Plugin Initialization

SkillAI & models

Initialize plugin in a project — install Iron Laws, auto-activation rules,

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Plugin Initialization skill

What this skill tells your AI

The instructions your AI receives, as published by oliver-kriska/claude-elixir-phoenix in targets/pi/skills/phx-init/SKILL.md and read by ahel’s review.

Install the Elixir/Phoenix plugin's behavioral instructions into the project's CLAUDE.md.

Usage

/skill:phx-init           # First-time installation
/skill:phx-init --update  # Update existing installation with latest rules

Iron Laws

  1. NEVER overwrite content outside plugin markers — User-written CLAUDE.md rules must be preserved verbatim
  2. Always detect stack before generating — Never assume Phoenix/Ecto versions
  3. Always validate after installation — Verify markers present and stack correct

Workflow

Step 1: Check Existing CLAUDE.md

Use Glob to check if CLAUDE.md exists. Then use Grep to check for existing ELIXIR-PHOENIX-PLUGIN:START marker in CLAUDE.md.

Step 2: Detect Project Stack

Scan the project to customize the injected instructions:

Read mix.exs and use Grep to extract:

  • Phoenix version: search for phoenix.*"~> in mix.exs
  • Ecto version: search for ecto.*"~> in mix.exs
  • Oban: search for "oban" and "oban_pro" in mix.exs
  • Frameworks: search for "ash", "surface" in mix.exs
  • Tidewave: search for "tidewave" in mix.exs
  • Project size: use Glob to count lib/**/*.ex files

Step 3: Handle Installation Modes

Mode A: Fresh Install (no CLAUDE.md or no markers)

  1. Create/append to CLAUDE.md
  2. Insert full behavioral instructions between markers
  3. Include only relevant sections based on detected stack

Mode B: Update (--update flag or markers exist)

  1. Find content between <!-- ELIXIR-PHOENIX-PLUGIN:START --> and <!-- ELIXIR-PHOENIX-PLUGIN:END -->
  2. Replace with latest behavioral instructions
  3. Preserve everything outside the markers

CRITICAL: NEVER overwrite or delete existing CLAUDE.md content outside the plugin markers — user-written rules, project conventions, and other plugin sections must be preserved verbatim

Step 4: Generate Content

Write the following structure to CLAUDE.md:

<!-- ELIXIR-PHOENIX-PLUGIN:START -->
<!-- Last updated: {date} | Plugin version: 1.0 | Stack: Phoenix {version}, Ecto {version}, {optional: Oban, Tidewave} -->

# Elixir/Phoenix Plugin - Auto-Activation Rules

{Include all sections from the Content Template below, filtered by detected stack}

<!-- ELIXIR-PHOENIX-PLUGIN:END -->

Step 4b: Offer Codex Review Guidelines (optional)

If command -v codex succeeds (or the user asks): offer to install a managed ## Review guidelines block into the project's AGENTS.md — honored by BOTH codex exec review locally and the Codex cloud PR reviewer. Follow the install rules and exact block in references/codex-review-guidelines.md: markers ELIXIR-PHOENIX-REVIEW-GUIDELINES:START/END, upsert in place on --update, never touch content outside markers, and STOP to ask if an unmanaged ## Review guidelines section already exists. When codex is absent and not requested, skip silently — never mention codex to users who don't have it.

Step 5: Output Summary

✅ Elixir/Phoenix plugin initialized

Detected stack:
- Phoenix {version}
- Ecto {version}
- {Oban standard | Oban Pro | not detected}
- {Tidewave ✓ | Tidewave not detected}
- {Ash Framework detected - Ecto patterns disabled | not detected}

Added to CLAUDE.md:
- Auto-activation rules (complexity detection, interview mode)
- Agent trigger patterns ({n} agents available)
- Reference auto-loading ({n} reference docs)
- Iron Laws enforcement ({n} laws)
- Verification rules
{- Codex review guidelines → AGENTS.md (only if installed in Step 4b)}

Run /skill:phx-init --update after plugin updates.
Run /skill:phx-audit for a full project health check.

Content Template

The exact content to inject is in references/injectable-template.md.

Key structure:

  1. Routing table — which /skill:phx-* command fits which kind of request
  2. Iron Laws — STOP behavior on violations
  3. Conditional Sections — Include based on detected stack:
    • {OBAN_SECTION} — If Oban detected (not Pro)
    • {OBAN_PRO_SECTION} — If Oban Pro detected
    • {ASH_SECTION} — If Ash Framework detected
    • {TIDEWAVE_SECTION} — If Tidewave detected
  4. Verification — Mandatory after code changes
  5. Quick Reference — Skill routing table

Placeholder substitution:

PlaceholderSource
{DATE}Current date
{PHOENIX_VERSION}From mix.exs
{ECTO_VERSION}From mix.exs
{OPTIONAL_STACK}Detected optional deps

See references/injectable-template.md for full template with all placeholders and conditional sections.

Validation

After running /skill:phx-init:

  1. Check CLAUDE.md contains markers
  2. Verify detected stack matches actual project
  3. New session should:
    • Auto-detect complexity when given tasks
    • Stop on Iron Law violations
    • Offer relevant workflows based on task

Error Handling

ScenarioAction
CLAUDE.md read-onlyError: "Cannot modify CLAUDE.md - check permissions"
Markers corruptedWarn, offer to remove and reinstall
Unknown Phoenix versionUse conservative defaults (all features enabled)
Not an Elixir projectError: "No mix.exs found - is this an Elixir project?"

Relationship to Other Commands

CommandWhen to Use
/skill:phx-initFirst time, or after plugin updates
/skill:phx-auditPeriodic project health check
/skill:phx-verifyAfter code changes

Signals

GitHub stars
551
Forks
39
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
phx-init
Source
github.com/oliver-kriska/claude-elixir-phoenix