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/microsoft/hve-core/python-foundationalnpx skills add microsoft/hve-core --skill python-foundationalgit clone --depth 1 https://github.com/microsoft/hve-coreWhat 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 | $0.00017 | $0.01238 |
| Opus 5 | $0.00009 | $0.00619 |
| Sonnet 5 | $0.00003 | $0.00248 |
| Haiku 4.5 | $0.00002 | $0.00124 |
Grade A, and why
python-foundational 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Foundational Coding Standards Skill
Overview
Foundational Python excellence that every diff must satisfy. This skill is loaded first for any .py change. All higher-order skills build on it.
This content is a skill rather than an instructions file for three reasons: skills are distributed through the CLI plugin and VS Code extension without requiring consumers to copy files into their repo; new language skills can be added without modifying the review agent itself; and skills are loaded on demand, keeping the context window small when the diff contains no Python.
Core Checklist
1. Readability & Style
- Use Python naming:
PascalCaseclasses,snake_casefunctions/variables,UPPER_SNAKE_CASEconstants,_private members. - Group imports: stdlib → third-party → local (blank line between groups, no trailing whitespace).
2. Pythonic Idioms
- Prefer comprehensions for simple transforms; use explicit loops for complex logic/side-effects.
- Always use
withfor files, locks, DB connections. - Prefer
dataclass/NamedTuple/Enumfor data holders. - Use
pathliboveros.path; timezone-awaredatetimewhen relevant. - Use
*keyword-only arguments for multi-optional functions. - Never use mutable defaults or
global/nonlocalunless strictly required.
3. Function & Class Design
- Keep functions small and single-responsibility.
- Add docstrings to all public APIs (follow repo style).
- Document unavoidable side-effects.
- Follow codebase’s class-member ordering (if defined).
4. Type Safety Foundations
- Add type hints to all public APIs, module vars, and class attributes.
- Use PEP 695 (3.12+) or
TypeVarfor generics. - Avoid
Anyexcept in thin wrappers.
5. Error Handling
- Raise specific exceptions; never bare
except:(broadexcept Exception:only at app boundaries with logging). - No silent failures or generic error messages.
- Provide context, expected state, and guidance in every exception.
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 · 111 lines · 17 tokens per session scan A eab08a2ecc39
python-foundational is a skill published in the GitHub repository microsoft/hve-core (1,405 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 1,238 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…