Auto-loaded skills
Open a *_live.ex file → LiveView patterns load. Editing a migration → Ecto patterns. Auth code → Security Iron Laws. No /load commands. No prompt engineering.
phxagents
Iron Laws and specialist agents for Elixir/Phoenix in your AI coding tool.
Your AI coding tool is great. But it doesn’t know that assign_new silently skips on reconnect, that :float will corrupt your money fields, or that your Oban job isn’t idempotent.
This plugin does. It coordinates 21 specialist agents that plan, implement, review, and verify your Elixir/Phoenix code in parallel — each with fresh context, domain expertise, and enforced Iron Laws that catch the bugs your tests won’t. 43 skills auto-load based on the file you’re editing, so there’s no prompt engineering and no /load commands. Currently shipping for Claude Code at v2.8.8; Codex, OpenCode, and Pi support landing in v3.0.0.
$ /phx:plan Add real-time comments
✓ plan written: plans/2026-05-08-comments.md
43
skills auto-loaded for the file you're editing
21
specialist agents — planners, reviewers, investigators
22
Iron Laws — production-tested rules that catch bugs before they ship
104
deep-dive references for Phoenix, Ecto, LiveView, Oban, OTP
Where it runs
| AI coding tool | Status | Notes |
|---|---|---|
| Claude Code | ✓ shipped | v2.x — full plugin |
| Codex CLI | ◔ in development | landing v3.0.0 |
| OpenCode | ◔ in development | landing v3.0.0 |
| Pi | ◔ in development | landing v3.0.0 |
How it works
Section titled “How it works”Specialist agents
/phx:plan runs 4 research agents in parallel. /phx:review runs 4 review agents. Each has fresh context and domain expertise. The orchestrator synthesises.
Iron Laws enforcement
22 non-negotiable rules: no :float for money, always assign_async in mount, never String.to_atom with user input. Verified at edit time and at review.
Plan → Work → Review → Compound
Filesystem is the state machine. Plans live as checkbox markdown. Reviews produce findings, not source edits. Solved problems become reusable knowledge.
Start with these
Four core workflow skills and four flagship orchestrators. Browse all 43 skills or all 21 agents.
Workflow skills
phx:plan Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks. → phx:work Execute Elixir/Phoenix plan tasks with progress tracking. Use after /phx:plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work. → phx:review Review code with parallel agents — tests, security, Ecto, LiveView, Oban. Use after implementation to catch bugs and anti-patterns before committing. → phx:full Use for large features spanning multiple contexts, new domain modules, or when the user wants autonomous end-to-end implementation. Runs the full plan-implement-review-compound cycle with specialist agents and Iron Laws enforcement. →
Orchestrators & reviewers
workflow-orchestrator Orchestrates the full agentic workflow cycle (plan → work → review). Internal use by /phx:full command. → parallel-reviewer Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes. → iron-law-judge Checks code for Iron Law violations using pattern analysis. Use proactively after code changes or as part of review. → phoenix-patterns-analyst Analyzes codebase for existing Phoenix patterns, contexts, module structure, scopes, plugs, and routing. Use proactively when planning features to understand current conventions. →
Get started
Section titled “Get started”Run these in Claude Code, one at a time. Each block has its own copy button.
/plugin marketplace add oliver-kriska/claude-elixir-phoenix/plugin install elixir-phoenix