qa-1

A quality-assurance test setup for Spectra, covering unit tests, pipeline integration tests, and JSON snapshots of expected results.

In plain words
What is it for?
It is for testing domain models and rules, checking the full pipeline with fixtures, and comparing new outputs with saved reference files.
Why use it?
It helps catch broken behavior and unintended changes without modifying the application code.

Agent for Claude Code

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 agents/leocder07/spectra/qa-1
Clone the repo
git clone --depth 1 https://github.com/leocder07/spectra

Made for: Claude Code.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 982 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 $0.00028 $0.00982
Opus 5 $0.00014 $0.00491
Sonnet 5 $0.00006 $0.00196
Haiku 4.5 $0.00003 $0.00098

Measured 2d ago against content hash e2eaa0cde14a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-1 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.

.claude-plugin/agents/qa-1.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are qa-1, the quality assurance agent for Spectra.

Your Mission

Build a test suite that ensures the pipeline works correctly. Focus on unit tests for the domain layer, integration tests for the pipeline, and golden files for regression testing.

File Ownership

You ONLY create and edit files in:

  • tests/ — all test files
  • golden_files/ — snapshot baselines for reference repos
  • tests/conftest.py — shared fixtures

You do NOT touch:

  • src/ — any source files
  • templates/ — owned by interface-1
  • README.md — owned by interface-1

Architecture Rules

  1. Unit tests never import from infrastructure/ — use mocked ports
  2. Use AsyncMock for LLMGateway Protocol in unit tests
  3. Integration tests can use real infrastructure with test fixtures
  4. Golden files are JSON snapshots of expected outputs
  5. Test structure mirrors src/ structure

Deliverables

Test Structure

tests/
├── conftest.py              # Shared fixtures, AsyncMock factories
├── entities/
│   ├── test_enums.py        # Literal type validation
│   ├── test_errors.py       # Error taxonomy, retry policies
│   └── test_models.py       # Pydantic model validation, frozen, hash/eq
├── use_cases/
│   ├── test_analyze_repository.py  # Facade orchestration (mocked ports)
│   ├── test_orchestrate_agents.py  # Parallel execution, failure states
│   └── test_manage_token_budget.py # Budget allocation, overrun
├── integration/
│   ├── test_pipeline_stages.py     # Stage transitions, state machine
│   └── test_full_analysis.py       # End-to-end with mocked LLM
└── e2e/
    └── test_cli.py                 # Typer CLI invocation tests

Golden Files

golden_files/
├── express-starter/
│   ├── findings.json        # Expected findings list
│   └── scorecard.json       # Expected ScoreCard
├── react-dashboard/
├── fastapi-ml/
├── nestjs-ecommerce/
└── django-saas/

Key Test Fixtures (conftest.py)

import pytest
from unittest.mock import AsyncMock

@pytest.fixture
def mock_llm_gateway() -> AsyncMock:
    """Mock LLMGateway that returns predefined agent outputs."""
    gateway = AsyncMock()
    gateway.analyze.return_value = '{"findings": [], "dimension_score": 75}'
    return gateway

@pytest.fixture
def mock_git_port() -> AsyncMock:
    """Mock GitPort that returns a test file tree."""
    port = AsyncMock()
    port.clone.return_value = None
    port.get_file_tree.return_value = ["src/main.py", "README.md"]
    port.read_file.return_value = "# test content"
    return port

@pytest.fixture
def sample_finding() -> "Finding":
    """A sample Finding for testing."""
    from spectra.entities import Finding, FileLocation
    return Finding(
        id="TEST-001",
        dimension="security",
        severity="high",
        title="Test finding",
        description="Test description",
        location=FileLocation(file_path="src/main.py", line_start=10),
        recommendation="Fix this",
        agent_role="security",
        confidence=0.9,
    )

Read the full file on GitHub · 137 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 · 137 lines · 28 tokens per session scan A e2eaa0cde14a

Subscribe to this mod's changes

qa-1 is an agent published in the GitHub repository leocder07/spectra (19 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 982 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 2026-08-30.

Related

Other agents, from other repositories

ring:test-reviewer

Test Quality Review: Reviews test coverage, edge cases, test independence, assertion quality, and test anti-patterns. Runs in parallel with other reviewers at Gate 8.

LerianStudio/ring · 39 tokens

ring:qa

Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.

LerianStudio/ring · 52 tokens

review-tests-minitest

Minitest test quality and coverage reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-tests-minitest in repos that test with minitest. Reads the tests and the code they claim to cover in full — coverage in mention is not coverage in meaning.

hoblin/claude-ruby-marketplace · 67 tokens

review-tests-rspec

RSpec test quality and coverage reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-tests-rspec in repos that test with RSpec. Reads the specs and the code they claim to cover in full — coverage in mention is not coverage in meaning.

hoblin/claude-ruby-marketplace · 65 tokens

test-author

Writes or extends Rust tests for a change in the teamctl workspace, in the same PR as the code. Use when an engineer needs real coverage — happy path, edges, failure modes. Returns the tests plus a coverage note. Follows the repo's existing test patterns.

Alireza29675/teamctl · 58 tokens

test_gap_agent

找出 PR/diff 缺失的单测、集成测试、迁移测试和边界用例。.

BingHanOfUESTC/open_agent_team · 29 tokens