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 agentmods add skills/miles990/claude-software-skills/pythonnpx skills add miles990/claude-software-skills --skill pythongit clone --depth 1 https://github.com/miles990/claude-software-skillsWhat 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 | $0.00008 | $0.02823 |
| Opus 5 | $0.00004 | $0.01411 |
| Sonnet 5 | $0.00002 | $0.00565 |
| Haiku 4.5 | $0.00001 | $0.00282 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python
Overview
Modern Python development patterns including type hints, async programming, and Pythonic idioms.
Type Hints
Basic Types
from typing import (
Optional, Union, List, Dict, Set, Tuple,
TypeVar, Generic, Callable, Any,
Literal, TypedDict, Protocol
)
from dataclasses import dataclass
from datetime import datetime
# Basic type hints
def greet(name: str) -> str:
return f"Hello, {name}!"
# Optional (can be None)
def find_user(user_id: str) -> Optional['User']:
return users.get(user_id)
# Union types
def process(value: Union[str, int]) -> str:
return str(value)
# Python 3.10+ union syntax
def process_new(value: str | int | None) -> str:
return str(value) if value else ""
# Collections
def process_items(
items: List[str],
mapping: Dict[str, int],
unique: Set[str],
pair: Tuple[str, int]
) -> None:
pass
# Python 3.9+ built-in generics
def process_items_new(
items: list[str],
mapping: dict[str, int],
unique: set[str]
) -> None:
pass
Advanced Types
# TypeVar for generics
T = TypeVar('T')
K = TypeVar('K')
V = TypeVar('V')
def first(items: list[T]) -> T | None:
return items[0] if items else None
# Generic classes
class Repository(Generic[T]):
def __init__(self) -> None:
self._items: dict[str, T] = {}
def get(self, id: str) -> T | None:
return self._items.get(id)
def save(self, id: str, item: T) -> None:
self._items[id] = item
# TypedDict for structured dicts
class UserDict(TypedDict):
id: str
name: str
email: str
age: int # Required
nickname: str # Required
class PartialUserDict(TypedDict, total=False):
nickname: str # Optional
# Literal types
Mode = Literal["read", "write", "append"]
def open_file(path: str, mode: Mode) -> None:
pass
# Protocol (structural typing)
class Readable(Protocol):
def read(self) -> str: ...
def process_readable(source: Readable) -> str:
return source.read()
# Callable types
Handler = Callable[[str, int], bool]
AsyncHandler = Callable[[str], 'Awaitable[bool]']
def register_handler(handler: Handler) -> None:
pass
What ships with it
3 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.
- 2d ago First seen · 475 lines · 8 tokens per session scan A c8f21b03b568
python is a skill published in the GitHub repository miles990/claude-software-skills (20 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 2,823 once invoked, about $0.0000 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.
Other skills, from other repositories
python-docs
Comprehensive Python 3.13 reference covering all language features: variables, built-in types, strings, control flow, functions, lambdas, decorators, classes, inheritance, dataclasses, enums, metaclasses, collections (list, dict, set, tuple, comprehensions), modules and packages, pip, venv, exceptions, context…
code-review-python
Deep Python-specific code review covering type annotations, async pitfalls, mutable defaults, threading safety, and domain modeling. Applied in addition to the generic code-review skill when Python code is detected. Invoked when reviewing Python PRs, Py changes, or performing Python-specific quality checks.
fastapi
FastAPI best practices + Pydantic. Use when building or reviewing FastAPI APIs.
fastapi-patterns
FastAPI production patterns — routing, dependency injection, background tasks, streaming, error handling, and async. Use when building or reviewing a FastAPI service.
python-patterns
Python best practices — type hints, async/await, dataclasses, error handling, and performance patterns. Use when writing new Python code, reviewing Python, or modernizing legacy code.
fastapi-docs
FastAPI 0.115+ — path/query params, Pydantic, dependency injection, OAuth2/JWT, middleware, WebSocket, testing.