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/johnnichev/selectools/testnpx skills add johnnichev/selectools --skill testgit clone --depth 1 https://github.com/johnnichev/selectoolsWhat 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 | $0.00016 | $0.01290 |
| Opus 5 | $0.00008 | $0.00645 |
| Sonnet 5 | $0.00003 | $0.00258 |
| Haiku 4.5 | $0.00002 | $0.00129 |
Grade A, and why
test 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Writing
Write tests for: $ARGUMENTS
Live Project State
- Current tests: !
pytest tests/ --collect-only -q 2>/dev/null | tail -1
Test Organization
tests/
conftest.py # SharedFakeProvider, fixtures, helpers
test_<module>.py # Unit tests per source module
agent/ # Agent core, observer, batch, regression
test_regression.py # ALL regression tests go here
providers/ # Provider-specific tests
rag/ # RAG pipeline, chunking, stores
integration/ # Cross-module integration tests
tools/ # Tool system tests
SharedFakeProvider (from conftest.py)
Use the fake_provider fixture — it returns a factory. Responses can be:
str— auto-wrapped asMessage(role=ASSISTANT, content=...)Message— used as-is (for tool_calls, etc.)(Message, UsageStats)tuple — controls token/cost tracking
def test_example(self, fake_provider):
# Simple text response
provider = fake_provider(responses=["Hello"])
# Tool call response
provider = fake_provider(responses=[
Message(role=Role.ASSISTANT, content="", tool_calls=[
ToolCall(tool_name="search", parameters={"q": "test"})
]),
"Final answer",
])
# Response with specific usage stats (for budget/cost tests)
provider = fake_provider(responses=[
(Message(role=Role.ASSISTANT, content="answer"),
UsageStats(prompt_tokens=100, completion_tokens=50,
total_tokens=150, cost_usd=0.01,
model="test", provider="test")),
])
Important: Agent requires at least one tool. Use a dummy:
_DUMMY = Tool(name="noop", description="noop", parameters=[], function=lambda: "ok")
Recording Provider Pattern
Use to verify exact args passed to provider methods:
class RecordingProvider:
name = "recording"
supports_streaming = False
supports_async = False
def __init__(self):
self.last_messages = []
self.last_system_prompt = ""
self.last_tools = None
def complete(self, *, model, system_prompt, messages, tools=None, **kw):
self.last_messages = list(messages)
self.last_system_prompt = system_prompt
self.last_tools = tools
return Message(role=Role.ASSISTANT, content="ok"), UsageStats(
prompt_tokens=10, completion_tokens=5, total_tokens=15,
cost_usd=0.0001, model=model, provider="recording",
)
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 · 171 lines · 16 tokens per session scan A b42f380b2f32
test is a skill published in the GitHub repository johnnichev/selectools (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,290 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 skills, from other repositories
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
Content Safety & Filtering
Topic-based content filtering to block harmful or unauthorized content in agent output.
guardrails-docs-access
Access and read guardrails skill documentation, configuration examples, and usage guides at runtime.
Output Security & Secret Scanning
Prevent sensitive data (secrets, credentials, PII) from leaking in agent output.
Policy Configuration Hierarchy
How guardrail policies cascade from organization through team to project level.
Sandbox Isolation
Run untrusted or risky commands in Docker-based sandbox with resource limits and network isolation.