Boundaries logo

Boundaries

Community
oliver-kriska
boundaries

Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.

Overview

Publisheroliver-kriska
Repositoryclaude-elixir-phoenix
Skill nameboundaries
Stars
555
Forks
40
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by oliver-kriska on GitHub. Read the source before you install it.

Installation

Install the Boundaries AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix.git /tmp/claude-elixir-phoenix
mkdir -p .claude/skills
cp -r /tmp/claude-elixir-phoenix/plugins/elixir-phoenix/skills/boundaries .claude/skills/boundaries
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Boundaries in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Boundaries on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Boundaries is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Phoenix Context Boundary Validation

Analyze module dependencies to ensure clean context separation and proper architectural boundaries.

Usage

/phx:boundaries              # Check for violations
/phx:boundaries --assess     # Score context health (0-100)
/phx:boundaries --fix        # Suggest fixes for violations

--assess Mode: Context Health Score

Evaluate overall boundary health with a quantified score.

Metrics Calculated

MetricHealthy RangeRed FlagWeight
Modules per context3-15>20 or <220%
Public API surface5-30 funcs>40 funcs15%
Fan-out (contexts called)1-4>620%
Fan-in (called by contexts)1-6>1015%
Circular dependencies0>015%
Boundary violations0>015%

Commands for Assessment

Use Glob to count .ex files per context directory under lib/my_app/*/. Use Grep to count public function definitions per context file under lib/my_app/*.ex. Run mix xref graph --format stats for dependency analysis. Run mix xref graph --format cycles --label compile for compile-time circular dependencies.

Output Format

markdown
## Context Health Assessment

### Overall Score: 82/100 (Good)

| Context | Modules | API | Fan-Out | Fan-In | Score |
|---------|---------|-----|---------|--------|-------|
| Accounts | 5 | 12 | 2 | 4 | 95 |
| Orders | 18 | 45 | 8 | 3 | 62 |
| Shared | 2 | 8 | 0 | 12 | 78 |

### Issues Found

1. **Orders** - Too large (18 modules, 45 funcs)
   - Consider: Extract Fulfillment, Invoicing sub-contexts

2. **Orders** - High fan-out (8 contexts)
   - Consider: Review if all dependencies necessary

### Recommendations

- Split Orders into Orders + Fulfillment
- Review Accounts ← Billing dependency

Iron Laws - Never Violate These

  1. Controllers call only contexts - No direct Repo access from web layer
  2. Schemas are pure data - No side effects, no Repo calls in schema modules
  3. Contexts own their schemas - Don't import schemas from other contexts
  4. Explicit dependencies only - Cross-context calls must be intentional
  5. DO NOT refactor context boundaries without running mix xref first — Refactoring without dependency data creates new violations; always map the dependency graph before moving modules

Dependency Rules

LayerCan CallCannot Call
ControllersContexts, Plug, ConnRepo, Schemas directly
LiveViewsContexts, Components, PubSubRepo, Schemas directly
ContextsOwn schemas, Repo, other contextsWeb layer modules
SchemasEcto types, validationsContexts, Repo

Analysis Commands

Check Compile Dependencies

Run mix xref graph --label compile-connected.

Find What Depends on a Context

Run mix xref graph --sink MyApp.Accounts --label compile.

Find What a Module Calls

Run mix xref callers MyApp.Accounts.get_user!/1.

Check for Circular Dependencies

Run mix xref graph --format cycles --label compile.

Red Flags to Detect

IssueDetection CommandFix
Repo in web layergrep -r "Repo\." lib/my_app_web/Move to context
Schema with queriesgrep -r "import Ecto.Query" lib/my_app/**/schemas/Move queries to context
Cross-context schema importgrep -r "alias MyApp.Other.Schema" lib/my_app/ctx/Call context API
Business logic in LiveViewgrep -r "Repo\.|Ecto\.Multi" lib/my_app_web/live/Extract to context

Boundary Verification Process

  1. Run mix xref graph --label compile-connected for overview
  2. Check for context cross-contamination
  3. Verify no direct Repo calls from web layer
  4. Ensure schemas have no side effects
  5. Validate explicit cross-context dependencies

Next Steps

Always end with actionable follow-up — findings without a plan get lost:

- `/phx:plan` — Create a plan to fix violations (recommended for 3+ issues)
- `/phx:quick` — Fix a single boundary violation directly
- `/phx:review` — Review specific modules for deeper issues

References

For detailed patterns, see:

  • ${CLAUDE_SKILL_DIR}/references/context-design.md - Context design principles
  • ${CLAUDE_SKILL_DIR}/references/refactoring-boundaries.md - Fixing boundary violations

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Boundaries AI skill do?

Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.

Why use Boundaries on TypingMind?

Because you install it once and use it with any model. Boundaries is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Boundaries in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/oliver-kriska/claude-elixir-phoenix/tree/main/plugins/elixir-phoenix/skills/boundaries. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Boundaries?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Boundaries?

As many as you like. As long as a model supports skills, you can use Boundaries with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Boundaries AI skill free?

Yes. It is published on GitHub by oliver-kriska under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇