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 CassetteTapeCrackle/claude-starters --skill clean-code-pythongit clone --depth 1 https://github.com/CassetteTapeCrackle/claude-startersWrote 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/cassettetapecrackle/claude-starters/clean-code-python)<a href="https://agentmods.dev/skills/cassettetapecrackle/claude-starters/clean-code-python"><img src="https://agentmods.dev/badge/skills/cassettetapecrackle/claude-starters/clean-code-python/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/cassettetapecrackle/claude-starters/clean-code-python"><img src="https://agentmods.dev/badge/skills/cassettetapecrackle/claude-starters/clean-code-python.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 | $0.00039 | $0.00312 |
| Opus 5.5 | $0.00016 | $0.00125 |
| Sonnet 5.5 | $0.00008 | $0.00062 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
clean-code-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 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.
What it actually says
Clean-code Python (depth)
On top of the base rules (type hints, ruff, pytest).
Types & data
- Explicit hints on public functions;
from __future__ import annotationsfor forward refs. No bareAny. - Model records with
@dataclass(or pydantic at boundaries); avoid dicts-as-objects for structured data.
Footguns
- Never mutable default args (
def f(x=[])) — useNone+ assign inside. - EAFP over LBYL:
try/exceptaround the operation rather than pre-checking, but keeptrybodies small. - No bare
except:— catch specific exceptions; re-raise with context.
Idioms
pathlib.Pathoveros.pathstring surgery. Context managers (with) for files/locks/resources.- Comprehensions/generators over manual accumulation loops; generators for large/streamed data.
- f-strings for formatting;
loggingnotprintfor diagnostics.
Smells
- A function taking/returning big untyped dicts → dataclass.
except Exception: pass→ swallows bugs.- Manual file
open/closewithoutwith→ leak on error.
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 · 28 lines · 39 tokens per session scan A c242f572097a
clean-code-python is a skill published in the GitHub repository CassetteTapeCrackle/claude-starters (1 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 312 once invoked, about $0.0002 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
python-services
Python patterns for CLI tools, async parallelism, and backend services. Use when building CLI apps, async/parallel Python, FastAPI services, background jobs, or configuring Python project tooling (uv, ruff, ty).
python-coder
Implements Python code following PEP 8, type hints, and project conventions. Use when implementing features designed by python-architect.
python-testing
Python testing patterns with pytest including unit tests, integration tests, fixtures, mocking, and coverage. Use when writing Python tests.
Unit Test Scaffold (Python/pytest)
Generate Python/pytest unit test skeletons from specifications.
python-architect
Creates high-level Python architecture with protocols, test stubs, and module structure. Use when designing Python projects or features.
py-reviewer
Review selected Python code for typing, async and exception behavior, resource ownership, data access, framework boundaries, and concrete contract defects in the project's actual runtime.