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/jenreh/appkit/python-clean-codenpx skills add jenreh/appkit --skill python-clean-codegit clone --depth 1 https://github.com/jenreh/appkitWhat 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 | $0.00165 | $0.02217 |
| Opus 5 | $0.00082 | $0.01108 |
| Sonnet 5 | $0.00033 | $0.00443 |
| Haiku 4.5 | $0.00016 | $0.00222 |
Grade A, and why
python-clean-code 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Code Python
Apply these principles whenever writing or refactoring Python code. Don't narrate the framework to the user — just produce code that embodies these values. Use the self-review checklist before presenting any non-trivial code.
Before writing code
Think through: what is the single responsibility of this component? What are its dependencies? What will callers need from it? Design the interface and type signatures before the body. Only implement what the current requirement demands.
Principles
SRP — Single Responsibility Principle
One class, one reason to change. If a class touches persistence AND domain logic AND notifications, split it.
# Bad: three responsibilities in one class
class User:
def save(self) -> None: ... # persistence
def send_welcome_email(self) -> None: ... # notifications
def validate_email(self) -> bool: ... # domain rule
# Good: one class per responsibility
class User: ... # domain model only
class UserRepository: ... # persistence
class UserMailer: ... # notifications
SoC — Separation of Concerns
Cross-cutting concerns (logging, caching, auth, retries) belong in decorators or middleware, not scattered inline inside business methods.
# Bad: logging woven into business logic
def get_user(user_id: int) -> User:
log.info("Fetching user %d", user_id)
user = db.query(User).get(user_id)
log.info("Fetched %s", user.name)
return user
# Good: concern at the boundary, not the body
@log_call
def get_user(user_id: int) -> User:
return repo.get(user_id)
SLA — Single Level of Abstraction
Every line in a function should live at the same conceptual level. Don't mix raw SQL with domain calls or HTTP requests with UI logic.
# Bad: two levels in one function
def process_order(order_id: int) -> None:
row = db.execute("SELECT * FROM orders WHERE id=?", [order_id]).fetchone()
order = Order(id=row[0], total=Decimal(row[1]))
send_confirmation_email(order.customer_email)
# Good: uniform level of abstraction
def process_order(order_id: int) -> None:
order = order_repo.get(order_id)
notifier.send_confirmation(order)
What ships with it
1 file 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.
- yesterday First seen · 288 lines · 165 tokens per session scan A 66fe05c96fca
python-clean-code is a skill published in the GitHub repository jenreh/appkit (4 stars, last pushed 6d ago), licensed MIT. It adds 165 tokens to every session and 2,217 once invoked, about $0.0008 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
generate-asset
Generate a single media asset — image, video, audio, or 3D. Use when the user wants one output from a clear prompt. Calls muapiselect to pick the best model, then muapigenerate.
run-skill
Run a named muapi multi-step recipe (UGC ad, storyboard, brand kit, product video, social carousel…). Use when the brief matches a known workflow. Delegates to the creative-specialist subagent.
custom-blocks
Use when the user has written (or wants to write) a ModularPipelineBlocks subclass in a local Python file and needs to package it into a Hub-uploadable directory. Covers the workflow from a single block.py file to a published custom-block repo that consumers can load via ModularPipeline.frompretrained( …
srt-whiteboard-animation
将 SRT 字幕做成暖米黄纸张底的白板手绘动画:读字幕→输出配图策略→确认后生成统一风格线稿→按叙事语义标注分区→预览台调整→渲染 MP4。编排沿用分区遮罩揭示(annotation.json / sequence / startMs / protectedRegions),但每个区域内的落墨换成 stream 的连续笔迹(骨架/网格 ink→color)。当用户提供 SRT 字幕并要求"字幕做成白板手绘/流式笔迹视频""SRT 生成白板动画""按字幕分镜画手绘"时触发。.
video2mp3
从视频文件中提取音频并保存为 MP3。当用户提到视频转音频、提取音频、抽 MP3、视频提取声音时使用。.
videoagent-image-studio
Tired of juggling 8 API keys? This skill gives you one-command access to Midjourney, Flux, Ideogram, and more, with zero setup. Use when you want to generate any image without worrying about API keys.