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 lawwu/agentic-ml-plugin --skill plan-experimentgit clone --depth 1 https://github.com/lawwu/agentic-ml-pluginWrote 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/lawwu/agentic-ml-plugin/plan-experiment)<a href="https://agentmods.dev/skills/lawwu/agentic-ml-plugin/plan-experiment"><img src="https://agentmods.dev/badge/skills/lawwu/agentic-ml-plugin/plan-experiment/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/lawwu/agentic-ml-plugin/plan-experiment"><img src="https://agentmods.dev/badge/skills/lawwu/agentic-ml-plugin/plan-experiment.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 | $0.00086 | $0.01394 |
| Opus 5.5 | $0.00034 | $0.00558 |
| Sonnet 5.5 | $0.00017 | $0.00279 |
| Haiku 4.5 | $0.00009 | $0.00139 |
Grade A, and why
plan-experiment 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 1mo 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 144 lines · 86 tokens per session scan A 243ac75311bd
plan-experiment is a skill published in the GitHub repository lawwu/agentic-ml-plugin (3 stars, last pushed 7mo ago), with no licence file. It adds 86 tokens to every session and 1,394 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
build-ml-pipeline
Declare the pipeline from data source to predictor as a skrub DataOps graph. Stateless steps use .skb.applyfunc. Stateful steps use .skb.apply. After the graph exists, attach the locked splitter and any non-default score. No fit, tune, persistence, or skore.evaluate. TRIGGER when writing or editing any link from data…
sync-ml-reports
Copy skore reports between local, Hub, and MLflow with skore sync, and optionally switch the recorded upload destination. Trigger when the user asks to sync or migrate reports, switch skore mode, upload reports to Hub or MLflow, or pull Hub/MLflow reports onto disk. First G-SKORE-MODE pick stays evaluate-ml-pipeline.
explore-ml-data
Owns data understanding before any model is designed. Place dataanalysis/dataanalysis.py and do not execute it. Run materialize.py once, write dataanalysis.md and JOURNAL § Data understanding. Never design the model, edit src/ /, or modify raw data files. TRIGGER when the user asks to explore, profile, or understand…
smoke-test-ml-pipeline
Owns one experiment's smoke test: a small pytest that fits on part of real data/ and predicts on a disjoint slice with no pre-history buffer. Prediction count must equal predict-grid rows. TRIGGER when an approved experiment needs its smoke test, pytest tests/smoke/ fails on row count, the user asks why the smoke test…
data-science-python-stack
Deprecated compatibility skill. Trigger only when an installed workflow still references this old id.
ds-validate
Chooses a leakage-safe way to split data — temporal, grouped, stratified, or nested cross-validation — matched to how the rows are actually structured, and decided before any model is trained. Use when someone asks how to split into train and test, set up cross-validation, or pick between KFold, GroupKFold…