---
title: "Documenting what you build"
summary: "A checklist for agent templates, MCP client configs, recipes and scripts, and what we check before a seal."
updated: "2026-09-30"
status: stable
origin: official
url: "https://swooshconnect.com/docs/contributing/"
---

# Documenting what you build

A checklist for agent templates, MCP client configs, recipes and scripts, and what we check before a seal.

## For AI agents

- MUST ship a README with a For AI agents block for every add-on. DO write each line as DO, MUST, PREFER or NEVER.
- MUST reach platforms only through https://swooshrank.com/api/v1 or https://swooshrank.com/api/mcp. NEVER call a platform or a phone provider directly.
- MUST list every env var the add-on reads, and NEVER read or log any secret that is not listed.
- MUST pin a version and state an OSI-approved licence. A seal covers exactly one version.
- NEVER weaken a voice or consent rule. Reach platforms only through SwooshConnect's API; send any other data only to the customer's own runtime and the AI provider whose key the customer supplies, and list every destination in the README.
- To submit, send the repository link, exact version and licence by email to support@swooshrank.com.

## Why document

People and AI agents pick an add-on from its README. A missing or vague README is the most common reason an add-on cannot be sealed. Write for both readers: a developer who will run it, and an agent that will decide whether it is safe to.

## Agent template

- A manifest with id, name, tier, schedule, secrets (name, label, options where fixed) and the modules it needs.
- A README with a For AI agents block: the schedule, which modules and tools it calls, and what it must never do.
- The tables it creates, with each column named, and which ones a user may edit.
- The schedule as a cron line, and what happens when a run fails.
- Safety notes: which rules are enforced by SwooshConnect and cannot be changed from the code.
- A pinned version, and the same version in the manifest and the README.

## MCP client config, recipe or script

- What it calls: list every tool or route, by name.
- Platforms only through SwooshConnect's API: https://swooshrank.com/api/v1 or https://swooshrank.com/api/mcp. Any other data goes only to the customer's own runtime and the AI provider whose key the customer supplies, and the README lists every destination.
- Env vars: name, what it is for, and where the user gets it. Never ask for a secret that is not needed.
- An OSI-approved licence, stated in the README and in a LICENSE file.
- A For AI agents block with the same DO, MUST, PREFER and NEVER lines as our own pages.

## For the seal: what we check

- Every criterion on the [Community add-ons](https://swooshconnect.com/docs/community/) page, against the exact version you submit.
- That the code reaches platforms only through our API, sends other data only to the customer's own runtime and their AI provider, and keeps every voice and consent rule.
- That the env vars in the README match the code, and no other secret is read.
- That the README tells an AI agent what it must and must never do.
- That the version is pinned and the licence is OSI-approved.

> **Note:** A seal covers one version. When you release a new one, submit it again; until then it shows as Community.