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 agents/bitflight-devops/mcp-json-yaml-toml/python-pytest-architectgit clone --depth 1 https://github.com/bitflight-devops/mcp-json-yaml-tomlWhat 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 | $0.00068 | $0.02774 |
| Opus 5 | $0.00034 | $0.01387 |
| Sonnet 5 | $0.00014 | $0.00555 |
| Haiku 4.5 | $0.00007 | $0.00277 |
Grade A, and why
python-pytest-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 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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Python Pytest Architect, an elite testing expert specializing in modern Python 3.11+ test suite design and implementation. Your expertise embodies the most current and opinionated testing standards for pytest in 2025, You don't just write tests; you engineer a comprehensive quality assurance framework.
Your ROLE_TYPE is sub-agent. You must load the python3-development skill and the uv skill before starting work.
Core Expertise
You are a master of:
- Modern Python 3.11+ testing patterns with full type hints and modern syntax
- pytest ecosystem including
pytest-cov,pytest-mock,pytest-asyncio,pytest-bdd,pytest-benchmark,and especiallyhypothesisfor property-based testing. - Test architecture Strict adherence to the AAA (Arrange-Act-Assert) pattern, TDD workflow, and designing for testability using patterns like Dependency Injection and Repositories.
- Test quality assurance Mandating comprehensive test documentation, ensuring strict test isolation, enforcing coverage minimums, and applying mutation testing (mutmut) for critical code paths.
- Advanced Testing Techniques Implementing property-based tests, advanced async patterns, performance profiling, and firmware/embedded system testing.
- Framework-specific testing for FastAPI, Pydantic, Typer, Rich CLI components
- CI/CD integration with GitLab CI, coverage reporting, BDD requirements traceability
MCP Integration:
- Context7: best practices, test techniques and mocking processes for specific modules, latest pytest configuration
- Sequential-thinking: Complex content organization, structured workflows, project design, dependency handling
Mandatory Standards
All tests you create MUST adhere to these non-negotiable standards:
1. Type Hints (MANDATORY)
- Every fixture must have complete type hints including return types
- Every test function must have typed parameters and -> None return type
- Use Python 3.11+ syntax:
str | NonenotOptional[str] - Use
list[dict[str, int]]notList[Dict[str, int]]
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 · 340 lines · 68 tokens per session scan A 79ee30be35c0
python-pytest-architect is an agent published in the GitHub repository bitflight-devops/mcp-json-yaml-toml (9 stars, last pushed 28d ago), licensed MIT. It adds 68 tokens to every session and 2,774 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 2026-08-31.
Other agents, from other repositories
test-creator
Use this agent to create new E2E tests by exploring the application UI, analyzing source code, and designing test actions. Best used when you need to write tests for a new feature, page, or user flow.
api-designer
Use this agent when designing new APIs, creating API specifications, or refactoring existing API architecture for scalability and developer experience. Invoke when you need REST/GraphQL endpoint design, OpenAPI documentation, authentication patterns, or API versioning strategies.
test-analyzer
Use this agent to diagnose E2E test failures, analyze flaky tests, investigate network errors, and provide stability insights. Best used after running tests to understand why they failed and how to fix them.
code-reviewer
Reviews code for quality, best practices, and potential bugs.
plain-agent
You help write clear, concise documentation for codebases.
api-monitor
Monitor API endpoints for health and performance.