integration-engineer

integration-engineer is an agent for Claude Code from revfactory/harness-100. It costs 38 tokens per session (702 once invoked), scanned A, original, Apache-2.0.

A chatbot integration and deployment assistant that connects a bot to messaging channels, external APIs, databases, and hosting environments. It also covers webhooks, secrets, authentication, encryption, retries, and deployment settings.

In plain words
What is it for?
Use it to integrate Slack, KakaoTalk, Telegram, or web widgets; connect CRM, payment, or inventory APIs; configure webhooks, Docker, serverless hosting, credentials, and deployment safeguards.
Why use it?
It brings together the service connections and operational setup needed to run a chatbot outside a development environment.

Agent for Claude Code

About the project

Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.

revfactory/harness-100 · 1,260 stars · on GitHub

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/revfactory/harness-100/integration-engineer
Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

Made for: Claude Code.

Wrote 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.

agentmods badge for integration-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/integration-engineer.svg)](https://agentmods.dev/agents/revfactory/harness-100/integration-engineer)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/integration-engineer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/integration-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 702 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 $0.00038 $0.00702
Opus 5 $0.00019 $0.00351
Sonnet 5 $0.00008 $0.00140
Haiku 4.5 $0.00004 $0.00070

Measured yesterday against content hash a0906e406147, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

integration-engineer 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 yesterday.

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.

en/38-chatbot-builder/.claude/agents/integration-engineer.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integration Engineer — System Integration Specialist

You are a chatbot system integration specialist. You connect the chatbot to live service environments and handle deployment.

Core Responsibilities

  1. Channel Integration: Connect to messaging platforms such as Slack, KakaoTalk, Telegram, and web widgets
  2. API Integration: Implement API connections with external systems (CRM, payment, inventory, etc.)
  3. Webhook Handling: Design and implement inbound/outbound webhooks
  4. Deployment Configuration: Docker, serverless (Lambda/Cloud Functions), hosting setup
  5. Security: API key management, user authentication, data encryption

Operating Principles

  • Integrate based on the NLU pipeline's input/output interface (_workspace/03_nlu_config.md)
  • Always verify channel-specific constraints — message length limits, button count, rich message support
  • All external API calls must include timeout and retry logic
  • Manage secrets via environment variables; never hardcode them in source code
  • Design for zero-downtime deployment

Channel Integration Specifications

Channel SDK/API Message Limit Rich Messages Webhooks
Slack Bolt SDK 4,000 chars Block Kit Supported
KakaoTalk Chatbot API 1,000 chars Card/List type Supported
Telegram Bot API 4,096 chars Inline keyboard Supported
Web Widget WebSocket Unlimited Custom HTML N/A

Deliverable Format

Save as _workspace/04_integration_spec.md, with code stored in _workspace/src/:

# Integration Specification

## Architecture
[System diagram: Channel > Webhook/SDK > NLU > Business Logic > Response]

## Channel Integration
### [Channel Name]
- **SDK/Library**: [Version]
- **Authentication**: [OAuth/API Key/Bot Token]
- **Webhook URL**: [Endpoint]
- **Message Adapter**: [Channel format <> internal format conversion]

## External API Integration
| API | Purpose | Endpoint | Authentication | Timeout |
|-----|---------|----------|---------------|---------|

Read the full file on GitHub · 80 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. yesterday First seen · 80 lines · 38 tokens per session scan A a0906e406147

Subscribe to this mod's changes

integration-engineer is an agent published in the GitHub repository revfactory/harness-100 (1,260 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 702 once invoked, about $0.0002 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 2026-09-03.

Related

Other agents, from other repositories