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/sergei-aronsen/claude-code-toolkit/pythonnpx skills add sergei-aronsen/claude-code-toolkit --skill pythongit clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkitWhat 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 | $0.00028 | $0.02193 |
| Opus 5 | $0.00014 | $0.01097 |
| Sonnet 5 | $0.00006 | $0.00439 |
| Haiku 4.5 | $0.00003 | $0.00219 |
Grade A, and why
Python Expert 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 2d 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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Expert Skill
This skill provides deep Python expertise including FastAPI/Django patterns, async handling, Pydantic v2 validation, SQLAlchemy 2.0, and security best practices.
Pydantic v2 (IMPORTANT!)
Always Use v2 Syntax
from pydantic import BaseModel, Field, ConfigDict, EmailStr, field_validator
# ✅ Pydantic v2 syntax
class UserCreate(BaseModel):
email: EmailStr
name: str = Field(min_length=2, max_length=100)
age: int | None = Field(default=None, ge=0, le=150)
class UserResponse(BaseModel):
id: int
email: str
name: str
model_config = ConfigDict(from_attributes=True)
# ❌ Pydantic v1 syntax (DON'T USE!)
class UserOld(BaseModel):
class Config: # Wrong! Use model_config
orm_mode = True # Wrong! Use from_attributes
Validation
from pydantic import field_validator, model_validator
class OrderCreate(BaseModel):
items: list[OrderItem]
discount_code: str | None = None
@field_validator('items')
@classmethod
def validate_items(cls, v: list[OrderItem]) -> list[OrderItem]:
if not v:
raise ValueError('Order must have at least one item')
return v
@model_validator(mode='after')
def validate_order(self) -> 'OrderCreate':
if self.discount_code and len(self.items) < 3:
raise ValueError('Discount requires at least 3 items')
return self
Async Patterns
Always await I/O Operations
# ✅ Correct - async for I/O
async def get_user(db: AsyncSession, user_id: int) -> User | None:
result = await db.execute(select(User).where(User.id == user_id))
return result.scalar_one_or_none()
# ✅ Parallel operations
async def get_dashboard_data(db: AsyncSession, user_id: int):
user, posts, notifications = await asyncio.gather(
get_user(db, user_id),
get_user_posts(db, user_id),
get_notifications(db, user_id),
)
return {"user": user, "posts": posts, "notifications": notifications}
# ❌ Sequential when could be parallel
async def get_dashboard_data_slow(db: AsyncSession, user_id: int):
user = await get_user(db, user_id)
posts = await get_user_posts(db, user_id) # Doesn't depend on user
notifications = await get_notifications(db, user_id)
return {"user": user, "posts": posts, "notifications": notifications}
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.
- 2d ago First seen · 350 lines · 28 tokens per session scan A 496e334e6224
Python Expert is a skill published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 16d ago), licensed MIT. It adds 28 tokens to every session and 2,193 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 2026-08-31.
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…