recommend-new-approaches

recommend-new-approaches is a skill for Claude Code from lawwu/agentic-ml-plugin. It costs 134 tokens per session (2,331 once invoked), scanned A, original, no licence file.

A research-support skill that suggests new experiments after a machine-learning training run finishes. It can propose modeling changes, architecture ideas, and different loss functions, which control how a model learns from errors.

In plain words
What is it for?
Use it to explore improvements to model architecture, training objectives, loss functions, and research direction after a run.
Why use it?
It provides possible next steps when a model's results are incomplete or disappointing. This helps turn training outcomes into specific follow-up experiments.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the agentic-ml plugin — 15 skills shipped together

Good fit Use it to explore improvements to model architecture, training objectives, loss functions, and research direction after a run.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lawwu/agentic-ml-plugin/recommend-new-approaches
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.

Any agent
npx skills add lawwu/agentic-ml-plugin --skill recommend-new-approaches
Clone the repo
git clone --depth 1 https://github.com/lawwu/agentic-ml-plugin

Made for: Claude Code.

Or install agentic-ml, the plugin that ships this one along with the rest of its 15 skills.

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 recommend-new-approaches

README.md
[![agentmods](https://agentmods.dev/badge/skills/lawwu/agentic-ml-plugin/recommend-new-approaches/github.svg)](https://agentmods.dev/skills/lawwu/agentic-ml-plugin/recommend-new-approaches)
Your own site
<a href="https://agentmods.dev/skills/lawwu/agentic-ml-plugin/recommend-new-approaches"><img src="https://agentmods.dev/badge/skills/lawwu/agentic-ml-plugin/recommend-new-approaches/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.

agentmods 80×15 button for recommend-new-approaches

Your own site · 80×15
<a href="https://agentmods.dev/skills/lawwu/agentic-ml-plugin/recommend-new-approaches"><img src="https://agentmods.dev/badge/skills/lawwu/agentic-ml-plugin/recommend-new-approaches.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,331 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 5.1 $0.00134 $0.02331
Opus 5 $0.00067 $0.01166
Sonnet 5 $0.00027 $0.00466
Haiku 4.5 $0.00013 $0.00233

Measured 8d ago against content hash b828b4739531, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

recommend-new-approaches 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 8d 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.

plugins/agentic-ml/skills/recommend-new-approaches/SKILL.md · 180 lines

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.

Read it on GitHub

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. 8d ago First seen · 180 lines · 134 tokens per session scan A b828b4739531

Subscribe to this mod's changes

recommend-new-approaches is a skill published in the GitHub repository lawwu/agentic-ml-plugin (3 stars, last pushed 5mo ago), with no licence file. It adds 134 tokens to every session and 2,331 once invoked, about $0.0007 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

semantic-diff

This skill should be used when the user asks to "diff two archetypes", "compare two templates", "what changed between these two versions", "is this a patch, minor or major bump?", "how compatible are these two artefacts?", or invokes /semantic-diff. Auto-detects archetype vs template (any serialisation) and version vs…

Cadasto/openehr-assistant-plugin · 135 tokens

physicsnemo-discover

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…

NVIDIA/physicsnemo · 124 tokens

pysr

Use when fitting equations to data with PySR or SymbolicRegression.jl, when a user wants an interpretable formula, symbolic model, scaling law, or empirical relation discovered from numeric data, or when debugging a PySR search that is slow, stuck, or giving poor equations.

astroautomata/PySR · 61 tokens

cellxgene-census-query

Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…

PharMolix/OpenBioMed · 105 tokens

ml-mlip-nvalchemi

GPU-accelerated batched inference for MACE, MatGL (TensorNet/M3GNet/CHGNet), and FairChem MLIPs using NValchemi, enabling parallel static, relax, and MD workflows across multiple structures simultaneously.

learningmatter-mit/AtomisticSkills · 59 tokens

ml-mace-finetune

Fine-tune MACE machine learning interatomic potentials on custom datasets.

learningmatter-mit/AtomisticSkills · 21 tokens