration + model quality | CRITICAL |
| Staging environment | Modelos probados antes de prod | CRITICAL |
| Rollback mechanism | Volver a versión anterior en <5min | CRITICAL |
| A/B testing / Shadow mode | Comparar modelos en paralelo | WARNING |
Paso 3 — Auditar Model Risk Management
Basado en SR 11-7 (Federal Reserve) y EBA Guidelines:
- Model inventory: ¿Existe registro de todos los modelos en producción?
- Model documentation: ¿Cada modelo tiene model card con: propósito, datos, métricas, limitaciones?
- Validation: ¿Modelos validados por equipo independiente?
- Performance monitoring: ¿Métricas monitoreadas (AUC, precision, recall, calibration)?
- Drift detection: ¿Data drift y concept drift monitoreados?
- Challenger models: ¿Existe benchmark contra modelo challenger?
- Materiality assessment: ¿Clasificación por impacto (Tier 1/2/3)?
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.
- 1mo ago First seen · 129 lines · 28 tokens per session scan A ba2a3c931414
banking-mlops-audit is a command published in the GitHub repository gonzalezpazmonica/pm-workspace (50 stars, last pushed 7d ago), licensed MIT. It adds 28 tokens to every session and 1,228 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 2026-09-03.
Other commands, from other repositories
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
laravel-ai-sdk
Build AI features with the first-party Laravel AI SDK (Laravel 13+); use the laravel:ai-sdk skill exactly as written.
vlm-ocr-evaluation
Run the vlm-ocr skill in its evaluate phase: compare candidate OCR systems against a stratified human-transcribed ground-truth sample and pick a model on measured CER/WER before committing to a bulk run.
dare-llm-integration
Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.