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 Netcracker/qubership-ai-packages --skill pythondoc-authoringgit clone --depth 1 https://github.com/Netcracker/qubership-ai-packagesWrote 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/netcracker/qubership-ai-packages/pythondoc-authoring)<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/pythondoc-authoring"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/pythondoc-authoring/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/netcracker/qubership-ai-packages/pythondoc-authoring"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/pythondoc-authoring.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 | $0.00240 | $0.15948 |
| Opus 5 | $0.00120 | $0.07974 |
| Sonnet 5 | $0.00048 | $0.03190 |
| Haiku 4.5 | $0.00024 | $0.01595 |
Grade A, and why
pythondoc-authoring scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`def fetch(timeout: float)` carries one fact, the unit, and pays for it with a line the reader has to sift. The How it starts
The opening of the file, as written. The whole thing — 964 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring a Python docstring
This skill governs what a docstring says and in what order. Wording, tone, sentence length, and dialect belong to
english-developer-style: load it too, and defer to it on the prose. The two compose: this skill picks the slots; that
one writes the sentences.
Two facts about Python change the job at the root, and both come back in later sections.
A docstring is a runtime object, not source text. It is __doc__: help() renders it, doctest executes the
examples in it, a CLI framework can print it as --help, and python -OO deletes it. Every one of those is a surface
an edit reaches.
No formatter owns its prose. black and ruff format re-indent a docstring's body and strip its trailing
whitespace, but they never rewrap it (measured on ruff 0.14). You place the line breaks, and E501 counts them.
Conventions carried in from another language's doc comments go wrong in three places, so do not translate them in your head. The summary is one physical line whose mood the project picks, not a first sentence fixed in the third person (§3). References have no syntax of their own, so the form depends on the renderer and nothing checks it by default (§5). The section headings belong to a dialect the project has already chosen, not to the language (§6).
1. The correction that matters most
"Document the why, not the what" is half wrong for a docstring, and the wrong half does the damage.
An inline # comment documents the why; it sits next to code the reader can already see. A docstring documents the
contract: what a caller may rely on, what an implementer must guarantee, what holds before and after. That is a
what at the level of a promise, not a restatement of the code.
The failure mode is therefore not "explains what the code does". It is one of these:
- Narrating the implementation.
Loops over the rows and adds each to the index.The body already states it, and the docstring becomes false on the next refactor. - Justifying the code's existence.
This helper centralizes the retry logic every client copied.That belongs in the commit message and the pull request description. A docstring's reader has to use or fix the thing, not decide whether to merge it. - Restating the annotations, which is Python's own.
Args: timeout (float): the timeout in seconds.ondef fetch(timeout: float)carries one fact, the unit, and pays for it with a line the reader has to sift. The annotations are the signature; §6 says what a parameter line has to add before it earns its place.
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 Changed · -15 lines 049e1981b9be
- 6d ago Changed · +176 lines · +20 tokens per session 9135c08fe8ba
- 11d ago First seen · 803 lines · 220 tokens per session scan A c6144ead70a1
pythondoc-authoring is a skill published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 240 tokens to every session and 15,948 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
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.