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/rakaarwaky/qwen-web-arwaky/create-agent-pythonnpx skills add rakaarwaky/qwen-web-arwaky --skill create-agent-pythongit clone --depth 1 https://github.com/rakaarwaky/qwen-web-arwakyWrote 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/rakaarwaky/qwen-web-arwaky/create-agent-python)<a href="https://agentmods.dev/skills/rakaarwaky/qwen-web-arwaky/create-agent-python"><img src="https://agentmods.dev/badge/skills/rakaarwaky/qwen-web-arwaky/create-agent-python.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 | $0.00060 | $0.01150 |
| Opus 5 | $0.00030 | $0.00575 |
| Sonnet 5 | $0.00012 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
create-agent-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 3d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-agent-python
Agent = orchestration only. No I/O, no business logic, no domain computation, no local domain data.
Allowed imports: shared/* — taxonomy VOs, constants, aggregate ABCs, protocol ABCs, utility functions.
Forbidden imports: capabilities_*, agent_*, surface_*.
Allowed ops: for/while/async for, if/else/match, try/except/raise, asyncio.wait_for, collecting results into shared VOs.
Forbidden ops: open(), Path(), os.*, requests.*, httpx.*, sqlite3.*, asyncpg.*, stdout/stderr write, env mutation, global state mutation.
3-Block Structure
# Block 1: Class Definition & Constructor
# Block 2: Aggregate Method Implementation
# Block 3: Dunder Methods, Factories, Helpers
Method placement:
Module-level def? → EXTRACT to *_utility.py
@abstractmethod in aggregate ABC? → Block 2
Dunder / factory @classmethod? → Block 3
@staticmethod pure + no class dep? → EXTRACT to *_utility.py
Private helper (uses self)? → Block 3
Helper vs Utility
Keep in Block 3 if ANY: uses self, coupled to this class, factory, agent-specific logic, single-use.
Extract to utility only if ALL: no self/cls, pure, no side effects, domain-agnostic, reusable.
I/O: stateless + I/O + domain-agnostic = taxonomy utility. Stateless + I/O + domain-specific = capabilities.
Computation, Errors, VOs
Computation forbidden: arithmetic, totals, averages, .reduce/.fold, parsing, normalization. Allowed: iteration to call deps, routing results, propagating errors.
Error rules:
- Rule 1: Never silently discard — no
checker.check() or "". - Rule 2: Analysis orchestration → return
list[<ResultVO>], catch per-item into VO. - Rule 3: Execution orchestration → return
Result[...]. - Rule 4: Delegate I/O errors to capabilities — agent only wraps into VO.
VO rules: str/int/float forbidden for domain fields/contracts. bool for semantic toggles only.
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.
- 3d ago First seen · 115 lines · 60 tokens per session scan A 8cd25a123897
create-agent-python is a skill published in the GitHub repository rakaarwaky/qwen-web-arwaky (11 stars, last pushed 6d ago), licensed MIT. It adds 60 tokens to every session and 1,150 once invoked, about $0.0003 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
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.
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
python-sdk
Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.
datamodel-code-generator
Use this skill when the user wants Python data models, Pydantic models, dataclasses, TypedDicts, msgspec structs, or type-safe Python classes generated from OpenAPI, AsyncAPI, JSON Schema, GraphQL, JSON/YAML/CSV sample data, MCP tool schemas, Protocol Buffers, XML Schema, Apache Avro, or existing Python model objects.…