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 instructions/duqueom/ml-mlops-portfolio/agents-mdgit clone --depth 1 https://github.com/DuqueOM/ML-MLOps-PortfolioWrote 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/instructions/duqueom/ml-mlops-portfolio/agents-md)<a href="https://agentmods.dev/instructions/duqueom/ml-mlops-portfolio/agents-md"><img src="https://agentmods.dev/badge/instructions/duqueom/ml-mlops-portfolio/agents-md.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 5.1 | $0.08440 | $0.08440 |
| Opus 5 | $0.04220 | $0.04220 |
| Sonnet 5 | $0.01688 | $0.01688 |
| Haiku 4.5 | $0.00844 | $0.00844 |
Grade C, and why
ML-MLOps-Portfolio AGENTS.md scanned grade C with 1 finding 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| Scaffold new service (`new-service.sh`) | AUTO | Reversible via `rm -rf` | How it starts
The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — ML Service Template
Project Identity
ML Service Template: Agent-driven framework for building and maintaining production-grade ML systems with multi-cloud deployment (GKE + EKS), comprehensive observability, and enterprise CI/CD. Every architectural decision documented in ADRs with measured trade-offs.
- Stack: Python 3.11+, scikit-learn, XGBoost, LightGBM, FastAPI, Docker, Kubernetes, Terraform, GitHub Actions
- Clouds: GCP (primary) + AWS (secondary parity)
- Tracking: MLflow (self-hosted on K8s)
- Monitoring: Prometheus + Grafana + AlertManager + Evidently
- Data: DVC (GCS + S3 remotes), Pandera validation
Agent Architecture
LAYER 1: ORCHESTRATOR
→ Receives high-level requests ("create a new ML service for [domain]")
→ Determines which specialist agents are needed and in what order
→ Manages task dependencies (cannot deploy before training completes)
→ Calibrates engineering level to project scale (no under/over-engineering)
LAYER 2: SPECIALIST AGENTS (build phase)
├── Agent-EDAProfiler Dataset exploration, baseline distributions, leakage pre-audit
├── Agent-DataValidator Pandera schemas, DVC versioning, leakage checks
├── Agent-MLTrainer Training pipeline, model selection, Optuna tuning
├── Agent-APIBuilder FastAPI app, async inference, SHAP integration
├── Agent-DockerBuilder Optimized Dockerfile, init container pattern
├── Agent-K8sBuilder K8s manifests, HPA, Kustomize overlays
├── Agent-TerraformBuilder IaC for GCP + AWS resources
├── Agent-CICDBuilder GitHub Actions workflows
├── Agent-SecurityAuditor Secret scans, IAM least-privilege, image signing, SBOM
├── Agent-MonitoringSetup Prometheus metrics, Grafana dashboards, alerts
├── Agent-DriftSetup PSI thresholds, CronJob, heartbeat alerts
├── Agent-DocumentationAI ADRs, READMEs, runbooks
└── Agent-TestGenerator Unit, integration, regression, load tests
LAYER 3: MAINTENANCE AGENTS (operate phase)
├── Agent-DriftMonitor PSI scores → alerts → retraining triggers
├── Agent-RetrainingAgent Executes retraining with quality gates
├── Agent-CostAuditor Reviews costs against budget
└── Agent-DocUpdater Keeps documentation in sync with code
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.
- 5d ago First seen · 547 lines · 8,440 tokens per session scan C 2ca22e64d2cf
ML-MLOps-Portfolio AGENTS.md is an instructions file published in the GitHub repository DuqueOM/ML-MLOps-Portfolio (5 stars, last pushed 4d ago), licensed MIT. It adds 8,440 tokens to every session, about $0.0422 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
mlflow CLAUDE.md
Claude Code instructions for mlflow/mlflow, covering claude.md, knowledge cutoff note, code style principles, repository overview and quick start: development server.
mlflow code-review.instructions.md
Instructions for mlflow/mlflow, covering code review instructions, knowledge cutoff, verify when it's cheap and do not comment on.
zenml CLAUDE.md
Claude Code instructions for zenml-io/zenml, covering zenml claude code guidelines, project structure, use zenml docs via mcp, code style & quality standards and commenting policy — explain why, not what.
mlflow github-actions.instructions.md
Instructions for mlflow/mlflow: For workflow style conventions, see .claude/rules/github-actions.md.
mlflow python.instructions.md
Instructions for mlflow/mlflow: For style conventions and code examples, see .claude/rules/python.md.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.