connector-behavior

An agent-behaviour guide for building or changing integrations with external services, marketplaces, webhooks, and data synchronization systems.

In plain words
What is it for?
Use it when connecting APIs or synchronizing products, stock, orders, prices, invoices, or customers, including scheduled jobs and webhooks.
Why use it?
It helps prevent unreliable integrations by requiring clear data ownership, error handling, retries, logging, and repeat-safe operations.

Agent

Install

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.

agentmods
npx agentmods add agents/codeforusers/odoo-dev-superskill/connector-behavior
Clone the repo
git clone --depth 1 https://github.com/CodeForUsers/odoo-dev-superskill
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00404
Opus 5 $0.00000 $0.00202
Sonnet 5 $0.00000 $0.00081
Haiku 4.5 $0.00000 $0.00040

Measured 2d ago against content hash 8b88a38a779f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

connector-behavior 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.

references/agents/connector-behavior.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Connector Behavior

Purpose

Define how the agent should behave when implementing or modifying integrations with external APIs, marketplaces, webhooks, import/export pipelines, and synchronization logic.

When to activate

  • The task involves external APIs.
  • The task mentions marketplaces, e-commerce, logistics, payments, or webhooks.
  • The module synchronizes products, stock, orders, prices, invoices, or customers.
  • The task includes scheduled jobs, retries, queueing, or idempotency concerns.

Pre-checks

  • Identify integration direction: import, export, bidirectional sync, webhook.
  • Identify external system constraints: rate limits, auth, payload formats, retries.
  • Identify Odoo model boundaries and ownership of truth.
  • Check whether the connector should extend an existing backend architecture.
  • Inspect whether logs, mapping tables, and sync state need dedicated models.

Workflow

  1. Model the integration flow clearly before coding.
  2. Separate transport layer, mapping logic, and business logic.
  3. Define idempotent operations where possible.
  4. Add structured logging and error handling.
  5. Treat retries and transient failures explicitly.
  6. Avoid coupling external payload formats directly to business models.
  7. Use queues/cron patterns when synchronization volume requires it.
  8. Plan tests for payload mapping and critical flows.

Rules

  • Integration logic must be traceable and debuggable.
  • Mapping should be explicit, not implicit.
  • Idempotency matters for imports, exports, and webhooks.
  • External failures must not corrupt internal state.
  • Connector code should remain modular and extensible.

Avoid

  • Mixing API calls directly inside business methods with no abstraction.
  • Silent failures and swallowed exceptions.
  • Tight coupling between raw external payloads and core models.
  • No logging on sync jobs.
  • Assuming remote systems are always consistent or available.
  • references/security.md
  • references/sql-performance.md
  • references/testing.md
  • references/maturity-levels.md

Read the full file on GitHub · 48 lines

Changes

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.

  1. 2d ago First seen · 48 lines · 0 tokens per session scan A 8b88a38a779f

Subscribe to this mod's changes

connector-behavior is an agent published in the GitHub repository CodeForUsers/odoo-dev-superskill (12 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 404 tokens. 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.