Agent skill

Hex Reference Architecture

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Implement Hex reference architecture with best-practice project layout.

MITAuto-check passedDevOps & Cloud

Install Hex Reference Architecture

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill hex-reference-architecture -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace hex-reference-architecture --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/hex-reference-architecture .claude/skills/hex-reference-architecture && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hex-reference-architecture
GitHub stars
2.8k
Token cost
~1k tokens
SKILL.md length
244 words
Files
1
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Implement Hex reference architecture with best-practice project layout.

  • Works in 5 steps: Map every trigger-to-project edge with… → Start with a sandbox project and fail… → Make asynchronous execution idempotent… → …
  • Designing new Hex integrations
  • SKILL.md covers Architecture, Project Structure, Integration Patterns and Overview, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Hex Reference Architecture is an agent skill from jeremylongshore/tons-of-skills-marketplace. Implement Hex reference architecture with best-practice project layout. Use when designing new Hex integrations, reviewing project structure, or establishing architecture standards for Hex applications. Trigger with phrases like "hex architecture", "hex best practices", "hex project structure", "how to organize hex", "hex layout".

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Designed for Claude Code

It sits in DevOps & Cloud. It works with Apache Airflow. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Designing new Hex integrations
  • Reviewing project structure
  • Establishing architecture standards for Hex applications
  • With phrases like hex architecture

Example prompts

  • “hex architecture”
  • “hex best practices”
  • “hex project structure”
  • “/hex-reference-architecture”

Requirements

  • Compatibility (from SKILL.md): Designed for Claude Code
  • Pre-approved tools (allowed-tools): Read, Grep

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Map every trigger-to-project edge with owner, data class, allowed parameters, authorization scope, retry behavior, observability, and…
  2. Start with a sandbox project and fail closed on unknown project, parameter schema, destination, or response shape.
  3. Make asynchronous execution idempotent and bounded; quarantine uncertainty rather than resubmitting or exporting output for debugging.
  4. Canary one project with aggregate signals before promotion and retain the prior revision.
  5. Re-evaluate controls whenever credentials, project ownership, schedules, or parameters change.

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • learn.hex.tech
    • github.com
    • hex.tech

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Designed for Claude Code

    From compatibility in the SKILL.md frontmatter.

Context cost

Hex Reference Architecture loads about 1k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 244 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~90
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 244 words, ~1,004 tokens.

Download SKILL.mdSave it as .claude/skills/hex-reference-architecture/SKILL.md (or your agent's skills folder).
name
hex-reference-architecture
description
Implement Hex reference architecture with best-practice project layout. Use when designing new Hex integrations, reviewing project structure, or establishing architecture standards for Hex applications. Trigger with phrases like "hex architecture", "hex best practices", "hex project structure", "how to organize hex", "hex layout".
allowed-tools
Read, Grep
compatibility
Designed for Claude Code
version
1.6.0
license
MIT
author
Jeremy Longshore <jeremy@intentsolutions.io>
tags
saas, hex, data, analytics

Hex Reference Architecture

Architecture

┌────────────────────────────────────────┐
│          Orchestration Layer            │
│  (Airflow, Dagster, GitHub Actions,    │
│   Cron, Custom API)                    │
├────────────────────────────────────────┤
│           Hex API Client               │
│  (Run, Poll, Cancel, List)             │
├────────────────────────────────────────┤
│            Hex Platform                │
│  ┌──────────┐  ┌───────────────────┐  │
│  │ Projects  │  │ Data Connections  │  │
│  │ (SQL,     │  │ (Snowflake,      │  │
│  │  Python,  │  │  BigQuery,       │  │
│  │  R)       │  │  Postgres, etc.) │  │
│  └──────────┘  └───────────────────┘  │
└────────────────────────────────────────┘

Project Structure

hex-orchestrator/
├── src/hex/
│   ├── client.ts         # API client
│   ├── orchestrator.ts   # Pipeline runner
│   ├── scheduler.ts      # Cron-based triggers
│   └── types.ts          # TypeScript interfaces
├── src/notify/
│   └── slack.ts          # Completion notifications
├── tests/
├── config/
│   └── pipelines.json    # Pipeline definitions
└── .env.example

Integration Patterns

PatternWhenTool
CI-triggered refreshOn deployGitHub Actions
Scheduled pipelineDaily/weekly reportsCron, Airflow
On-demand runUser-triggered analysisAPI endpoint
Orchestrated pipelineMulti-step ETLAirflow, Dagster

Overview

This architecture separates project triggers, parameter validation, scoped execution, bounded orchestration, aggregate observability, and cancellation/rollback. Workspace data remains inside approved project boundaries and never becomes architectural telemetry.

Prerequisites

  • A project/data owner for each source, environment allowlist, secret manager, and owner for every execution edge.
  • Separate sandbox/staging/production configuration plus rollback for project, schedule, queue, and client controls.

Instructions

  1. Map every trigger-to-project edge with owner, data class, allowed parameters, authorization scope, retry behavior, observability, and rollback.
  2. Start with a sandbox project and fail closed on unknown project, parameter schema, destination, or response shape.
  3. Make asynchronous execution idempotent and bounded; quarantine uncertainty rather than resubmitting or exporting output for debugging.
  4. Canary one project with aggregate signals before promotion and retain the prior revision.
  5. Re-evaluate controls whenever credentials, project ownership, schedules, or parameters change.

Output

Produce an architecture record with owners, opaque project IDs, policy revisions, idempotency/retry behavior, observability, test evidence, and rollback revision. Exclude SQL, output, credentials, and identities.

Error Handling

Stop on unknown scope/destination, failed redaction, non-idempotent retry, or authorization drift. Quarantine the event and restore the prior controlled path instead of adding a broad fallback.

Examples

source=scheduled-sandbox; project=proj-sandbox-12; params=r4; trigger=approved; probe=pass; rollback=arch-r17 is a reviewable architecture receipt.

Resources

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/.curated/hex-reference-architecture of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287

Compare with similar skills

Hex Reference Architecture next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hex Reference Architecture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hex Reference Architecture this skilljeremylongshore/tons-of-skills-marketplace2.8k—~1kAutomated safety check: PassMIT
Verify CI Impactgodatadriven/whirl205—~1.3kAutomated safety check: PassApache-2.0
ML Pipeline Workflowwshobson/agents40k12 repos~1.8kAutomated safety check: PassMIT
ML Pipeline ExpertJeffallan/claude-skills12k—~1.9kAutomated safety check: PassMIT
ML Pipeline Automationsecondsky/claude-skills227—~3.2kAutomated safety check: PassMIT
Paidf Orchestration SetupNVIDIA/skills3.6k—~3.8kAutomated safety check: WarnApache-2.0

Similar skills

  • Verify CI Impact

    godatadriven/whirl

    Before committing, work out which Whirl examples need a CI run to verify changes still work, then run them after confirming with the user.

    205 GitHub stars~1.3k tokensUpdated 9 days ago
    DevOps & CloudAuto-check passed
  • ML Pipeline Workflow

    wshobson/agents

    Guides an agent through designing an MLOps pipeline that covers data preparation, training, validation and deployment, with DAG orchestration and reference guides.

    40k GitHub starsUsed in 12 repos~1.8k tokens
    DevOps & CloudAuto-check passed
  • ML Pipeline Expert

    Jeffallan/claude-skills

    Designs ML pipeline infrastructure: experiment tracking with MLflow or Weights & Biases, Kubeflow and Airflow orchestration, Feast feature stores and model validation gates.

    12k GitHub stars~1.9k tokensUpdated 7 days ago
    DevOps & CloudAuto-check passed
  • ML Pipeline Automation

    secondsky/claude-skills

    Automate ML workflows with Airflow, Kubeflow, MLflow. An agent skill from secondsky/claude-skills.

    227 GitHub stars~3.2k tokensUpdated 13 days ago
    DevOps & CloudAuto-check passed
  • Official

    Audit, prepare, and deploy PAIDF Orchestration on a Kubernetes GPU cluster - single-GPU H100/L40S hosts, managed Kubernetes, kubeadm, and similar.

    3.6k GitHub stars~3.8k tokensUpdated yesterday
    DevOps & CloudAuto-check: warnings
  • Helm Chart

    astronomer/astronomer

    A skill your agent uses for Helm chart work - creating charts, modifying existing charts, values design, testing.

    491 GitHub stars~6.5k tokensUpdated 2 days ago
    DevOps & CloudAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo
  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes
  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed
  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Works with

Questions about Hex Reference Architecture

What does Hex Reference Architecture do?

Implement Hex reference architecture with best-practice project layout. Hex Reference Architecture is an agent skill from jeremylongshore/tons-of-skills-marketplace. Implement Hex reference architecture with best-practice project layout.

When should I use Hex Reference Architecture?

Hex Reference Architecture fits situations like: designing new Hex integrations; reviewing project structure; establishing architecture standards for Hex applications; with phrases like hex architecture.

How do I install Hex Reference Architecture in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill hex-reference-architecture -a claude-code`. Or copy the skill folder (skills/.curated/hex-reference-architecture in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/hex-reference-architecture in your project. Claude Code loads it when a task matches its description.

How do I install Hex Reference Architecture in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill hex-reference-architecture -a codex`. Or copy the skill folder (skills/.curated/hex-reference-architecture in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/hex-reference-architecture in your project. Codex loads it when a task matches its description.

Can I use Hex Reference Architecture in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill hex-reference-architecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hex-reference-architecture, .gemini/skills/hex-reference-architecture, .github/skills/hex-reference-architecture and .opencode/skills/hex-reference-architecture in your project.

What does Hex Reference Architecture need to run?

SKILL.md names no scripts, command-line tools or credentials: Hex Reference Architecture is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep. Compatibility (from SKILL.md): Designed for Claude Code.

Does Hex Reference Architecture access the network?

SKILL.md names 3 domains. As links in the text: learn.hex.tech, github.com and hex.tech. This is read from the text; nothing was executed.

Is Hex Reference Architecture safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hex Reference Architecture use?

Hex Reference Architecture is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hex Reference Architecture use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hex Reference Architecture?

Skills that share tags, products or a category with Hex Reference Architecture: Verify CI Impact (godatadriven/whirl, 205 stars), ML Pipeline Workflow (wshobson/agents, 40k stars), ML Pipeline Expert (Jeffallan/claude-skills, 12k stars) and ML Pipeline Automation (secondsky/claude-skills, 227 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hex Reference Architecture?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.