fastai

fastai is a skill for Claude Code, Codex from G1Joshi/Agent-Skills. It costs 15 tokens per session (235 once invoked), scanned A, original, MIT.

A Python library for building and training deep-learning models, with simpler high-level tools on top of PyTorch. It can also expose lower-level PyTorch controls when needed.

In plain words
What is it for?
Use it to learn deep learning, create quick model baselines, apply transfer learning, and train models with built-in choices for optimizers, learning rates, and data augmentation.
Why use it?
It reduces the amount of setup and tuning needed to get a model training, while still allowing custom work when the defaults are not enough.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to learn deep learning, create quick model baselines, apply transfer learning, and train models with built-in choices for optimizers, learning rates, and data augmentation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/g1joshi/agent-skills/fastai
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 G1Joshi/Agent-Skills --skill fastai
Clone the repo
git clone --depth 1 https://github.com/G1Joshi/Agent-Skills

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 fastai

README.md
[![agentmods](https://agentmods.dev/badge/skills/g1joshi/agent-skills/fastai/github.svg)](https://agentmods.dev/skills/g1joshi/agent-skills/fastai)
Your own site
<a href="https://agentmods.dev/skills/g1joshi/agent-skills/fastai"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/fastai/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 fastai

Your own site · 80×15
<a href="https://agentmods.dev/skills/g1joshi/agent-skills/fastai"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/fastai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 235 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 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 5.1 $0.00015 $0.00235
Opus 5 $0.00008 $0.00118
Sonnet 5 $0.00003 $0.00047
Haiku 4.5 $0.00002 $0.00023

Measured 9d ago against content hash 8d19682de2ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fastai 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 9d 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/ai-ml/fastai/SKILL.md · 39 lines

What it actually says

fastai

fastai is a layered API on top of PyTorch. It popularized Transfer Learning and good defaults (One Cycle Policy).

When to Use

  • Learning DL: The best course/library for beginners ("Practical Deep Learning for Coders").
  • Quick Baselines: Get state-of-the-art results in 5 lines of code.

Core Concepts

Defaults

fastai chooses the best learning rate finder, optimizer (AdamW), and augmentations for you.

Layered API

You can use the high-level Learner or peel back layers to raw PyTorch.

Best Practices (2025)

Do:

  • Watch the Course: Jeremy Howard's course updates annually and is world-class.
  • Use nbdev: fastai's literate programming environment is powerful.

Don't:

  • Don't get stuck: If you need something very custom, drop down to PyTorch.

References

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. 9d ago First seen · 39 lines · 15 tokens per session scan A 8d19682de2ff

Subscribe to this mod's changes

fastai is a skill published in the GitHub repository G1Joshi/Agent-Skills (12 stars, last pushed 7mo ago), licensed MIT. It adds 15 tokens to every session and 235 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories