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-bpmn-server/writing-python-codenpx skills add jenreh/appkit-bpmn-server --skill writing-python-codegit clone --depth 1 https://github.com/jenreh/appkit-bpmn-serverWhat 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 | $0.00056 | $0.00912 |
| Opus 5 | $0.00028 | $0.00456 |
| Sonnet 5 | $0.00011 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
writing-python-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.
This is a copy
91% identical to writing-python-code — 22 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Python Code
Quick reference
- Python 3.13 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, 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.
File size rule
No Python file may exceed 1000 lines. When approaching the limit, apply clean code refactoring strategies.
Design patterns & refactoring strategies: See references/clean-code.md.
Testing
Coverage target: ≥ 80% for services, repositories, models, utilities, and Reflex State classes. UI component rendering is best-effort.
task test # full suite with coverage
uv run pytest tests -k assistant # targeted
uv run pytest tests -x # stop on first failure
Test patterns, fixtures, Reflex State testing: See references/testing.md.
Security & config
- No credentials in code/history; use
.envlocally, Key Vault in prod. - Access Pydantic
SecretStrvia.get_secret_value(). - Parameterized logs; avoid sensitive values.
- Use
appkit_commons.database.session_manager.get_session_manager().session()for DB access outside Reflex handlers (notrx.session()).
What ships with it
2 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.
- yesterday First seen · 112 lines · 56 tokens per session scan A 970c2fada253
writing-python-code is a skill published in the GitHub repository jenreh/appkit-bpmn-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 912 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to writing-python-code, differing in 22 lines, and is treated as a copy.
Other skills, from other repositories
python-binance
Help developers use the python-binance library for trading on Binance. Use when code imports binance, references Client/AsyncClient, or asks about Binance API trading, market data, websockets, or account management.
python-clean-code
Review Python code in the gsc-mcp codebase for clean code violations. Checks function size, single responsibility, type hints, naming, error handling patterns, and adherence to the project's module contracts. Use when refactoring a module or before code review.
gurume-cli
Use the gurume CLI to search Japanese restaurants on Tabelog. Trigger this whenever the user wants to find, recommend, or research restaurants/eateries in Japan — by area (Tokyo, Osaka, Kyoto, 三重, etc.), by cuisine (ramen, sushi, yakiniku, izakaya...), or with a vague request like "where should I eat in Shibuya" or…
swag
This skill should be used when the user says "add proxy config", "create reverse proxy", "SWAG config", "nginx proxy", "expose service", "proxy configuration", "subdomain config", "subfolder config", "configure SWAG", "list proxy configs", "view proxy config", "edit proxy config", "remove proxy config", "check proxy…
add-tool
Add a new MCP tool to this WhatsApp server. Use when asked to expose a new capability, wrap a new bridge endpoint, or add a tool to tools.py or scheduling.py. Covers annotations, the confirm guard, core-set placement, retrieval aliases, and the eval case.
onpage-audit
Complete on-page audit of a single URL in one pass, combining heading structure, internal linking, technical meta tags, content quality and schema, then cross-checked against real Search Console data before any recommendation is made. Use when asked for a full page audit, an all-in-one check, or what to fix on a page.…