ml-project

A command that starts a structured workflow for building or improving an AI or machine-learning project. It covers tasks such as language models, computer vision, medical imaging, and time-series data.

In plain words
What is it for?
Use it to research methods, choose an approach, train models, compare baselines, evaluate them honestly, and improve an existing model when its accuracy is too low.
Why use it?
It helps prevent premature coding by requiring research, checks for data leakage, fair baselines, and rigorous evaluation before claiming results.

Command

Install

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.

agentmods
npx agentmods add commands/mxslr/mlcraft/ml-project
Clone the repo
git clone --depth 1 https://github.com/mxslr/mlcraft
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 359 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.00359
Opus 5 $0.00026 $0.00179
Sonnet 5 $0.00010 $0.00072
Haiku 4.5 $0.00005 $0.00036

Measured 2d ago against content hash 41e9274aea2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ml-project 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 2d 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.

commands/ml-project.md · 21 lines

What it actually says

You are acting as a senior AI/ML engineer and researcher. The user's task:

$ARGUMENTS

Invoke the ml-research-methodology skill and follow it end to end. Do not jump straight to code.

Non-negotiables (the "professor standard"):

  1. Research before building. Use the literature-review skill (and the paper-researcher agent if available) to find SOTA and the realistic accuracy ceiling for this exact task/dataset. Be skeptical of inflated numbers.
  2. Audit data leakage first (data-rigor-and-leakage) - especially group/patient/temporal splits. A leaky 98% is worthless.
  3. Route to the right domain skill based on the task (see the methodology's routing table).
  4. Honest baselines before fancy models, identical configs for fair comparison.
  5. Evaluate rigorously (rigorous-evaluation) - thresholds chosen on validation, calibration, the metric that actually matters for the use case.
  6. Only claim a result after you have run it and seen the output. Evidence before assertions.

If the task is about improving an existing model ("accuracy still too low", "boost it"), use the accuracy-improvement-loop skill instead of starting from scratch.

Changes

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.

  1. 2d ago First seen · 21 lines · 52 tokens per session scan A 41e9274aea2d

Subscribe to this mod's changes

ml-project is a command published in the GitHub repository mxslr/mlcraft (8 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 359 once invoked, about $0.0003 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.