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/systemowiec/ai-agents-workspace-starter/python-standardsnpx skills add systemowiec/ai-agents-workspace-starter --skill python-standardsgit clone --depth 1 https://github.com/systemowiec/ai-agents-workspace-starterWrote 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/systemowiec/ai-agents-workspace-starter/python-standards)<a href="https://agentmods.dev/skills/systemowiec/ai-agents-workspace-starter/python-standards"><img src="https://agentmods.dev/badge/skills/systemowiec/ai-agents-workspace-starter/python-standards.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.02183 |
| Opus 5 | $0.00019 | $0.01092 |
| Sonnet 5 | $0.00008 | $0.00437 |
| Haiku 4.5 | $0.00004 | $0.00218 |
Grade A, and why
python-standards 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 4d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Enterprise Python Standards
Principal/Staff-level Python patterns. NOT junior/mid rules. These standards produce code that scales, is testable, and is maintainable by large teams. Apply to ALL Python code in this project.
A. Architecture & Design
- Protocols over ABC - Use
typing.Protocolfor interfaces, notabc.ABC. Protocols enable structural subtyping (duck typing with type safety) without inheritance coupling. - Frozen dataclasses for value objects - Immutable by default:
@dataclass(frozen=True, slots=True). Mutable state only where explicitly needed. - Result pattern for expected failures - Return
Result[T, E](orT | ErrorType) instead of raising exceptions for business-level failures. Exceptions only for truly exceptional (unexpected) situations. __slots__on hot-path classes - Reduces memory footprint and attribute access time. Always on dataclasses (slots=True), domain models, and DTO/schema objects.- Composition over inheritance - Favor dependency injection and delegation. Inheritance allowed only for framework requirements (e.g.,
AgentExecutor). - Single Responsibility - One class = one reason to change. Max 500 lines/class, 50 lines/function. If a method needs a comment explaining "what it does", it should be a separate function.
B. Type System
- Exhaustive type hints - Every function: params + return type. No
Anyunless interfacing with untyped libraries (and wrap it immediately). TypeVarwith bounds -T = TypeVar("T", bound=BaseModel)for generic functions operating on model subtypes.ParamSpecfor decorator preservation - Decorators must preserve wrapped function's signature:P = ParamSpec("P"),Callable[P, R].TypeGuardfor narrowing - UseTypeGuard[SpecificType]in filter/validation functions to enable type narrowing in callers.Finalfor constants - All module-level constants annotated withFinal. Prevents accidental reassignment.Annotatedfor validation metadata -Annotated[int, Field(ge=0)]instead of runtime-only checks. Self-documenting constraints.TYPE_CHECKINGfor circular imports - Import type-only dependencies insideif TYPE_CHECKING:block. Never restructure code just to avoid forward references.
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.
- 4d ago First seen · 125 lines · 38 tokens per session scan A a51ee21376fb
python-standards is a skill published in the GitHub repository systemowiec/ai-agents-workspace-starter (2 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 2,183 once invoked, about $0.0002 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
bump-dependency
Bumps a Python package dependency across Home Assistant Core integrations, regenerates core requirement files, runs verification tests and prek lint, and prepares a pull request with proper release/compare links.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.