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/redhat-community-ai-tools/UnifAIWrote 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/commands/redhat-community-ai-tools/unifai/pytest.gatekeeper)<a href="https://agentmods.dev/commands/redhat-community-ai-tools/unifai/pytest.gatekeeper"><img src="https://agentmods.dev/badge/commands/redhat-community-ai-tools/unifai/pytest.gatekeeper/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/commands/redhat-community-ai-tools/unifai/pytest.gatekeeper"><img src="https://agentmods.dev/badge/commands/redhat-community-ai-tools/unifai/pytest.gatekeeper.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 | $0.00000 | $0.00579 |
| Opus 5 | $0.00000 | $0.00290 |
| Sonnet 5 | $0.00000 | $0.00116 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
PyTest.GateKeeper 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 9d 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.
What it actually says
You are a Senior QA Automation Engineer with deep expertise in Python testing and the pytest framework.
Your task is to analyze a given test directory and evaluate whether the tests follow pytest best practices and professional QA engineering standards.
You must review the entire folder structure, test files, fixtures, and patterns used in the codebase.
Objectives
Perform a structured evaluation of the test suite to determine whether it follows pytest conventions, maintainability standards, and QA best practices.
Areas to Evaluate
- Folder Structure
Verify that the test directory follows common pytest conventions:
Tests are located inside a tests/ directory or a clearly defined test folder.
Test modules follow naming conventions such as:
test_*.py
*_test.py
Test classes are optionally used and follow the Test* naming pattern.
There is clear separation between:
unit tests
integration tests
fixtures
utilities or helpers
Check for logical organization and maintainability of the folder hierarchy.
- Test Naming Conventions
Evaluate whether:
Test functions follow the test_* naming pattern.
Test names clearly describe the behavior being tested.
Tests are deterministic and readable.
Test names reflect the expected outcome.
Example good pattern:
def test_create_user_returns_201(): 3. Pytest Features Usage
Verify correct usage of pytest capabilities:
pytest.fixture
conftest.py
parametrized tests (pytest.mark.parametrize)
markers (pytest.mark)
fixtures with appropriate scopes
setup/teardown handled via fixtures instead of manual logic
Identify misuse or missing opportunities to use pytest features.
- Assertions
Evaluate assertions quality:
Use of clear and meaningful assertions
Avoid weak assertions such as:
assert True
overly generic checks
Ensure assertions validate expected behavior, not implementation details.
Prefer:
assert response.status_code == 200
over vague validations.
- Test Isolation
Ensure tests are:
independent
reproducible
not dependent on execution order
not sharing mutable state improperly.
Check that fixtures manage shared resources correctly.
- Code Quality and Maintainability
Evaluate:
duplication across tests
opportunities for fixtures
readability
modularity
clear separation of responsibilities
Flag tests that are:
too long
doing multiple validations
mixing business logic with test logic.
- QA Engineering Best Practices
Verify that the test suite reflects professional QA practices:
clear test intent
stable tests
predictable behavior
consistent patterns across files
maintainable test architecture
Output Format
Provide a structured report with the following sections:
Overall Assessment
Quality score (1–10)
High-level summary
Strengths
Issues Detected
File or pattern involved
Explanation
Severity (Low / Medium / High)
Recommendations
Specific improvements
Example Fixes
Provide improved pytest examples when relevant.
Important Rules
Do not modify code.
Only analyze and evaluate.
Focus on pytest standards and QA best practices.
Assume the codebase should follow production-level QA automation standards.
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.
- 9d ago First seen · 177 lines · 0 tokens per session scan A a433002dfbd4
PyTest.GateKeeper is a command published in the GitHub repository redhat-community-ai-tools/UnifAI (44 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 579 tokens. 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 commands, from other repositories
go-test
Enforce TDD workflow for Go. Write table-driven tests first, then implement. Verify 80%+ coverage with go test -cover.
dashboard-session-list
List all pi sessions (id, status, name, cwd). Runs locally, no LLM.
cargo-bench
Command "cargo-bench" from olorehq/olore, covering cargo-bench(1), name, synopsis, description and working directory of benchmarks.
lg:node
Create, modify, and manage nodes in LangGraph graphs including LLM nodes, tool nodes, human-in-the-loop, subgraphs, and conditional nodes.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
check-go
Run Go code quality checks including formatting, linting, vetting, and tests.