coding-patterns

coding-patterns is a skill for Claude Code from AnswerDotAI/skill-plugins. It costs 157 tokens per session (1,831 once invoked), scanned A, original, Apache-2.0.

A set of coding conventions based on the fastai style guide and long-term Python development experience. It explains how to keep code concise, readable, and purposeful.

In plain words
What is it for?
Use it when reading, searching, designing, or changing code to choose suitable libraries and assess whether each part of an implementation earns its place.
Why use it?
It helps reviewers and agents avoid unnecessary wrappers, defensive code, comments, type hints, and dependencies that make code harder to understand.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the claude-aai plugin — 5 skills shipped together

Good fit Use it when reading, searching, designing, or changing code to choose suitable libraries and assess whether each part of an implementation earns its place.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/answerdotai/skill-plugins/coding-patterns
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 AnswerDotAI/skill-plugins --skill coding-patterns
Clone the repo
git clone --depth 1 https://github.com/AnswerDotAI/skill-plugins

Made for: Claude Code.

Or install claude-aai, the plugin that ships this one along with the rest of its 5 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 coding-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/answerdotai/skill-plugins/coding-patterns/github.svg)](https://agentmods.dev/skills/answerdotai/skill-plugins/coding-patterns)
Your own site
<a href="https://agentmods.dev/skills/answerdotai/skill-plugins/coding-patterns"><img src="https://agentmods.dev/badge/skills/answerdotai/skill-plugins/coding-patterns/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 coding-patterns

Your own site · 80×15
<a href="https://agentmods.dev/skills/answerdotai/skill-plugins/coding-patterns"><img src="https://agentmods.dev/badge/skills/answerdotai/skill-plugins/coding-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,831 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 $0.00157 $0.01831
Opus 5.5 $0.00063 $0.00732
Sonnet 5.5 $0.00031 $0.00366
Haiku 4.5 $0.00016 $0.00183

Measured 1mo ago against content hash bdfc97f5dfe8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coding-patterns 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.

plugins/claude-aai/skills/coding-patterns/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coding Patterns

Based on the fastai style guide and Jeremy's 3 decades of coding experience, and used across all of his projects, not only fastai ones.

Use the fastcore/fasthtml ecosystem (fastcore, fasthtml, fastlite, ...) when picking libraries - these are Jeremy's own, editable-installed as siblings, and preferred over heavier third-party alternatives.

Every Construct Must Earn Its Place

Readers assume everything present is necessary. When they see str(x) on something that's already a str, they stop and wonder what subtle thing it's guarding against; when the answer is "nothing", they paid for a mystery with no payoff. The same goes for defensive copies (list(x) that's never mutated), "just in case" try/excepts, redundant type coercions, and unused parameters. Before adding any construct, know why it's needed; if you can't say, leave it out. The cost doubles in nbdev projects, where tests are documentation.

The same applies to prose in code: almost never add comments (only when the code is truly unclear), and don't add type hints, docstrings, or boilerplate that pull no weight. Prefer concise, readable code over verbose "enterprise" style.

Docments

Docments are trailing comments on function parameters that fastcore uses for documentation. A signature with docments (or any long signature) uses this layout: ( stays on the def line, each parameter on its own line indented 4, and ): alone on its own line at def indent:

@delegates(start_kernel)
async def run_kernel(
    kernel_name='python3', # Kernelspec name to launch
    manager_cls=KernelManager, # Manager class, e.g. a subclass customizing launch
    **kwargs
):

NEVER remove docments when refactoring - they're essential documentation.

When **kwargs passes through to a known callee, decorate with @delegates(callee) so the signature shows the real options - and delegates REQUIRES the collector to be named kwargs, not kw etc. Skip the decorator when the callee's own signature is just **kwargs (nothing to delegate).

Read the full file on GitHub · 117 lines

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. 1mo ago First seen · 117 lines · 0 tokens per session scan A bdfc97f5dfe8

Subscribe to this mod's changes

coding-patterns is a skill published in the GitHub repository AnswerDotAI/skill-plugins (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 157 tokens to every session and 1,831 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

matlab

Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 44 tokens

pennylane

Builds and differentiates PennyLane quantum circuits, hybrid PyTorch or JAX models, molecular VQE and QAOA workflows. Use for variational quantum algorithms, quantum machine learning, simulator validation, and moving validated circuits to provider plugins. For hardware-specific compilation use qiskit or cirq; for…

K-Dense-AI/scientific-agent-skills · 74 tokens

rocm-kernels

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…

huggingface/kernels · 93 tokens

holoscan-install-wheel

Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.

NVIDIA/skills · 37 tokens

typing-exclusion-worker

Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.

getsentry/skills · 57 tokens

python

Python development with ruff, mypy, pytest - TDD and type safety.

alinaqi/maggy · 18 tokens