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 instructions/mattv8/ragtime/testinggit clone --depth 1 https://github.com/mattv8/ragtimeWhat 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 | $0.00644 | $0.00644 |
| Opus 5 | $0.00322 | $0.00322 |
| Sonnet 5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
ragtime testing.instructions.md 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Instructions
Strategy
- Use Python's stdlib
unittestframework (unittest.TestCaseandunittest.IsolatedAsyncioTestCase). - Fast and targeted execution using
pytest. - Emphasize integration tests that test the actual flow of the application. Avoid overly mocking databases or core infrastructure where possible unless absolutely necessary for external boundaries (like network calls).
Dirs & patterns
- Python tests:
tests/test_*.py - Schema reference:
prisma/schema.prisma
BASIC principles
- Readability: descriptive names; flat setup/asserts
- Autonomy: no shared state/order deps
- Speed: prefer integrated tests over heavily mocked ones. Mock only external third-party services (HTTPX) and LLM backends, but use real DB infrastructure when applicable.
- Clarity: one assertion or tight group; comment non-obvious setup
FastAPI Route Testing
- Avoid firing up a real ASGI server or using
TestClientfor every logic test unless doing an end-to-end route check. - When unit-testing internal route logic, you can build raw
starlette.requests.Requestobjects and manually call route functions with them:from starlette.requests import Request def _build_request(path: str) -> Request: return Request( { "type": "http", "method": "GET", "path": path, "headers": [(b"host", b"ragtime.dev")], "scheme": "https", } )
Boundaries and Isolation
- Patch specific external boundaries using
mock.patch.objectandSimpleNamespace(e.g. LLM calls or external APIs). - For database access, prefer using a real test database configuration over replacing Prisma
repositoryobjects with mock structures. - To test
asynciostreams and background tasks, create fake async iterators to mock FastAPI streaming responses if needed.
Patterns
import unittest
from types import SimpleNamespace
from unittest import mock
class MyFeatureTests(unittest.IsolatedAsyncioTestCase):
async def test_does_behavior(self) -> None:
fake_service = mock.AsyncMock(return_value="mock_value")
with mock.patch("ragtime.my_module.my_dependency", fake_service):
result = await do_something()
self.assertEqual(result, "mock_value")
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 · 72 lines · 644 tokens per session scan A 39ab154e7dc7
ragtime testing.instructions.md is an instructions file published in the GitHub repository mattv8/ragtime (33 stars, last pushed 5d ago), licensed MIT. It adds 644 tokens to every session, about $0.0032 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.