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.
git clone --depth 1 https://github.com/airweave-ai/airweaveWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/airweave-ai/airweave/monke-testing-guide)<a href="https://agentmods.dev/rules/airweave-ai/airweave/monke-testing-guide"><img src="https://agentmods.dev/badge/rules/airweave-ai/airweave/monke-testing-guide/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/airweave-ai/airweave/monke-testing-guide"><img src="https://agentmods.dev/badge/rules/airweave-ai/airweave/monke-testing-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.07424 | $0.07424 |
| Opus 5.5 | $0.02970 | $0.02970 |
| Sonnet 5.5 | $0.01485 | $0.01485 |
| Haiku 4.5 | $0.00742 | $0.00742 |
Grade A, and why
monke-testing-guide 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 1mo 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 — 1,121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building Monke Tests for Source Connectors
Overview
Monke is Airweave's end-to-end testing framework for source connectors. It creates real test data in external systems, triggers syncs, and verifies data appears correctly in the search index.
This guide shows you how to build comprehensive tests that verify every entity type your connector supports.
Why Test Every Entity Type?
Important: Your Monke tests should create and verify all entity types defined in your source connector.
Many connector tests only verify top-level entities (e.g., tasks) but ignore nested entities (e.g., comments, files).
Impact:
- Comments might not sync properly → Silent failures in production
- File attachments might not be indexed → Missing searchable content
- Entity relationships might be broken → Poor search results
- Users can't search the full breadth of data they expect
Solution: Create test entities for every entity type your connector syncs, and verify each one appears in Qdrant.
Before Writing Monke Tests:
- Open your source file:
backend/airweave/platform/sources/{short_name}.py - List all entity types yielded in
generate_entities():- Example: WorkspaceEntity, ProjectEntity, TaskEntity, CommentEntity, FileEntity
- Your Monke tests should create at least one instance of each type
- Verify each instance appears in Qdrant after sync
Validation:
- Count entity classes in
entities/{short_name}.py - Count entity types created in
bongos/{short_name}.py::create_entities() - These counts should match (excluding parent/workspace entities that don't get stored)
Core Components
Every Monke test requires four components:
- Bongo implementation (
monke/bongos/{short_name}.py) - Generation schemas (
monke/generation/schemas/{short_name}.py) - Generation adapter (
monke/generation/{short_name}.py) - Test configuration (
monke/configs/{short_name}.yaml)
Part 1: Bongo Implementation
The Bongo is a class that creates, updates, and deletes test data via the external API.
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.
- 1mo ago First seen · 1,121 lines · 7,424 tokens per session scan A c53a9590b09c
monke-testing-guide is a cursor rule published in the GitHub repository airweave-ai/airweave (6,558 stars, last pushed 4mo ago), licensed MIT. It adds 7,424 tokens to every session, about $0.0297 per session on Opus 5.5. 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 cursor rules, from other repositories
running-frontend-tests
How to run frontend component tests.
ui-verification
UI layout checks before claiming work is done.
turn-admission
Immediate turn admission and autonomous retry semantics.
frontend-tests
Frontend Tests.
playwright-e2e-testing
You are an expert QA engineer with deep knowledge of Playwright and TypeScript, tasked with creating end-to-end UI tests for web applications.
playwright-api-testing
You are an expert QA engineer with deep knowledge of Playwright and TypeScript, tasked with creating API tests for web applications.