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 skills/leeroo-ai/superml/ml-debugnpx skills add Leeroo-AI/superml --skill ml-debuggit clone --depth 1 https://github.com/Leeroo-AI/supermlWrote 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/leeroo-ai/superml/ml-debug)<a href="https://agentmods.dev/skills/leeroo-ai/superml/ml-debug"><img src="https://agentmods.dev/badge/skills/leeroo-ai/superml/ml-debug.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 | $0.00032 | $0.09132 |
| Opus 5 | $0.00016 | $0.04566 |
| Sonnet 5 | $0.00006 | $0.01826 |
| Haiku 4.5 | $0.00003 | $0.00913 |
Grade A, and why
ml-debug scanned grade A 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **Verification script that doesn't match the failure mode** | Serving fix verified with single curl; OOM fix verified with "run and see if it crashes" | Match verification to the failure: serving → concurrent load test How it starts
The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ML Debugging
Systematically diagnose ML failures using framework-specific knowledge, not guesswork.
Grounding
Detect mode: On your first grounding call, check if Leeroopedia KB tools are available. If they return results, use KB mode. If unavailable or auth fails, use Web mode.
HARD RULE: You MUST ground before writing analysis. If KB fails, you MUST WebFetch at least 2 URLs before writing ANY diagnosis. Writing from memory without fetching is the #1 failure mode of this skill — it produces zero-citation responses that score 0/3 on grounding. "I know X well" is NOT a substitute for fetching documentation.
KB mode: Call diagnose_failure → query_hyperparameter_priors → search_knowledge. Cite as [PageID].
KB mode grounding supplement (MANDATORY): After KB calls, you MUST WebFetch at least 2 public URLs (official docs, PyPI, GitHub issues/source) and cite them as [source](URL) alongside [PageID] citations. KB-only responses score 2/3 max on grounding because reviewers cannot verify proprietary page IDs. Pattern: KB call for diagnosis → WebFetch PyPI for version → WebFetch GitHub/docs for config verification → cite BOTH KB and public URLs in every section. Self-test: if your response has zero [source](URL) citations, you will lose a grounding point regardless of KB citation count.
Web mode: WebFetch GitHub issues for the error message → WebFetch framework troubleshooting docs → WebFetch config references. Cite as [source](URL). Start response with: > Grounding: Web mode — citations from official docs and GitHub issues.
Web mode grounding targets by response section (aim for these counts):
- Diagnosis root cause: 1+ citation (to a specific doc section or GitHub source line, NOT a top-level page)
- Each "Why it matters" explanation: 1+ citation or
[no KB] - Each fix step: 1+ citation for the specific API/config being changed
- Each quantitative claim ("X× faster"): 1 citation or
[no KB] - Prevention items: 1+ citation for the metric/tool referenced
Target: 5+ total citations in web mode, each linking to a specific doc section or source line (not top-level domain pages). Below 3 is a grounding failure. Generic page links (e.g.,
huggingface.co/docs/transformers) score lower than specific section links (e.g.,huggingface.co/docs/transformers/model_doc/mixtral#MixtralConfig).
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.
- 4d ago First seen · 348 lines · 32 tokens per session scan A b6bf218fccb1
ml-debug is a skill published in the GitHub repository Leeroo-AI/superml (193 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 9,132 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dataset-transformation
Generates code that transforms datasets between ML schemas for model training or evaluation. Use when the user says "transform", "convert", "reformat", "change the format", or when a dataset's schema needs to change to match the target format — always use this skill for format changes rather than writing inline…
dataset-evaluation
Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the user says "is my dataset okay", "evaluate my data", "check my training data", "I have my own data", or before starting any fine-tuning job. Detects file format, checks schema compliance against the selected model…
use-case-specification
Creates a reusable use case specification file that defines the business problem, stakeholders, and measurable success criteria for model customization, as recommended by the AWS Responsible AI Lens. Use as the default first step in any model customization plan. Skip only if the user explicitly declines or already has…
model-selection
Selects a base model for the user's use case by querying SageMaker Hub. Use when the user asks which model to use, wants to select or change their base model, mentions a model name or family (e.g., "Llama", "Mistral", "Nova"), or wants to evaluate a base model — always activate even for known model names because the…
finetuning-technique
Selects a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) for the user's use case and validates it against the selected model's available recipes. Use when the user has decided to finetune and needs to choose a technique, or when the technique needs to be validated against a model. Requires a base model to already be…
finetuning
Generates code that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says "start training", "fine-tune my model", "I'm ready to train", or when the plan reaches the finetuning step. Supports SFT, DPO, RLVR, and RLAIF trainers, including RLVR Lambda reward function and RLAIF custom…