python-dev

A guided workflow for developing Python software, from understanding the project through design, coding, review, and tests.

In plain words
What is it for?
Use it to plan module structure, define interfaces, create pytest test stubs, implement features, and review and test Python code.
Why use it?
It breaks development into clear stages and checks the project's existing structure and tools before changes are made. Unclear requirements are addressed before implementation.

Command

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.

agentmods
npx agentmods add commands/dmitriyyukhanov/claude-plugins/python-dev
Clone the repo
git clone --depth 1 https://github.com/DmitriyYukhanov/claude-plugins
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.00540
Opus 5 $0.00009 $0.00270
Sonnet 5 $0.00003 $0.00108
Haiku 4.5 $0.00002 $0.00054

Measured 2d ago against content hash 9d256f6d2010, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-dev 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.

plugins/python-dev/commands/python-dev.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Python Development Workflow

You are orchestrating a complete Python development workflow. Follow these phases systematically.

Phase 1: Discovery

First, understand the project and task:

  1. Check for Python project markers:

    • pyproject.toml
    • requirements.txt or Pipfile
    • setup.py or setup.cfg
    • .py files
    • Framework config (FastAPI, Django, Flask)
  2. Read existing architecture:

    • Check for CLAUDE.md or project documentation
    • Look at existing code patterns in src/
    • Identify framework and dependencies
  3. Clarify requirements if task is ambiguous using AskUserQuestion

Phase 2: Architecture

Use the python-architect skill knowledge to:

  1. Design module structure - Protocols, package hierarchy
  2. Create test stubs - pytest test cases
  3. Generate Mermaid diagrams - Class, data flow diagrams
  4. Define contracts - Protocols/ABCs before implementations

Present the architecture to the user for approval before implementing.

Phase 3: Implementation

Use the python-coder skill knowledge to implement:

  1. Follow PEP 8 and project conventions precisely
  2. Implement against the test stubs created in Phase 2
  3. Run tests continuously as you implement
  4. Use type hints everywhere

Phase 4: Review

Spawn the python-reviewer agent to perform Python-specific code review:

  • Type hint coverage
  • PEP 8 compliance
  • Error handling patterns
  • Async correctness
  • Performance concerns

Phase 5: Testing

Use the python-testing skill knowledge to:

  1. Ensure unit tests pass
  2. Ensure integration tests pass
  3. Generate coverage report for critical paths if requested

Workflow Commands

You can run individual phases:

  • "architect only" - Just Phase 2
  • "implement only" - Just Phase 3 (requires existing architecture)
  • "review only" - Just Phase 4
  • "test only" - Just Phase 5

Usage Examples

/python-dev Add REST API with FastAPI
/python-dev Implement data processing pipeline
/python-dev Create CLI tool with Click

Read the full file on GitHub · 86 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. 2d ago First seen · 86 lines · 17 tokens per session scan A 9d256f6d2010

Subscribe to this mod's changes

python-dev is a command published in the GitHub repository DmitriyYukhanov/claude-plugins (7 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 540 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.