haiflow: Skill for Claude Code

.claude/skills/haiflow-n8n/SKILL.md

haiflow-n8n is a skill for Claude Code from andersonaguiar/haiflow. It costs 185 tokens per session (9,193 once invoked), scanned C, original, MIT.

An expert guide to n8n, a visual tool for connecting services into automated workflows, and haiflow, an HTTP service for coordinating Claude Code agents. It explains workflow steps, data, triggers, errors, credentials, webhooks, and agent pipelines.

In plain words
What is it for?
Use it to design, configure, debug, and combine n8n workflows with haiflow services, webhooks, subworkflows, and multiple-agent processes.
Why use it?
It gives developers one place to understand how these two systems pass data, respond to events, and handle failures.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: 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/haiflow-n8n/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 haiflow-n8n

README.md
[![agentmods](https://agentmods.dev/badge/skills/andersonaguiar/haiflow/haiflow-n8n/github.svg)](https://agentmods.dev/skills/andersonaguiar/haiflow/haiflow-n8n)
Your own site
<a href="https://agentmods.dev/skills/andersonaguiar/haiflow/haiflow-n8n"><img src="https://agentmods.dev/badge/skills/andersonaguiar/haiflow/haiflow-n8n/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for haiflow-n8n

Your own site · 80×15
<a href="https://agentmods.dev/skills/andersonaguiar/haiflow/haiflow-n8n"><img src="https://agentmods.dev/badge/skills/andersonaguiar/haiflow/haiflow-n8n.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,193 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 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 $0.00185 $0.09193
Opus 5 $0.00093 $0.04596
Sonnet 5 $0.00037 $0.01839
Haiku 4.5 $0.00018 $0.00919

Measured 12d ago against content hash 17f674f3a738, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

haiflow-n8n scanned grade C 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 12d 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

2. **Secret file references**: `.env`, `credentials.json`, SSH keys, `.aws/credentials`, etc.

Makes network callslowCapability

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

When n8n MCP tools don't support creating workflows, use the **n8n public API (v1)** directly via curl/fetch.
.claude/skills/haiflow-n8n/SKILL.md · 1,001 lines

How it starts

The opening of the file, as written. The whole thing — 1,001 lines — stays where its author put it; the contents beside it link to each section on GitHub.

n8n + haiflow Expert

You are an expert in both n8n (workflow automation) and haiflow (Claude Code HTTP orchestrator). Use this knowledge to answer questions, design workflows, debug issues, and architect solutions that combine both systems.

Project references (read these for current implementation details):

  • README.md — haiflow setup, architecture, and examples
  • API.md — haiflow endpoint reference
  • src/index.ts — haiflow server implementation
  • examples/chained-calc/ — Chained calc n8n workflow steps and pipeline config

Part 1: n8n Deep Knowledge

Core Concepts

Workflows

  • A workflow is a DAG of nodes connected by edges that define data flow
  • Exported/imported as JSON: name, nodes[], connections{}, settings{}, pinData{}
  • Must be Active (published) to run automatically via triggers
  • Each workflow has id, name, active boolean

Data Model

All data between nodes is an array of items. Each item:

{
  "json": { "field": "value" },
  "binary": {
    "file-key": {
      "data": "base64...",
      "mimeType": "image/png",
      "fileExtension": "png",
      "fileName": "example.png"
    }
  }
}

Connections

{
  "connections": {
    "SourceNodeName": {
      "main": [[{ "node": "TargetNodeName", "type": "main", "index": 0 }]]
    }
  }
}
  • Outer array = output indices (e.g., IF has index 0 for true, index 1 for false)
  • Inner array = multiple connections from a single output (fan-out)

Execution Modes

  • $execution.mode === 'test' — Manual run from editor
  • $execution.mode === 'production' — Automatic via trigger (workflow must be Active)
  • $execution.mode === 'evaluation' — Running workflow tests

Trigger Nodes

Webhook (n8n-nodes-base.webhook)

  • Creates an HTTP endpoint that triggers workflows
  • Test URL: https://instance/webhook-test/{path} — editor development
  • Production URL: https://instance/webhook/{path} — live when Active
  • HTTP methods: GET, POST, PUT, PATCH, DELETE, HEAD
  • Path supports route params: /:variable, /path/:var1/:var2
  • Auth: None, Basic Auth, Header Auth, JWT Auth
  • Max payload: 16MB (configurable via N8N_PAYLOAD_SIZE_MAX)
  • Response modes:
    • Immediately — Returns {"status": "Workflow got started"} (fire-and-forget)
    • When Last Node Finishes — Waits for completion, returns last node output
    • Using 'Respond to Webhook' Node — Full control over response code/headers/body
    • Streaming Response — Real-time SSE for long-running ops

Read the full file on GitHub · 1,001 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. 12d ago First seen · 1,001 lines · 185 tokens per session scan C 17f674f3a738

Subscribe to this mod's changes

haiflow-n8n is a skill published in the GitHub repository andersonaguiar/haiflow (10 stars, last pushed yesterday), licensed MIT. It adds 185 tokens to every session and 9,193 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 2 findings (reaches for credential files, 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

swarm-pr-review

Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…

ZaxbyHub/opencode-swarm · 91 tokens

loop

Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…

ZaxbyHub/opencode-swarm · 72 tokens

council

Full execution protocol for MODE: COUNCIL -- General Council research, parallel member dispatch, disagreement handling, and synthesis.

ZaxbyHub/opencode-swarm · 28 tokens

deep-research

Full execution protocol for MODE: DEEPRESEARCH — orchestrator-worker deep research over external sources: decompose, iterative websearch/webfetch retrieval, parallel sme synthesis, dual-reviewer claim verification, critic challenge of high-stakes claims, and a cited report. Loaded on demand by the architect when the…

ZaxbyHub/opencode-swarm · 82 tokens

bundle-safety

Bundle transform safety — minification variant selection, consumer-constraint verification, identifier preservation, and namespace re-export coverage for build output.

ZaxbyHub/opencode-swarm · 30 tokens

safe-extraction

Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.

ZaxbyHub/opencode-swarm · 60 tokens