compare-runs

compare-runs is a skill for Claude Code, Codex from duonginspace/claude-code-databricks-ml. It costs 74 tokens per session (444 once invoked), scanned A, original, MIT.

A guide for comparing machine-learning experiments tracked in MLflow, a tool that records training runs and their results.

In plain words
What is it for?
Finding the best runs, comparing hyperparameters, checking training and validation behaviour, spotting overfitting, and reviewing failed runs.
Why use it?
It turns experiment history into a ranking and explains which settings improved or hurt model performance.

Skill for Claude CodeCodex

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 skills/duonginspace/claude-code-databricks-ml/compare-runs
Any agent
npx skills add duonginspace/claude-code-databricks-ml --skill compare-runs
Clone the repo
git clone --depth 1 https://github.com/duonginspace/claude-code-databricks-ml

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for compare-runs

README.md
[![agentmods](https://agentmods.dev/badge/skills/duonginspace/claude-code-databricks-ml/compare-runs.svg)](https://agentmods.dev/skills/duonginspace/claude-code-databricks-ml/compare-runs)
Your own site
<a href="https://agentmods.dev/skills/duonginspace/claude-code-databricks-ml/compare-runs"><img src="https://agentmods.dev/badge/skills/duonginspace/claude-code-databricks-ml/compare-runs.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 444 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 $0.00074 $0.00444
Opus 5 $0.00037 $0.00222
Sonnet 5 $0.00015 $0.00089
Haiku 4.5 $0.00007 $0.00044

Measured 5d ago against content hash 375d794247d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compare-runs 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.

skills/compare-runs/SKILL.md · 43 lines

What it actually says

Experiment comparison task

$ARGUMENTS

Steps

  1. Run uv run python scripts/pull_results_on_databricks.py to sync the latest results from MLflow.
  2. Read mlflow_results/all_runs.csv — this has all experiment history.
  3. Read mlflow_results/latest_run.json for the most recent run's full details.

Analysis to perform

Ranking

Sort all finished runs by the primary metric (look for val_accuracy, val_loss, or f1 — whichever is in the data). Show the top 5 as a markdown table with columns: rank, run name, primary metric, key hyperparameters, training time, run date.

What helped vs. hurt

Group runs by the parameter that changed most across experiments. For each parameter variant, show the mean and best metric. Identify which changes consistently improved performance and which hurt it.

Learning rate analysis

If lr or learning_rate is in params, plot or describe the lr vs. primary metric curve.

Convergence check

For the best run, read the metric history from latest_run.json. Did the model converge? Was there overfitting (train loss still dropping while val loss rises)? Suggest early stopping patience if relevant.

Environment issues

Check if any runs failed. Read mlflow_results/job_logs.txt if present. Report any recurring errors.

Output

Produce a clear summary with:

  1. The current best run and its config
  2. Three specific, concrete experiment suggestions ranked by expected improvement
  3. One environment/infrastructure recommendation if any runs failed

ultrathink

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. 5d ago First seen · 43 lines · 74 tokens per session scan A 375d794247d0

Subscribe to this mod's changes

compare-runs is a skill published in the GitHub repository duonginspace/claude-code-databricks-ml (5 stars, last pushed 5mo ago), licensed MIT. It adds 74 tokens to every session and 444 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens