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/secondlifes/code-intel/testinggit clone --depth 1 https://github.com/SecondLifes/code-intelWhat 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 | $0.00854 | $0.00854 |
| Opus 5 | $0.00427 | $0.00427 |
| Sonnet 5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing — Rules
pytest is the only test framework. Everything below is the real,
observed discipline of this repository, verified against pytest.ini and
the actual suite — not generic advice.
The two-tier split (non-negotiable)
tests/ ← default `pytest` run — NO real external services
tests/manual/ ← needs a real GPU / Ollama / Qdrant — EXCLUDED from the default run
pytest.ini enforces this:
[pytest]
testpaths = tests
norecursedirs = tests/manual .venv .git __pycache__
- A test that needs a running Qdrant, a loaded Ollama model, or actual GPU
hardware belongs in
tests/manual/— putting it intests/breaks the default run for everyone who doesn't have that hardware up. - Conversely, a test that needs nothing external belongs in
tests/, where it actually runs. Don't park a self-contained test intests/manual/where nobody executes it. tests/manual/is run explicitly and individually when the hardware and services are available — it is never expected to pass in a bare checkout.
Naming — the name states the locked-in behavior
test_<behavior_under_test>, not test_<function_name>. The name should
say what regression it prevents:
# Good — the real convention (tests/test_chunker.py)
def test_line_shift_does_not_change_chunk_id(tmp_path):
"""KRİTİK regresyon: bir chunk'ın ÜSTÜNE satır eklemek, içeriği aynı kalan
chunk'ların ID'sini DEĞİŞTİRMEMELİ (satır no ID'ye katılmıyor olmalı)."""
# Weak — names the function, not the behavior
def test_chunk_file():
Docstrings in tests follow the codebase-wide convention: Turkish, and they state why the test exists (which bug it locks out), not what the code does.
Self-contained fixtures, no external files
Tests build their own inputs — tmp_path plus inline source snippets
defined as module-level constants in the test file itself (see
tests/test_chunker.py's OVERLOADED_CLASS). A test in tests/ must not
depend on a path outside the repo, a network call, a pre-existing Qdrant
collection, or a model download.
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 · 88 lines · 854 tokens per session scan A 213b14cfd505
testing is a cursor rule published in the GitHub repository SecondLifes/code-intel (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 854 tokens to every session, about $0.0043 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 cursor rules, from other repositories
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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.