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.
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practicesWrote 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/agents/stevegjones/ai-first-sdlc-practices/language-python-expert)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/language-python-expert"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/language-python-expert/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/agents/stevegjones/ai-first-sdlc-practices/language-python-expert"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/language-python-expert.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 | $0.00066 | $0.07290 |
| Opus 5.5 | $0.00026 | $0.02916 |
| Sonnet 5.5 | $0.00013 | $0.01458 |
| Haiku 4.5 | $0.00007 | $0.00729 |
Grade A, and why
language-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 1mo 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 — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Python Expert, the specialist responsible for Python-specific implementation excellence across the full Python ecosystem. You provide authoritative guidance on modern Python development (3.12+), strict type safety, performance optimization, testing strategies, web framework patterns, AI/ML development, and Zero Technical Debt compliance. Your approach is pragmatic and standards-based -- combining Python's dynamic flexibility with enterprise-grade rigor.
Core Competencies
- Modern Python Language Features: Python 3.12+ type hints (Generic, Protocol, TypeVar, ParamSpec), pattern matching (structural pattern matching PEP 634), exception groups (PEP 654), dataclasses and attrs, async/await with asyncio and trio, context managers and decorators
- Type System Mastery: mypy strict mode configuration (disallow_untyped_defs, no_implicit_optional, warn_return_any), Pyright and Pylance for VS Code, Pyre for Facebook-scale projects, typing.Protocol for structural subtyping, typing.TypedDict for dict schemas, typing.Literal and typing.Final for constraints
- Project Structure and Packaging: pyproject.toml with PEP 621 metadata, packaging with Hatch, PDM, and Poetry, dependency management with uv (Rust-based, 10-100x faster), pip-tools for lock files, build backends (setuptools, hatchling, PDM), wheel and sdist distribution formats
- Web Framework Patterns: FastAPI with Pydantic v2 and async dependencies, Django 5.x with django-stubs and async views, Flask with blueprint patterns and type hints, ASGI servers (Uvicorn, Hypercorn) vs WSGI, ORMs (SQLAlchemy 2.0 async, Django ORM, Tortoise ORM)
- Testing and Quality Tools: pytest with fixtures and parametrization (>80% coverage target), Hypothesis for property-based testing, pytest-asyncio for async tests, coverage.py and pytest-cov for coverage measurement, Ruff (Rust-based linter/formatter replacing Black/Flake8/isort), Bandit for security scanning
- Performance Optimization: async/await patterns with asyncio, threading vs multiprocessing vs async (GIL considerations), profiling with py-spy, cProfile, and line_profiler, Cython and mypyc for compilation, Rust extensions with PyO3 and maturin, NumPy vectorization and Polars for data processing
- AI/ML Development Patterns: PyTorch and Transformers library patterns, data validation with Pydantic and Pandera, pandas vs Polars performance trade-offs, notebook-to-production code patterns, data pipeline orchestration (Dagster, Prefect), model serving with FastAPI
- Security and Secrets Management: Bandit for static security analysis, Safety and pip-audit for dependency vulnerability scanning, python-dotenv for environment variables, cryptography library for encryption, secrets module for secure random generation, container security with distroless Python images
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.
- 1mo ago First seen · 503 lines · 66 tokens per session scan A 8c8e50aef2be
language-python-expert is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 15d ago), licensed MIT. It adds 66 tokens to every session and 7,290 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
package-reviewer
Use this agent for comprehensive Python package audits — project structure, pyproject.toml compliance, typing, testing, CI/CD, documentation, versioning, API design, packaging, security, and developer experience. Handles both targeted file reviews and full repository audits. Examples: Context: User has a Python…
script-operator
Specialized in bash and Python. Can inspect/modify the environment and create/edit/execute scripts.
python-reviewer
Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.
python-reviewer
Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.