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-codingnpx skills add jenreh/appkit --skill python-codinggit 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 | $0.00057 | $0.01086 |
| Opus 5 | $0.00028 | $0.00543 |
| Sonnet 5 | $0.00011 | $0.00217 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
python-coding 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.
This is a copy
95% identical to writing-python-code — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Python Code
Quick reference
- Python 3.14 only; deps via uv; line length 88 chars (Ruff/Black).
- No f-strings in logger calls — use
log.info("x: %s", val). - Type annotations on every function and method.
- Files ≤ 1000 lines — refactor via Extract Class, Mixins, Strategy, etc.
- Coverage ≥ 80% for non-Reflex classes and Reflex State classes.
- Task runner:
task format,task lint,task test(notmake).
Code style
Logging
import logging
log = logging.getLogger(__name__)
log.info("Loaded items: %d", count) # ✅ parameterized
# log.info(f"Loaded items: {count}") # ❌ f-string
Never use print or printf. Log levels: debug → internal state (default), info → milestones, warning → recoverable, error → serious.
Type hints
def process(data: dict[str, Any], count: int = 0) -> list[str]: ...
async def handler(value: str) -> AsyncGenerator[Any, Any]:
yield
- Do not mix
Literal[...]withstr— pick one. - Remove unused imports immediately (F401).
- Remove unused args or prefix with
_(ARG001).
Imports & formatting
- Ruff handles lint + format; run
task formatbefore committing. - Break long calls/strings to fit 88 chars.
Ruff rules to watch (project-specific)
| Code | Rule | Fix |
|---|---|---|
| UP031 | No %-formatting outside logger calls — use f-strings |
Replace "x %s" % val with f"x {val}" |
| I001 | Import order | Auto-fixed by task format |
| PLC0415 | No local imports inside functions or test methods | Move to top of file |
| B017 | pytest.raises(Exception) too broad |
Use specific exception, e.g. pytest.raises(ValidationError) |
File size rule
No Python file may exceed 1000 lines. When approaching the limit, apply clean code refactoring strategies.
Design patterns & refactoring strategies: See skill python-clean-code.
Testing
Coverage target: ≥ 80% for services, repositories, models, utilities, and Reflex State classes. UI component rendering is best-effort.
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 · 125 lines · 57 tokens per session scan A d4dcc40f6e48
python-coding is a skill published in the GitHub repository jenreh/appkit (4 stars, last pushed 6d ago), licensed MIT. It adds 57 tokens to every session and 1,086 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to writing-python-code, differing in 9 lines, and is treated as a copy.
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.