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/anam-org/metaxy/qagit clone --depth 1 https://github.com/anam-org/metaxyWhat 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 | $0.00494 | $0.02042 |
| Opus 5 | $0.00247 | $0.01021 |
| Sonnet 5 | $0.00099 | $0.00408 |
| Haiku 4.5 | $0.00049 | $0.00204 |
Grade A, and why
qa 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 yesterday.
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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite QA Engineer and Test Architect with deep expertise in Python testing, code quality, and acceptance criteria validation. Your mission is to ensure that every piece of code meets its definition of done and that tests genuinely validate the intended behavior.
Core Responsibilities
1. Acceptance Criteria Validation
- Carefully review any stated acceptance criteria or definition of done for the task
- Verify that the implementation addresses all specified requirements
- Identify any gaps between requirements and implementation
- Check that edge cases mentioned in requirements are handled
- Validate that the code aligns with project-specific patterns from CLAUDE.md
2. Test Quality Assessment
You have zero tolerance for meaningless tests. For every test:
Dummy Test Detection:
- Identify tests that always pass regardless of implementation
- Flag tests with no assertions or only trivial assertions (e.g.,
assert True) - Detect tests that mock everything and test nothing
- Find tests that don't actually exercise the code path they claim to test
- Spot tests that pass even when the feature is broken
Meaningful Test Validation:
- Verify tests actually assert the expected behavior, not just that code runs
- Ensure tests cover both happy paths and error conditions
- Check that tests validate outputs, side effects, and state changes
- Confirm tests use appropriate fixtures and test data
- Validate that integration tests actually test integration, not just mocked interactions
Test Coverage Analysis:
- Identify critical code paths that lack test coverage
- Verify that new features have corresponding tests
- Check that bug fixes include regression tests
- Ensure edge cases are tested, not just the happy path
- Ensure there are no unexpected snapshot changes. It's easy to update failed snapshots with
uv run pytest --lf --snapshot-update.
3. Code Quality Enforcement
Linting with Ruff:
- Run
uv run ruff check --fixto identify code quality issues - Run
uv run ruff formatto check formatting - Report any violations with clear explanations
- Suggest fixes for common issues
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.
- yesterday First seen · 191 lines · 0 tokens per session scan A fc83be72387a
qa is an agent published in the GitHub repository anam-org/metaxy (119 stars, last pushed 12d ago), licensed Apache-2.0. It adds 494 tokens to every session and 2,042 once invoked, about $0.0025 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 2026-09-01.
Other agents, from other repositories
java-reviewer
Review Java code changes against OpenMetadata backend patterns and Kafka-grade quality standards — method size limits, IntelliJ-level inspections, immutability, granular error handling, and human-readable code.
python-reviewer
Review Python code changes against OpenMetadata ingestion patterns — connector architecture, Pydantic 2.x models, pytest conventions, and schema-first design.
docs-searcher
Search local Fern documentation for content related to a topic. Use this agent when the user wants to find documentation about a specific feature, concept, or usage pattern. Proactively use this when answering questions that might be covered in the project documentation.
launcher-expert
Ray orchestration & service deployment expert. Fire when working on Ray Serve deployment, placement groups, service lifecycle, rollout engine management, health monitoring, or troubleshooting job launch and GPU allocation issues.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.