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 rules/johnnichev/selectools/selectools-testinggit 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 | $0.00000 | $0.00466 |
| Opus 5 | $0.00000 | $0.00233 |
| Sonnet 5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
selectools-testing 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.
What it actually says
Testing Rules
Test Organization
tests/test_<module>.py— unit tests for each source moduletests/agent/— agent core, observer, batch, regression teststests/providers/— provider-specific, model registry, streaming, format teststests/rag/— RAG pipeline, chunking, hybrid search, vector store teststests/integration/— cross-module integration teststests/tools/— tool system tests
Mock Provider Pattern
class FakeProvider:
name = "fake"
supports_streaming = True
supports_async = True
def complete(self, *, model, system_prompt, messages, tools=None, **kw):
return Message(role=Role.ASSISTANT, content="response")
Always include tools=None in signature — missing it silently hides bugs.
Recording Provider Pattern
Use to verify exact args passed to provider methods:
class RecordingProvider(FakeProvider):
def __init__(self):
self.calls = []
def complete(self, **kwargs):
self.calls.append(("complete", kwargs))
return Message(role=Role.ASSISTANT, content="ok")
Regression Tests
- Go in
tests/agent/test_regression.py - Each test class documents the specific bug it prevents
- Name pattern:
TestXxxHandlingdescribing the failure mode - Include a docstring explaining what broke and when
Assertions
- Model counts: update when adding/removing models
- Observer events: verify run_id is passed to all events
- Streaming: verify
ToolCallobjects are yielded (not strings) - Policy: verify deny actually blocks execution
- Guardrails: verify block raises, rewrite modifies content
Running Tests
pytest tests/ -x -q # All tests, stop on first failure
pytest tests/ -k "not e2e" -x -q # Skip E2E (CI mode)
pytest tests/agent/ -x -q # Just agent tests
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 · 59 lines · 0 tokens per session scan A 451cd6583b5f
selectools-testing is a cursor rule published in the GitHub repository johnnichev/selectools (11 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 466 tokens. 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 cursor rules, from other repositories
agentguard
AgentGuard local-first safety.
cursorrules
When working with AI agents in this project, use Authensor for safety.
llm-router
When the user asks about architecture, system design, project structure, or "how should I build X", ALWAYS use the planworkflow MCP tool first.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.