format_python

A set of rules for writing and editing Python code, including formatting, naming, imports, type hints, errors, logging, testing, and security.

In plain words
What is it for?
Use it when creating or changing Python files to apply consistent style, structure, error handling, and code-quality practices.
Why use it?
It reduces inconsistent code and common problems that cause linting failures or make Python projects harder to maintain.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/theafh/ai-modules/format_python
Any agent
npx skills add theafh/ai-modules --skill format_python
Clone the repo
git clone --depth 1 https://github.com/theafh/ai-modules

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,473 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00072 $0.01473
Opus 5 $0.00036 $0.00737
Sonnet 5 $0.00014 $0.00295
Haiku 4.5 $0.00007 $0.00147

Measured 2d ago against content hash a77155e6d210, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

format_python 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 2d 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/ai_dev/skills/format_python/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

format_python

Formatting Standards

  • Use exactly 4 spaces for indentation (never tabs)
  • Use double quotes for all string literals consistently
  • Write one import per line, group in order: stdlib → third party → first party → local
  • Use snake_case for variables/functions, PascalCase for classes, UPPER_CASE for constants
  • Keep lines under 88 characters, break long lines at logical points with proper indentation

Code Quality Standards

  • Write valid Python syntax that passes all linter checks
  • Use specific exception types like ValueError, FileNotFoundError
  • Assign error messages to variables before raising exceptions
  • Import only what you use - avoid unused imports, types, or variables
  • Use _ for intentionally unused values to prevent F841 errors
  • Use modern type hints: dict[str, Any] instead of Dict[str, Any], str | None instead of Optional[str]
  • Import types only when needed - prefer built-in types over typing module when possible
  • Use f-strings for general formatting, use % formatting in logging statements
  • Use is/is not for None comparisons, use in/not in for membership testing
  • Avoid single-letter variable names except for loop counters
  • Don't shadow built-in names like list, dict, str, id, type
  • Use context managers (with statements) for all file operations and resource cleanup
  • Use logger = logging.getLogger(__name__) for module-level logging
  • Use logging instead of print statements for all output

Code Structure

  • Follow this exact order: docstring → imports → constants → classes → functions → main guard
  • Write functions with single responsibility, clear parameters, and early returns for better readability
  • Use clear, descriptive class names; apply proper decorators (@classmethod, @staticmethod) for class methods
  • Validate all input parameters when necessary, especially for public functions

Linting Prevention (Critical for LLM Code Generation)

  • Write one import per line to prevent E401 multiple imports error
  • Import only modules you actively use - remove unused imports immediately to prevent F401 errors
  • Omit exception variable name when not using the exception object
  • Remove commented-out code and unreachable statements immediately
  • Update all class references when renaming to prevent F821 undefined name errors
  • Use descriptive class names without "Test" prefix for non-test classes
  • Use is None instead of == None to prevent E711 comparison error

Read the full file on GitHub · 172 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. 2d ago First seen · 172 lines · 72 tokens per session scan A a77155e6d210

Subscribe to this mod's changes

format_python is a skill published in the GitHub repository theafh/ai-modules (38 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 1,473 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens