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/ankit-aglawe/python-coding-agent-skill/prod-pythonnpx skills add ankit-aglawe/python-coding-agent-skill --skill prod-pythongit clone --depth 1 https://github.com/ankit-aglawe/python-coding-agent-skillWhat 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 | $0.00045 | $0.03831 |
| Opus 5 | $0.00023 | $0.01916 |
| Sonnet 5 | $0.00009 | $0.00766 |
| Haiku 4.5 | $0.00005 | $0.00383 |
Grade A, and why
prod-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 yesterday.
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 — 603 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Production Python
Write Python like a senior developer — simple, readable, PEP-compliant. No AI slop. No over-engineering. No unnecessary abstractions.
Core principle: The best code is the simplest code that solves the problem correctly.
When to Use
- Writing any Python code (scripts, APIs, libraries, CLIs)
- Refactoring existing Python code
- Code reviews — flag AI patterns
- Code feels bloated, over-abstracted, or "AI-generated"
AI Slop — Eliminate on Sight
Module-Level Docstrings on Every File
# SLOP
"""User authentication module for handling login and registration."""
from flask import request
# CLEAN — filename says it all
from flask import request
Only add module docstrings for genuinely complex algorithms or non-obvious design decisions. Never add # src/path/file.py path comments.
Over-Documented Obvious Code
# SLOP — 20 lines to say "sum prices"
def calculate_total(items: List[Dict[str, Any]]) -> float:
"""
Calculate the total price of items.
Args:
items: List of item dictionaries containing prices
Returns:
float: The total sum of all item prices
Raises:
ValueError: If items is empty
KeyError: If price key missing
"""
total = 0.0
for item in items:
total += item['price']
return total
# CLEAN
def calculate_total(items: list[dict]) -> float:
return sum(item['price'] for item in items)
Docstrings: one line max for obvious functions. Skip entirely if the signature tells the story.
Narrating Code with Comments
# SLOP
# Initialize the user list
users = []
# Loop through each record
for record in records:
# Create user object
user = User(record)
# Append to list
users.append(user)
# CLEAN
users = [User(r) for r in records]
Comments explain WHY, never WHAT. If you need to explain what code does, rewrite the code.
Legacy typing Imports
# SLOP — pre-3.9 style
from typing import List, Dict, Optional, Union, Tuple, Any
def process(data: List[Dict[str, Any]]) -> Optional[Dict[str, Union[str, int]]]:
...
# CLEAN — modern builtins + PEP 604
def process(data: list[dict]) -> dict | None:
...
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.
- yesterday First seen · 603 lines · 45 tokens per session scan A 5017e8cf1d44
prod-python is a skill published in the GitHub repository ankit-aglawe/python-coding-agent-skill (2 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 3,831 once invoked, about $0.0002 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.
Other skills, from other repositories
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
agent-check
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
skill-check
Validate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.
prompt-sensei
Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.
agent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.