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/connector-development-end-to-end)<a href="https://agentmods.dev/rules/airweave-ai/airweave/connector-development-end-to-end"><img src="https://agentmods.dev/badge/rules/airweave-ai/airweave/connector-development-end-to-end/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/connector-development-end-to-end"><img src="https://agentmods.dev/badge/rules/airweave-ai/airweave/connector-development-end-to-end.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 | $0.06392 | $0.06392 |
| Opus 5 | $0.03196 | $0.03196 |
| Sonnet 5 | $0.01278 | $0.01278 |
| Haiku 4.5 | $0.00639 | $0.00639 |
Grade A, and why
connector-development-end-to-end 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 11d 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 — 856 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building and Testing a Source Connector: End-to-End Guide
Overview
This is the master guide for building a complete, production-ready source connector for Airweave. It combines source implementation with comprehensive E2E testing using the Monke framework.
Use this guide with your AI coding assistant to build connectors systematically.
Prerequisites
Note: The human has already completed these setup steps:
- ✅ OAuth credentials configured in
backend/airweave/platform/auth/yaml/dev.integrations.yaml - ✅ Monke authentication configured in
monke/configs/{short_name}.yaml(Composio or direct) - ✅ API documentation loaded into context
Your task is to write the code. The human will handle testing and running commands.
Important Guidelines
These are the most common mistakes when building connectors:
1. Make Entities Information-Rich (Embeddable Fields)
Rule: Mark ~70% of entity fields as embeddable=True
Why: Without embeddable=True, fields are only keyword-searchable, not semantically searchable. Users won't be able to find relevant data.
What to mark embeddable:
- ✅ All text content (descriptions, notes, comments, body)
- ✅ All names and titles
- ✅ All people (assignees, authors, owners, members)
- ✅ All status/metadata (status, priority, tags, labels)
- ✅ All timestamps (created_at, modified_at, due_dates)
What NOT to mark embeddable:
- ❌ Internal IDs (entity_id, external_id, database IDs)
- ❌ Binary metadata (sizes, checksums, mime_types)
Bad Example:
# Avoid: Sparse entity - users can't search by anything except name
class TaskEntity(ChunkEntity):
name: str = AirweaveField(..., embeddable=True)
description: str = Field(...) # Should be embeddable
assignee: Dict = Field(...) # Should be embeddable
Good Example:
# Better: Information-rich - users can search everything
class TaskEntity(ChunkEntity):
name: str = AirweaveField(..., embeddable=True)
description: str = AirweaveField(..., embeddable=True)
assignee: Dict = AirweaveField(..., embeddable=True)
status: str = AirweaveField(..., embeddable=True)
external_id: str = Field(...) # ID correctly not embeddable
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.
- 11d ago First seen · 856 lines · 6,392 tokens per session scan A 947b0bd3460e
connector-development-end-to-end is a cursor rule published in the GitHub repository airweave-ai/airweave (6,564 stars, last pushed 3mo ago), licensed MIT. It adds 6,392 tokens to every session, about $0.0320 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 cursor rules, from other repositories
manual-review.backend
A set of rules for verifying backend-only changes and changes that use different verification channels. It separates evidence the agent can collect from checks that require a person, a production authorization, or a business decision.
ui-verification
UI layout checks before claiming work is done.
api-validation-workflow
Integrates API validation tools (OpenAPI spec retrieval and HTTP request testing) into the development workflow, enabling autonomous testing and validation of features. This rule defines when and how to use API validation tools for continuous validation, debugging, and quality assurance throughout the development…
issues-tests
Backend test conventions — QuarkusTest, REST Assured, Given, ArchUnit.
routers_tests
Since this is a FastAPI web application, test logic for API endpoints often involves checking status codes. Remember, when making a request to an API endpoint, you should specify the followredirects parameter. With followredirects=False, the response code will often be 303; otherwise it will be the response code of…
playwright-api-testing-cursorrules-prompt-file
Cursor rules for Playwright development with API testing.