integrations

A practical guide to connecting ERP and AI applications with outside systems such as banks, CRMs, HR tools, shops, and tax services. ERP means software that manages core business operations and records.

In plain words
What is it for?
Use it to design APIs, scheduled or real-time data syncs, event-driven workflows, middleware, financial data transfers, and integrations for smaller organisations.
Why use it?
It helps plan how data moves between systems without unnecessary complexity or heavy controls. It addresses synchronisation, triggered actions, replacements of old systems, and partner access.

Skill for Claude CodeCodex

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 skills/erphq/skills/integrations
Any agent
npx skills add erphq/skills --skill integrations
Clone the repo
git clone --depth 1 https://github.com/erphq/skills

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,233 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00043 $0.08233
Opus 5 $0.00022 $0.04117
Sonnet 5 $0.00009 $0.01647
Haiku 4.5 $0.00004 $0.00823

Measured 2d ago against content hash 8fae6832d9b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

integrations scanned grade C with 1 finding 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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

- **No Error Visibility**: Integration failures silently logged to a file nobody reads. Use dashboards, alerts, and DLQ monitoring.
departments/information-technology/01-org-under-100/integrations/SKILL.md · 468 lines

How it starts

The opening of the file, as written. The whole thing — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrations

Size-Tier Scope

This variant scales the operating pattern for organizations under 100 people. Keep the controls lightweight, favor owner-led approvals, and introduce automation only where it removes recurring manual work without adding governance overhead.

Purpose

No enterprise system operates in isolation. An ERP connects to banks for payments, to CRMs for customer data, to HR platforms for employee records, to e-commerce systems for orders, to tax authorities for compliance, and to dozens of other internal and external systems.

Integration is the connective tissue of the enterprise technology landscape. Builders need this skill when:

  • Two systems need to share data in real time or on a schedule
  • A business event in one system must trigger an action in another
  • Master data (customers, products, employees) must stay synchronized across platforms
  • Financial transactions need to flow between ERP and banking systems
  • The organization is replacing a legacy system and must maintain continuity during transition
  • External partners (suppliers, logistics providers) need programmatic access to your data

Bad integrations are the number-one cause of enterprise system failures. Data gets lost, duplicated, corrupted, or delivered late. This skill covers how to avoid those outcomes.

Key Concepts

Integration Patterns

Pattern How It Works When to Use Drawbacks
Point-to-Point System A calls System B directly via API. Two systems, simple data exchange, low volume. Does not scale. N systems create N*(N-1)/2 connections.
Hub-and-Spoke A central integration hub (middleware) connects all systems. Each system connects only to the hub. 3+ systems need to exchange data. Central governance required. Hub is a single point of failure. Requires middleware platform.
Event-Driven Systems publish events to a message broker (Kafka, RabbitMQ, EventBridge). Other systems subscribe. Real-time, loosely coupled, high throughput. Multiple consumers for same event. Eventual consistency. Harder to debug. Requires event schema governance.
API Gateway A gateway sits in front of your APIs, handling authentication, rate limiting, routing, and versioning. Exposing APIs to external partners. Multi-tenant API access. Adds latency. Requires gateway management.
File-Based (Batch) Systems exchange flat files (CSV, XML, EDI) via SFTP, S3, or shared storage. Legacy systems, high-volume batch processing, EDI with trading partners. No real-time capability. Error handling is manual. File format is fragile.

Read the full file on GitHub · 468 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 · 468 lines · 43 tokens per session scan C 8fae6832d9b0

Subscribe to this mod's changes

integrations is a skill published in the GitHub repository erphq/skills (2 stars, last pushed 13d ago), licensed MIT. It adds 43 tokens to every session and 8,233 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

golden-rss

Use when testing the rss golden build.

yusufkaraaslan/Skill_Seekers · 12 tokens

golden-chat-single

Use when testing the goldenchatsingle golden build.

yusufkaraaslan/Skill_Seekers · 14 tokens

decided-import

Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…

asdecided/core · 98 tokens

plan-a-feature-to-confluence

Builds a feature specification from scratch with plan-a-feature and publishes it to a user-specified Confluence location, posting the spec as a parent page and each companion artifact (decision log, team findings, technical notes) as a child page beneath it. Use when the user wants a new feature planned, designed…

testdouble/han · 154 tokens

keep-the-why

Preserves or recovers the reasoning behind a codebase - architectural decisions, rejected alternatives, workarounds, incident learnings, operational constraints, and historical context the code itself cannot explain. Use when implementing or reviewing a non-trivial change involving a design decision, workaround…

oliver-zehentleitner/keep-the-why · 163 tokens

architectural-decisions

Use when encountering questions about WHY code is built a certain way, when about to make architectural changes (new patterns, restructuring, choosing between approaches), or when the user asks about design rationale in a Repowise-indexed codebase (.repowise/ directory exists). Also activates when commit messages or…

repowise-dev/repowise · 87 tokens