iliaal-marketplace

Compound Engineering Plugin

A Claude Code plugin that makes AI coding agents follow engineering discipline. Plan before coding. Verify before claiming done. Find root cause before patching. Review before merge. The agent picks up the right methodology based on what you're working on, no manual activation needed.

Bundles agents, skills, workflow commands, and a skill distillery for PHP, Python, TypeScript, React, and infrastructure workflows.

Who this is for

Teams using Claude Code for real work. You're building with PHP, Python, TypeScript, or React. You want the agent to plan before building, verify before shipping, and debug by reasoning instead of guessing. This plugin provides that structure.

Solo developers who want consistency. Write a Bash script and the agent enforces set -Eeuo pipefail and ShellCheck compliance. Touch a Laravel controller and it applies strict types and thin-controller patterns. No setup, no toggling.

Anyone building with AI agents. Includes skills for multi-agent orchestration, agent-native architecture design, and a distillery that generates new skills from top-rated community sources.

Install

Claude Code (recommended)

/plugin marketplace add https://github.com/iliaal/compound-engineering-plugin
/plugin install compound-engineering

Standalone skills (any AI coding agent)

Individual skills work with Claude Code, Cursor, Codex, Gemini CLI, Copilot CLI, OpenCode, and 35+ other agents via the ai-skills repo:

# All skills
npx skills add iliaal/ai-skills

# Single skill
npx skills add iliaal/ai-skills -s code-review

# Target a specific agent
npx skills add iliaal/ai-skills -a cursor

OpenCode & Codex

The repo includes a Bun/TypeScript CLI that converts Claude Code plugins to OpenCode and Codex formats:

bun run src/index.ts install ./plugins/compound-engineering --to opencode
bun run src/index.ts install ./plugins/compound-engineering --to codex

The workflow

Five commands form a loop: explore the problem, plan the solution, build it, review it, document what you learned. Each pass makes the next one faster because solutions accumulate as searchable docs.

Command	What it does
/workflows:brainstorm	Interviews you one question at a time to surface hidden requirements. Produces 2-3 named approaches with trade-offs. No code until a design doc is approved.
/workflows:plan	Turns a brainstorm or feature idea into a file-based plan with atomic tasks, specific file paths, and phased delivery in vertical slices.
/workflows:work	Executes a plan with task tracking, worktree isolation, and verification gates. Each task runs through build/test before marking complete.
/workflows:review	Multi-agent code review: scope-drift detection, spec compliance, code quality, security, performance. Auto-escalates to deep mode on complex diffs.
/workflows:compound	Captures what you just solved as searchable documentation in docs/solutions/ so the next person (or the agent) doesn't re-debug it.

You don't have to use all five. /workflows:review on its own is a solid pre-merge check. /workflows:plan works standalone for scoping. Mix and match.

Skills

Skills are instructions that activate based on what you're working on. They shape how the agent behaves, enforcing procedures and anti-patterns rather than adding knowledge.

Architecture & design

Skill	Description
agent-native-architecture	15-area architecture checklist for systems where AI agents are primary actors: tool design, execution patterns, context injection, approval gates, audit trails. For designing agent systems or MCP tools.
frontend-design	Requires a design philosophy statement before code, detects existing design systems to match, and bans AI design cliches (purple-to-blue gradients, Space Grotesk, three-card hero layouts). Calibrates output via variance, motion, and density parameters. For work where visual identity matters.
simplifying-code	Declutters code without changing behavior. Targets AI slop: redundant comments, unnecessary defensive checks, over-abstraction, verbose stdlib reimplementations. Applies changes in priority order and stops before touching public APIs. For cleanup after AI generation or accumulated complexity.

Language & framework