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 tao12345666333/ankaloop --skill ai-engineergit clone --depth 1 https://github.com/tao12345666333/ankaloopWrote 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/tao12345666333/ankaloop/ai-engineer)<a href="https://agentmods.dev/skills/tao12345666333/ankaloop/ai-engineer"><img src="https://agentmods.dev/badge/skills/tao12345666333/ankaloop/ai-engineer/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/tao12345666333/ankaloop/ai-engineer"><img src="https://agentmods.dev/badge/skills/tao12345666333/ankaloop/ai-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.01435 |
| Opus 5 | $0.00010 | $0.00718 |
| Sonnet 5 | $0.00004 | $0.00287 |
| Haiku 4.5 | $0.00002 | $0.00144 |
Grade A, and why
ai-engineer 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 11d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Engineer Skill
Machine Learning Development
Model Development Lifecycle
- Problem Definition: Business objective framing
- Data Collection: Gathering relevant datasets
- Data Preprocessing: Cleaning, transformation, feature engineering
- Model Selection: Algorithm choice and evaluation
- Training: Model fitting and hyperparameter tuning
- Evaluation: Metrics validation and testing
- Deployment: Production integration
- Monitoring: Performance tracking and drift detection
Deep Learning Frameworks
- TensorFlow/Keras: Production-ready deep learning
- PyTorch: Research-friendly dynamic graphs
- JAX: Functional programming and auto-diff
- FastAI: High-level deep learning API
Classical Machine Learning
- Scikit-learn: Traditional ML algorithms
- XGBoost/LightGBM: Gradient boosting frameworks
- Pandas/NumPy: Data manipulation and computation
MLOps and Model Deployment
Model Serving Options
- REST APIs: Flask, FastAPI, Django
- gRPC: High-performance RPC
- Serverless: AWS Lambda, Google Cloud Functions
- Containerized: Docker, Kubernetes
- Edge Deployment: ONNX, TensorFlow Lite
Model Versioning
- MLflow: Experiment tracking and model registry
- DVC: Data version control
- Git LFS: Large file storage
- Weights & Biases: Experiment tracking
Monitoring and Observability
- Prometheus/Grafana: Metrics collection and visualization
- ELK Stack: Logging and search
- Model Drift Detection: Data and concept drift monitoring
- A/B Testing: Model performance comparison
Data Engineering for AI
Data Pipeline Architecture
- Batch Processing: Airflow, Luigi, Prefect
- Stream Processing: Kafka, Apache Flink
- ETL/ELT: Data transformation patterns
- Data Lakes: Storage strategies for unstructured data
Feature Engineering
- Feature Stores: Feast, Hopsworks
- Real-time Features: Streaming feature computation
- Feature Monitoring: Data quality and validation
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.
- 11d ago First seen · 206 lines · 20 tokens per session scan A 32b03149e36c
ai-engineer is a skill published in the GitHub repository tao12345666333/ankaloop (48 stars, last pushed 12d ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,435 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
v4-best-practices
Use when working with deepseek-v4-pro or deepseek-v4-flash in thinking mode on multi-step or plan-driven tasks. Provides rules to prevent stale references, unverified plan assumptions, and vague plan output.
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.
nightly-session-watch
Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still recording. Triages each finding to the specialist skill that diagnoses it. Use for an unattended daily health check, or on…
memory-status
Show MemPalace memory system status — drawer counts, wings, rooms, knowledge graph stats, and embedding model state.
code-review-pi
Review code for quality, run linters, check test coverage, fix issues, and enforce gates. Save the final report to ./specs/issues/003-code-review-pi/PROMPT.md. Use before committing changes.
task-model-router
Route different task types to the best-fit model automatically. Chat → fast small model, coding → strong reasoning model, images → vision model, long documents → large context model. Use when: (1) Agent handles mixed tasks (chat + code + vision), (2) Want to optimize speed and cost by matching task to model, (3) User…