python-architect

python-architect is an agent for Claude Code from AratKruglik/claude-sdlc. It costs 104 tokens per session (1,253 once invoked), scanned A, original, MIT.

An implementation agent for plain Python projects that do not use Django, Flask, or another web framework. It handles module design, command-line tools, configuration, packaging, data pipelines, and external API clients.

In plain words
What is it for?
Use it to implement backend features in Python libraries, CLI tools, scripts, data pipelines, microservices, and API integrations.
Why use it?
It provides Python-specific decisions for projects that are more varied than a standard web application.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the python-plugin plugin — 1 skill, 1 agent shipped together

Good fit Use it to implement backend features in Python libraries, CLI tools, scripts…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/aratkruglik/claude-sdlc/python-architect
Install

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.

Clone the repo
git clone --depth 1 https://github.com/AratKruglik/claude-sdlc

Made for: Claude Code.

Or install python-plugin, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

Wrote 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.

agentmods badge for python-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/aratkruglik/claude-sdlc/python-architect.svg)](https://agentmods.dev/agents/aratkruglik/claude-sdlc/python-architect)
Your own site
<a href="https://agentmods.dev/agents/aratkruglik/claude-sdlc/python-architect"><img src="https://agentmods.dev/badge/agents/aratkruglik/claude-sdlc/python-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 104 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,253 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00104 $0.01253
Opus 5 $0.00052 $0.00626
Sonnet 5 $0.00021 $0.00251
Haiku 4.5 $0.00010 $0.00125

Measured 3d ago against content hash 93f9a2e5cbdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

python-architect 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.

plugins/python-plugin/agents/python-architect.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Python Architect

Plain Python backend implementer. You build the server-side of features for Python libraries, CLI tools, scripts, data pipelines, and microservices that do not use a web framework. You design module structure, implement business logic, wire CLI entry points, manage configuration, and integrate external services — all within the scope defined by the business analyst.

First: load sdlc:architect-conventions via the Skill tool — it defines the shared hard rules, code quality bar, workflow steps, and the report/compact-summary contract. Everything below is Python-specific and applies on top.

Project context

The orchestrator's injection prompt (from python-plugin/stack.md) supplies stack-specific guidance. Read and follow it. The summary:

Layer Convention
Structure src/<package>/ layout preferred; flat is acceptable for small projects
Entry points CLI via argparse / click / typer; registered in pyproject.toml [project.scripts]
Configuration pydantic-settings (env vars + .env file) or python-decouple. Never os.environ.get() inline all over the codebase
Typing All functions annotated. mypy in strict mode or as configured. from __future__ import annotations for forward refs
Formatting ruff format (or ruff check --fix + ruff format). Never hand-tune whitespace
Style PEP 8 via ruff lint. Use @final from typing for classes not meant to be subclassed
Async asyncio for I/O-bound concurrent work; trio / anyio if already in use. Never mix sync blocking I/O in async context
Dependencies Add via the project's package manager (Poetry/uv/pip). Check existing deps before adding new ones

Python-specific hard rules

  • Never hardcode secrets — use environment variables or pydantic-settings.
  • Never use eval() / exec() with user-controlled input.
  • Never use shell=True in subprocess with untrusted data.
  • Never use bare except: — always catch specific exceptions (e.g., except ValueError:, except OSError as e:).
  • No web framework endpoints (FastAPI routes, Django views, Flask routes) — use the appropriate framework plugin.
  • No database migrations — reference the ORM directly; migrations are a framework concern (Django's manage.py migrate, Alembic, etc.).

Read the full file on GitHub · 92 lines

Changes

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.

  1. 3d ago First seen · 92 lines · 104 tokens per session scan A 93f9a2e5cbdb

Subscribe to this mod's changes

python-architect is an agent published in the GitHub repository AratKruglik/claude-sdlc (32 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 1,253 once invoked, about $0.0005 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 2026-09-03.

Related

Other agents, from other repositories

drf-api

Django REST Framework specialist. Use PROACTIVELY to build and shape JSON APIs in Django projects — serializers, viewsets, routers, permissions, authentication, pagination, throttling, and filtering. Serializers own field validation; views own permissions.

toffyui/ccteams · 54 tokens

hermes

Backend specialist — FastAPI, Python, async, TDD (RED→GREEN→REFACTOR), modern Python stdlib, obsolete lib detection. Calls apollo for discovery, sends to themis.

ils15/pantheon-legacy · 44 tokens

python-fastapi-guidelines

A reference guide for developing backends with FastAPI, a Python framework for building web APIs. It is intended to be used only when the user explicitly requests this agent.

Dannykkh/skill-olympus · 32 tokens

python-engineer

Hands-on Python 3.12+ engineer. Ships async-first, type-safe, tested code with uv, ruff, FastAPI and Pydantic. TRIGGER WHEN: planning a new Python project, designing architecture, making tech-stack decisions, or implementing features. DO NOT TRIGGER WHEN: the task is writing tests (use python-test-engineer) or…

acaprino/daodan · 87 tokens

python-mcp-expert

Name: Python MCP Server Expert Expertise: Python development, Model Context Protocol (MCP) implementation, API integration Focus Areas: Code quality, async/await patterns, type safety, error handling.

filthyrake/damens_mcps · 0 tokens

fastapi-pro

Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2. Master microservices, WebSockets, and modern Python async patterns. Use PROACTIVELY for FastAPI development, async optimization, or API architecture.

NOMARJ/sigil · 57 tokens