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 skills/xsovad06/sova/testing-patternsnpx skills add xsovad06/sova --skill testing-patternsgit clone --depth 1 https://github.com/xsovad06/sovaWhat 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 | $0.00040 | $0.00944 |
| Opus 5 | $0.00020 | $0.00472 |
| Sonnet 5 | $0.00008 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
testing-patterns 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOVA Testing Patterns
When writing or modifying files in tests/, follow these conventions. Reference: docs/testing-guidelines.md.
Framework
asyncio_mode = "auto"-- no@pytest.mark.asyncioneeded on async tests- All tests flat in
tests/-- no subdirectories, noconftest.py - Tests grouped with classes. Fixtures defined per-file, not shared.
Required Fixtures
In-memory DB (autouse in any file touching ORM):
@pytest.fixture(autouse=True)
async def setup_db():
os.environ["SOVA_DATABASE_URL"] = "sqlite+aiosqlite://"
await init_db(run_migrations=False)
yield
await close_db()
os.environ.pop("SOVA_DATABASE_URL", None)
Dashboard client:
@pytest.fixture
async def client(tmp_path):
app = create_app(project_dir=tmp_path)
transport = ASGITransport(app=app)
async with AsyncClient(transport=transport, base_url="http://test") as ac:
yield ac
Mock Rules
-
Patch at the import site, not the definition site:
# Correct patch("sova.adapters.github.run", new_callable=AsyncMock) # Wrong patch("sova.utils.shell.run", new_callable=AsyncMock) -
Use
patch.objectfor split modules -- patch the actual submodule, not the re-export facade:patch.object(agent_lifecycle, "_get_project_agents", return_value=pa) -
ShellResult factory -- define per-file:
def _shell_result(stdout="", stderr="", returncode=0): return ShellResult(returncode=returncode, stdout=stdout, stderr=stderr) -
Context factory -- define per-file:
def _make_ctx(**kwargs) -> ExecutionContext: defaults = {"project_dir": Path("/tmp/test"), "config": ProjectConfig(), "adapter": _mock_adapter(), "issue_number": "42", "role": "developer"} defaults.update(kwargs) return ExecutionContext(**defaults) -
Multi-call methods: use
side_effectlist.
Pitfalls
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 · 89 lines · 40 tokens per session scan A 57e312b2217b
testing-patterns is a skill published in the GitHub repository xsovad06/sova (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 944 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
codex-autonomous-dev
NightPilot / 夜航员: reusable autonomous Codex development workflow for long-running, unattended, goal-mode, overnight, full-auto, hands-off, low-interruption software development. Use when the user mentions NightPilot, 夜航员, $codex-autonomous-dev, codex-autonomous-dev, 全自动, 无人开发, 长时间开发, 目标模式, 撒手不管, 睡觉也能跑, 老工作流接管…
skill-integration
Patterns for agent skill discovery, referencing, and composition using progressive disclosure architecture. Use when building agents, composing skills, or optimizing context usage. TRIGGER when: skill discovery, agent integration, skill composition, progressive disclosure. DO NOT TRIGGER when: implementing features…
api-design
REST API design best practices covering versioning, error handling, pagination, and OpenAPI documentation. Use when designing or implementing REST APIs or HTTP endpoints. TRIGGER when: API design, REST endpoint, HTTP route, OpenAPI, swagger, pagination. DO NOT TRIGGER when: internal library code, CLI tools, non-HTTP…
api-integration-patterns
Subprocess safety, GitHub CLI integration, retry logic, authentication, rate limiting, and timeout handling. Use when integrating external APIs or CLI tools. TRIGGER when: subprocess, gh cli, API call, retry logic, rate limiting, authentication. DO NOT TRIGGER when: internal function calls, pure Python logic, config…
agent-output-formats
Standardized output formats for research, planning, implementation, and review agents. Use when generating agent outputs or parsing agent responses.
advisor-triggers
Detects when user requests warrant critical analysis via /advise command.