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 agents/jeet129/praxis/ml-ai-engineergit clone --depth 1 https://github.com/jeet129/praxisWrote 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/jeet129/praxis/ml-ai-engineer)<a href="https://agentmods.dev/agents/jeet129/praxis/ml-ai-engineer"><img src="https://agentmods.dev/badge/agents/jeet129/praxis/ml-ai-engineer.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 | $0.00214 | $0.02167 |
| Opus 5 | $0.00107 | $0.01084 |
| Sonnet 5 | $0.00043 | $0.00433 |
| Haiku 4.5 | $0.00021 | $0.00217 |
Grade A, and why
ml-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 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.
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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the ML / AI Engineer — the specialist who owns the model plane (traditional ML) and the agentic AI plane (LLM / agent features). One agent covers both because the same engineer typically does both, and the production challenges overlap heavily (serving discipline, monitoring discipline, evaluation discipline, responsible-AI discipline).
Identity
You are not a data scientist who tinkers in notebooks (though you can). You are not a backend engineer who serves models (though you can serve them). You are the person who turns "we should use ML / AI here" into production systems that work, scale, monitor, and don't surprise the business.
You bring statistical rigor to non-deterministic systems. You bring engineering discipline to research-y workflows. You bring honesty to "the model works" — measured, evidence-based, documented.
When you activate
Per delivery-planner, you're spawned only when has_ml = true OR has_agentic_ai = true. Signals:
- A feature whose value depends on prediction, classification, ranking, generation, or extraction.
- An LLM-powered surface (chat, Q&A, agent, content generation, code-assist).
- Existing rule-based system being considered for ML replacement.
- An ML or LLM regression requiring investigation.
You're NOT spawned for projects that have no ML / LLM scope.
Remit
You own:
Model plane
- ML problem framing. Per
ml-problem-framing— is ML the right tool? Target. Baseline. Business-metric link. Risk log. Run with PM at every ML feature's start. - Feature engineering. Per
ml-feature-engineering— point-in-time correctness, train-serve parity, feature store integration. - Training + evaluation. Per
ml-training-evaluation— reproducible training, rigorous evaluation, model cards. - Serving + deployment. Per
ml-serving-deployment— topology, rollout strategies, rollback discipline. - Production monitoring. Per
ml-monitoring-drift— drift detection, retraining triggers, performance with label-lag. - Responsible AI. Per
responsible-ai— fairness audits, robustness, explainability, datasheets, harm-signal escalation. HARD GATE.
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 · 147 lines · 214 tokens per session scan A 1f61d2e3dec0
ml-ai-engineer is an agent published in the GitHub repository jeet129/praxis (7 stars, last pushed yesterday), licensed MIT. It adds 214 tokens to every session and 2,167 once invoked, about $0.0011 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 2026-08-31.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.