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 skills add d-mariano/spicyclaude --skill python-developmentgit clone --depth 1 https://github.com/d-mariano/spicyclaudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/d-mariano/spicyclaude/python-development)<a href="https://agentmods.dev/skills/d-mariano/spicyclaude/python-development"><img src="https://agentmods.dev/badge/skills/d-mariano/spicyclaude/python-development/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/d-mariano/spicyclaude/python-development"><img src="https://agentmods.dev/badge/skills/d-mariano/spicyclaude/python-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00121 | $0.00829 |
| Opus 5.5 | $0.00048 | $0.00332 |
| Sonnet 5.5 | $0.00024 | $0.00166 |
| Haiku 4.5 | $0.00012 | $0.00083 |
Grade A, and why
python-development 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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Development
Project Setup
Detect existing package manager first:
ls -la pyproject.toml poetry.lock uv.lock Pipfile* requirements.txt .venv/ 2>/dev/null
| Found | Use |
|---|---|
poetry.lock |
poetry install && poetry run pytest |
uv.lock |
uv sync && uv run pytest |
requirements.txt |
source .venv/bin/activate && pip install -r requirements.txt |
| Nothing | uv init && uv venv && source .venv/bin/activate |
Never switch package managers. Never install globally.
When using uv, avoid uv pip install and use commands like uv add and uv sync instead.
Type System
Avoid Any and generic dicts. Use structured types.
from __future__ import annotations
# ✗ AVOID
def process(data: dict[str, Any]) -> dict[str, Any]: ...
# ✓ PREFER
@dataclass(frozen=True, slots=True)
class User:
id: int
email: str
name: str
def process(user: User) -> User: ...
| Data Origin | Use |
|---|---|
| API input/output | Pydantic BaseModel |
| Internal objects | @dataclass(frozen=True, slots=True) |
| External JSON you don't control | TypedDict |
| Interface contracts | Protocol |
Details: type-system.md
Core Patterns
Pydantic for validation:
class CreateUserRequest(BaseModel):
email: EmailStr
name: str = Field(min_length=1, max_length=100)
Dataclass for domain objects:
@dataclass(frozen=True, slots=True)
class UserId:
value: int
Protocol for DI:
class UserRepository(Protocol):
def get(self, id: UserId) -> User | None: ...
def save(self, user: User) -> None: ...
Error handling — preserve chain, never swallow:
except httpx.HTTPError as e:
raise ServiceError("API failed") from e
# ✗ NEVER: except Exception: pass
Details: patterns.md
Testing
Fixtures over setup, parametrize for variants:
@pytest.fixture
def user_service(mock_repo: Mock) -> UserService:
return UserService(repo=mock_repo)
@pytest.mark.parametrize("email,valid", [
("[email protected]", True),
("invalid", False),
])
def test_email_validation(email: str, valid: bool) -> None:
assert validate_email(email) == valid
What ships with it
5 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.
- 1mo ago First seen · 132 lines · 121 tokens per session scan A 253f102177de
python-development is a skill published in the GitHub repository d-mariano/spicyclaude (5 stars, last pushed 2mo ago), licensed MIT. It adds 121 tokens to every session and 829 once invoked, about $0.0005 per session on Opus 5.5. 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
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Builds and differentiates PennyLane quantum circuits, hybrid PyTorch or JAX models, molecular VQE and QAOA workflows. Use for variational quantum algorithms, quantum machine learning, simulator validation, and moving validated circuits to provider plugins. For hardware-specific compilation use qiskit or cirq; for…
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
typing-exclusion-worker
Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.
python
Python development with ruff, mypy, pytest - TDD and type safety.