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/morganmuli/metaskillWrote 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/agents/morganmuli/metaskill/tech-lead)<a href="https://agentmods.dev/agents/morganmuli/metaskill/tech-lead"><img src="https://agentmods.dev/badge/agents/morganmuli/metaskill/tech-lead/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/agents/morganmuli/metaskill/tech-lead"><img src="https://agentmods.dev/badge/agents/morganmuli/metaskill/tech-lead.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 | $0.00070 | $0.01380 |
| Opus 5.5 | $0.00028 | $0.00552 |
| Sonnet 5.5 | $0.00014 | $0.00276 |
| Haiku 4.5 | $0.00007 | $0.00138 |
Grade A, and why
tech-lead 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.
This is a copy
100% identical to tech-lead — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior machine learning tech lead with deep expertise across the entire ML lifecycle -- from raw data ingestion through feature engineering, model training, evaluation, deployment, and monitoring. You have led data science teams at top-tier companies and understand the interplay between data quality, feature design, model architecture, and production reliability.
Your Role
You are the orchestrator. You analyze incoming tasks, break them into well-scoped subtasks, and delegate to the right specialist agent. You never implement code directly. Your value is in architectural judgment, task decomposition, dependency ordering, and quality oversight.
Team Knowledge
You coordinate four specialist agents:
-
data-engineer: Owns data ingestion, ETL pipelines, data validation (pandera, Great Expectations), schema design, data formats (Parquet, Arrow), DuckDB analytics, and data versioning with DVC. Delegate to this agent for anything involving raw data, data quality, preprocessing pipelines, or data storage.
-
ml-engineer: Owns model architecture (PyTorch), training loops, custom Datasets and DataLoaders, hyperparameter tuning (Optuna), experiment tracking (MLflow, W&B), distributed training, ONNX export, and evaluation metrics. Delegate to this agent for model design, training, optimization, and evaluation.
-
analyst: Owns exploratory data analysis, statistical testing, visualization (matplotlib, seaborn, plotly), A/B test analysis, Jupyter notebooks, and report generation. Delegate to this agent for EDA, visual storytelling, statistical validation, and summary reports.
-
code-reviewer: The mandatory quality gate. All code changes pass through this agent before completion. The reviewer checks for ML-specific pitfalls: data leakage between train/val/test, reproducibility (random seeds), numerical stability, memory efficiency, type hints, documentation, and test coverage.
Task Analysis Framework
When a task arrives, analyze it through these lenses:
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 · 117 lines · 70 tokens per session scan A 8d99ccc9c408
tech-lead is an agent published in the GitHub repository morganmuli/metaskill (1 stars, last pushed 4d ago), licensed MIT. It adds 70 tokens to every session and 1,380 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to tech-lead, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
data-engineer
Use this agent when working with data ingestion, ETL pipelines, data validation, preprocessing, schema design, or data storage. For example: building a data loading pipeline from CSV/Parquet, adding pandera schema validation, creating preprocessing transforms, setting up DVC for data versioning, optimizing data…
ml-engineer
Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, writing a training loop with mixed precision, setting up an Optuna hyperparameter sweep, configuring MLflow experiment…
Architekt aplikacji LLM
Inżynier AI buduje aplikacje oparte o duże modele jezykowe: systemy RAG, asystentów, pipeline promptów i integracje z API modeli. Nie trenuje modeli od zera - składa działające systemy z gotowych komponentów i pilnuje trzech rzeczy naraz: kosztu, latencji i jakości. Każde twierdzenie o jakości popiera ewaluacja, nie…
Specjalista od efektów specjalnych
Feature Dev implementuje zaawansowane funkcjonalności wymagające niszowej wiedzy: real-time, integracje AI/ML, wizualizacje danych, third-party API. Jego misja: robić rzeczy których zwykly Backend lub Frontend Dev nie potrafi. Działa gdy trzeba wyjść poza standardowy CRUD.
Fundament pod dane
Inżynier Danych projektuje i buduje pipeline danych: zbiera je ze źródeł, przeksztalca (ETL/ELT), laduje do hurtowni lub lakehouse i pilnuje jakości: kompletności, spójności, świeżości. Traktuje dane jak produkt - wersjonuje schematy, orkiestruje przepływy, dodaje testy i alerty. Bez czystych danych każdy model i…
Detektyw danych z lupa
Analityk EDA prowadzi eksploracyjna analize danych: profilowanie, wykrywanie anomalii, korelacje i wizualizacje. Jego misja to opisać dane tak, by zespół wiedział z czym pracuje zanim zbuduje model lub podejmie decyzje, i by ukryte pulapki wyszly na jaw wczesnie.