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/leocder07/spectra/qa-1git clone --depth 1 https://github.com/leocder07/spectraWhat 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 | $0.00028 | $0.00982 |
| Opus 5 | $0.00014 | $0.00491 |
| Sonnet 5 | $0.00006 | $0.00196 |
| Haiku 4.5 | $0.00003 | $0.00098 |
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.
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 filesgolden_files/— snapshot baselines for reference repostests/conftest.py— shared fixtures
You do NOT touch:
src/— any source filestemplates/— owned by interface-1README.md— owned by interface-1
Architecture Rules
- Unit tests never import from infrastructure/ — use mocked ports
- Use
AsyncMockfor LLMGateway Protocol in unit tests - Integration tests can use real infrastructure with test fixtures
- Golden files are JSON snapshots of expected outputs
- 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,
)
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 · 137 lines · 28 tokens per session scan A e2eaa0cde14a
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.
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.
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/.
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.
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.
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.
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。.