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/codeready-toolchain/tarsyWrote 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/codeready-toolchain/tarsy/create-python-tests)<a href="https://agentmods.dev/commands/codeready-toolchain/tarsy/create-python-tests"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/create-python-tests/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/codeready-toolchain/tarsy/create-python-tests"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/create-python-tests.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 | $0.01372 |
| Opus 5.5 | $0.00000 | $0.00549 |
| Sonnet 5.5 | $0.00000 | $0.00274 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
create-python-tests 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Tests for Python LLM Service
Running Tests
From Project Root
All tests:
make test- Run all tests (Go + Python + Dashboard)make test-go- Run all Go testsmake test-python- Run all Python tests
Python-specific:
make test-llm- Run LLM service testsmake test-llm-unit- Run unit tests onlymake test-llm-integration- Run integration tests onlymake test-llm-coverage- Run with coverage report
Go-specific:
make test-go-coverage- Run Go tests with coverage report
From llm-service/ Directory
- All tests:
uv run pytest tests/ -v - Unit tests only:
uv run pytest tests/ -m unit -v - Integration tests only:
uv run pytest tests/ -m integration -v - Coverage:
uv run pytest tests/ --cov=llm --cov-report=term-missing - Specific file:
uv run pytest tests/test_servicer.py -v - Specific test:
uv run pytest tests/test_servicer.py::TestLLMServicer::test_generate_success -v - Show print statements:
uv run pytest -s - Stop on first failure:
uv run pytest -x
Critical Rules
1. Be Pragmatic
Write tests that add real value. If a test requires overly complex mocking or doesn't validate meaningful behavior, skip it. It's better to have no test than a brittle one that breaks with every minor change. If fighting with mocks, consider an integration test instead.
2. Test Behavior, Not Implementation
Focus on what the code does, not how. Don't test that specific internal methods were called or verify exact sequences of internal function calls.
3. No Historical Comments in Code
No # Added in TASK-0025 or # Testing new implementation. Historical context belongs in git commits. Tests should be self-explanatory.
4. Extend Existing Tests Before Creating New Ones
When code already has test coverage, prefer modifying or extending existing tests to cover new behavior rather than creating new test functions that largely duplicate what's already there. Add cases to existing parameterized tests when the scenario fits.
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 · 126 lines · 0 tokens per session scan A 77e1d2c6e286
create-python-tests is a command published in the GitHub repository codeready-toolchain/tarsy (10 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,372 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 2026-08-31.
Other commands, from other repositories
aqe-generate
Generate comprehensive test suites using AI-powered analysis and sublinear optimization.
testing
Comprehensive testing through distributed execution.
verify
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…
generate-widget
Génération Widget Flutter avec Tests.
api-endpoint
Création Endpoint API Platform.
test-suite
Run comprehensive test suite with coverage analysis.