haiflow: Skill for Claude Code

.claude/skills/integration-builder/SKILL.md

integration-builder is a skill for Claude Code from andersonaguiar/haiflow. It costs 150 tokens per session (1,723 once invoked), scanned B, original, MIT.

A guided tool for connecting services, APIs, and other software using haiflow, a system that runs Claude Code sessions and exposes them over HTTP. It helps discover the workflow, research APIs, design the connection, and build it.

In plain words
What is it for?
Use it to plan and build n8n workflows or direct code integrations that trigger work, send prompts, queue tasks, and retrieve results from haiflow.
Why use it?
It turns a vague integration request into a defined trigger, data flow, and implementation path instead of requiring the developer to design every connection detail alone.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is andersonaguiar/haiflow's own configuration. It tells Claude Code how to work on haiflow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything haiflow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to andersonaguiar/haiflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/andersonaguiar/haiflow/main/.claude/skills/integration-builder/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/andersonaguiar/haiflow

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-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/andersonaguiar/haiflow/integration-builder.svg)](https://agentmods.dev/skills/andersonaguiar/haiflow/integration-builder)
Your own site
<a href="https://agentmods.dev/skills/andersonaguiar/haiflow/integration-builder"><img src="https://agentmods.dev/badge/skills/andersonaguiar/haiflow/integration-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,723 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00150 $0.01723
Opus 5 $0.00075 $0.00861
Sonnet 5 $0.00030 $0.00345
Haiku 4.5 $0.00015 $0.00172

Measured 8d ago against content hash 5422f32986ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

integration-builder scanned grade B with 2 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 8d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST localhost:3333/session/start -d '{"cwd":"/path/to/project"}'

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST localhost:3333/session/start -d '{"cwd":"/path/to/project"}'
.claude/skills/integration-builder/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integration Builder

Build integrations between services using haiflow as the AI orchestration layer. Haiflow wraps Claude Code in tmux sessions and exposes a REST API — integrations trigger prompts, queue work, and poll for responses over HTTP.

Project references (read these for API details, don't duplicate):

  • README.md — Full API docs, setup, and architecture
  • src/index.ts — Endpoint implementations and types
  • examples/chained-calc/ — Chained calc workflow example

Workflow

  1. Discover — What services to connect, what triggers the flow, what data moves
  2. Research — Look up API/library capabilities via context7
  3. Propose — Recommend n8n or raw integration path, present the plan
  4. Build — Create the workflow or code
  5. Deploy — Activate in n8n or hand off runnable code

Phase 1: Discover

Ask concise questions (max 3 per message) to understand:

  • Source system(s) — Where does data/event originate?
  • Destination system(s) — Where should data/action land?
  • Trigger — Webhook, schedule, manual, or polling?
  • Data flow — What moves between systems? Transforms needed?
  • Path preference — n8n workflow or raw code?

n8n vs raw code decision:

Factor n8n Raw code
User has n8n instance or n8n MCP available Prefer -
Visual workflow management needed Prefer -
Many conditional branches Prefer -
High-performance / low-latency - Prefer
Deep custom logic / complex transforms - Prefer
User explicitly prefers code - Prefer

Default to n8n if user mentions it or mcp__n8n-mcp__* tools are available.


Phase 2: Research

Use context7 MCP to research each service/library involved:

  1. mcp__context7__resolve-library-id — Resolve each service/library name
  2. mcp__context7__query-docs — Query for:
    • Authentication methods
    • Available endpoints / webhook events
    • Rate limits or quirks
    • SDK availability

Read the full file on GitHub · 195 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. 8d ago First seen · 195 lines · 150 tokens per session scan B 5422f32986ff

Subscribe to this mod's changes

integration-builder is a skill published in the GitHub repository andersonaguiar/haiflow (10 stars, last pushed today), licensed MIT. It adds 150 tokens to every session and 1,723 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). 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

flowise-builder

Use when flowise visual LLM workflow builder — drag-drop chatflows, API endpoints, document loaders, tools. Use when working with flowise builder.

oyi77/1ai-skills · 35 tokens

n8n-workflows

Use when n8n workflow automation — nodes, triggers, expressions, credentials, webhooks, error handling. Use when working with n8n workflows.

oyi77/1ai-skills · 37 tokens

pipedream-workflows

Use when pipedream serverless workflows — triggers, code steps, pre-built actions, data stores, HTTP. Use when working with pipedream workflows.

oyi77/1ai-skills · 38 tokens

postbridge-social-manager

Use when multi-platform social media posting, scheduling, analytics, and media management via PostBridge API for TikTok, Instagram, X, LinkedIn, and Facebook. Use when working with postbridge social manager.

oyi77/1ai-skills · 47 tokens

telegram-userbot

Use when full MTProto control of Telegram account via Telethon. DM, Voice Note, Call, Video Call, Group/Channel management, member scraping, bot cloning, outreach automation, broadcast, CRM tracking, content reposting, scheduled messaging, webhook triggers. Use for all Telegram automation as a real user (not bot API).

oyi77/1ai-skills · 70 tokens

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

hackermanishackerman/claude-skills-vault · 61 tokens