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 skills add morganmuli/metaskill --skill run-pipelinegit 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/skills/morganmuli/metaskill/run-pipeline)<a href="https://agentmods.dev/skills/morganmuli/metaskill/run-pipeline"><img src="https://agentmods.dev/badge/skills/morganmuli/metaskill/run-pipeline/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/skills/morganmuli/metaskill/run-pipeline"><img src="https://agentmods.dev/badge/skills/morganmuli/metaskill/run-pipeline.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 | $0.00049 | $0.01036 |
| Opus 5 | $0.00024 | $0.00518 |
| Sonnet 5 | $0.00010 | $0.00207 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade A, and why
run-pipeline 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 10d 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 run-pipeline — 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are executing the full data science pipeline for this project. Run each stage sequentially, verifying success before proceeding to the next stage. Stop immediately if any stage fails and report the error clearly.
Dynamic Context
Current branch: !git branch --show-current
Data directory contents: !ls data/ 2>/dev/null || echo "No data/ directory found"
Available configs: !ls configs/*.yaml 2>/dev/null || ls configs/*.toml 2>/dev/null || echo "No config files found"
Python environment: !which python3 && python3 --version 2>/dev/null || echo "Python not found"
Recent changes: !git diff --stat HEAD~3 2>/dev/null || echo "No recent commits"
Configuration
If the user provided a config file as an argument, use it: $ARGUMENTS
Otherwise, look for the default config at configs/experiment.yaml or configs/experiment.toml.
Pipeline Stages
Execute each stage in order. After each stage, check for errors and verify outputs exist before proceeding.
Stage 1: Environment Check
Verify the Python environment is ready:
python3 -c "import torch; import pandas; import numpy; print(f'PyTorch {torch.__version__}, pandas {pandas.__version__}, NumPy {numpy.__version__}')"
If imports fail, report which packages are missing and suggest pip install -r requirements.txt.
Stage 2: Data Validation
Run data validation on the raw data:
python3 -m src.data.validate --data-dir data/raw/
If the validation script does not exist, look for alternative patterns:
python3 src/data/validate.pypython3 -m pytest tests/test_data/ -v --tb=short- Check for pandera schemas in
src/data/and report their status
Verify: validation passes with no critical errors. Log any warnings.
Stage 3: Preprocessing
Run the preprocessing pipeline:
python3 -m src.data.preprocess --config $CONFIG_FILE
Alternative patterns:
python3 src/data/preprocess.py --config $CONFIG_FILEdvc repro preprocess(if DVC pipeline is configured)
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.
- 10d ago First seen · 134 lines · 49 tokens per session scan A a7ce44b3fd0e
run-pipeline is a skill published in the GitHub repository morganmuli/metaskill (1 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 1,036 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to run-pipeline, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
generate-report
Generate a comprehensive summary report of the latest experiment including metrics, plots, and comparison with baseline. Use this after training and evaluation to create a shareable experiment summary.
evaluate-model
Load the latest model checkpoint, run evaluation on the test set, and generate a metrics report with confusion matrix. Use this after training to assess model performance or to re-evaluate a specific checkpoint.
run-pipeline
Run the full data science pipeline: validate raw data, preprocess, engineer features, train model, and evaluate. Use this when you want to execute the end-to-end ML pipeline or re-run it after data or code changes.
memory-optimization
Tune moflo's memory stack for speed, RAM, and index quality. Covers HNSW parameters (M, efConstruction, ef), vector quantization, batch operations, and common bottlenecks. Use when scaling past 100k entries or when search latency regresses.
memory-patterns
Persistent memory patterns for moflo agents — session memory, long-term knowledge, pattern learning, and cross-session context via moflo's node:sqlite + HNSW vector store. Use when building stateful agents or assistants that need to remember across runs.
vector-search
Semantic vector search with moflo — RAG over your own documents, similarity matching, context-aware retrieval via HNSW (node:sqlite-backed). Use when building retrieval layers for chat, search, or context-assembly.