By muon-m2
End-to-end Magento 2 engineering skills: scaffold, review, test, fix, deploy, audit, and more. Hub-and-spoke design around magento2-context.
Full release-readiness audit — every findings dimension consolidated into one ranked report + merged SARIF (magento2-audit)
Reproduce → root-cause → minimal TDD fix → regression test → review (magento2-bug-fix)
Resolve the Magento 2 project context — vendor, runner, versions, theme, tools (magento2-context). Use when explicitly asked to resolve or refresh project context.
Deploy Magento 2 module(s) — pre-flight, ordered deploy, rollback (magento2-deploy)
End-to-end Magento 2 feature implementation orchestrator (magento2-feature-implement)
Use for a read-only COMPREHENSION mapping of an existing Magento 2 module or feature — maps execution paths, DI wiring, plugin/observer/preference extension points, service-contract and cross-module dependencies, and produces a Mermaid call-chain flowchart. Use before modifying unfamiliar code, during bug-fix root-cause analysis (RCA) to trace a suspect execution path, or as the inventory/comprehension step of a parallel review (run this first, then pass the map to magento2-reviewer for quality judgement). Returns a structured COMPREHENSION MAP — entry points, data flow, extension points, dependencies, Mermaid flowchart, and open questions. Never modifies code and never emits severity-ranked findings (that is magento2-reviewer's role). Examples — "map how Acme_Checkout builds the grand totals and which plugins intercept the collect call"; "trace what runs when sales_order_place_after fires in Acme_Loyalty".
Use for an independent, READ-ONLY review/audit of a Magento 2 module — either a whole module or a single review dimension (architecture/API, security, frontend/admin, testing/tooling, or performance/operations). Dispatch one agent per dimension to review large or security-sensitive modules in parallel; the caller (magento2-module-review) owns final synthesis (dedup, severity normalization, conflict tie-breaking). Returns findings-first results — each finding with a severity (Critical/High/Medium/Low/Info), category, `file:line` evidence, and a concrete fix. Never modifies code. Examples — "review the security dimension of app/code/Acme/OrderExport"; "audit the performance surfaces of Acme_Catalog and return ranked findings".
Audit a Magento 2 module's/theme's storefront templates for WCAG accessibility issues — missing alt text, unlabelled form controls, ARIA misuse, heading-order breaks, keyboard/tab-index problems, and LESS color-contrast heuristics — and emit ranked findings (Markdown + JSON + SARIF). Static-first (no running instance needed); optional opt-in pa11y runtime pass. For building accessible frontend assets use `magento2-frontend-create`; for general module quality use `magento2-module-review`.
Generate a Magento 2 adminhtml UI-component edit form — the modern declarative ui_component/{entity}_form.xml plus its DataProvider, button blocks, and the New/Edit/Save/Delete controllers wired to a listing. Use when the user wants to add or scaffold a new admin form, an entity edit page, a "New/Edit" backend screen, fieldsets, a WYSIWYG field, a toggle, dynamic-rows, or file/image uploaders in the Magento admin. Detects edition (Open Source vs Adobe Commerce) and flags Commerce-only form features. Produces files that pass magento2-module-review with zero Critical/High findings.
Generate a Magento 2 adminhtml UI-component listing/grid — the declarative `ui_component/{entity}_listing.xml` plus its DataProvider, columns, actions column, and mass actions, wired to an existing edit form. Use when the user wants to add or scaffold an admin grid, data grid, listing page, grid columns, filters, mass actions, or an actions column in the Magento admin. Pairs with magento2-adminhtml-form (the edit form); for the form itself use magento2-adminhtml-form. Detects edition and flags Commerce-only grid features. Produces files that pass magento2-module-review with zero Critical/High findings.
Use when the user wants a full pre-release, release-readiness, or "audit everything" pass over a Magento 2 module or codebase — one command that runs every read-only findings dimension and returns a SINGLE consolidated, de-duplicated, severity-ranked report plus one merged SARIF for CI / GitHub Code Scanning. Fans the dimensions out in parallel: architecture/quality/security review via the `magento2-reviewer` agent per dimension, plus the specialist audits `magento2-security-audit`, `magento2-performance-audit`, `magento2-static-analysis`, `magento2-accessibility-audit`, `magento2-marketplace-prep`, and `magento2-breeze-compat-audit` where the module's surface warrants — then consolidates. Read-only; never modifies code. For a SINGLE dimension, invoke that skill directly (`magento2-module-review`, `magento2-security-audit`, `magento2-performance-audit`); to BUILD or change functionality rather than inspect it, use `magento2-feature-implement`.
Scaffold a Swissup Breeze (Breezefront) child theme — theme.xml with a Swissup/breeze-* parent, registration.php, composer.json, a Breeze-only layout handle, and Breeze-side overrides in web/css/breeze/_default.less with @critical guards. Use when the user wants a new Breeze child or custom theme. Detects Breeze via magento2-context (theme.breeze) and refuses with the install command when Breeze is absent. Sibling to magento2-frontend-create, which builds generic Luma/Hyva/custom themes plus RequireJS/Knockout/Alpine components; this skill is Breeze-specific. To adapt an existing module to Breeze use magento2-breeze-module-adapt; to check a module's Breeze compatibility use magento2-breeze-compat-audit.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
A Claude Code plugin of skills for end-to-end Magento 2 engineering: scaffolding, review, testing, bug-fixing, deployment, auditing, and more — built around a shared context-resolver so the same toolkit adapts to any project and environment.
🌐 Website: https://muon-m2.github.io/magento2-tools/
/plugin marketplace add muon-m2/magento2-tools
/plugin install magento2-tools@muon-m2 --scope user
--scope user makes it available in every project. Use --scope project to pin it to
one repo. Skills are then invoked namespaced, e.g. magento2-tools:magento2-bug-fix.
Team auto-enable — commit to a project's .claude/settings.json:
{
"extraKnownMarketplaces": {
"muon-m2": { "source": { "source": "github", "repo": "muon-m2/magento2-tools" } }
},
"enabledPlugins": { "magento2-tools@muon-m2": true }
}
On folder-trust, Claude Code offers to install the marketplace and enables the plugin — zero manual steps for teammates.
New to the toolkit? Open any Magento 2 project in Claude Code and try these — all read-only, nothing is modified:
# 1. Let the toolkit learn your project (vendor, runner, versions, theme, tools)
Resolve the Magento 2 project context
# 2. Severity-ranked review of one of your modules, with file:line evidence
Quick review of the module app/code/<Vendor>/<Module>
# 3. One-page health snapshot: indexers, caches, queues, cron, versions
/magento2-tools:snapshot
Skills are triggered by plain language ("fix this checkout bug", "scaffold a module
for order export") or invoked explicitly with flags
(/magento2-tools:deploy --env=staging Acme_OrderExport). Code-writing skills
always stop at an approval gate (blueprint, RCA, deploy plan, release push) before
changing anything; reports land in your project's .docs/ folder. The full
walkthrough lives in docs/getting-started.md.
Developer documentation lives in docs/:
| Doc | What it covers |
|---|---|
| Getting started | Install, first run, safety model, first commands for first-time users |
| Daily workflows | Day-to-day recipes: bug fixes, features, reviews, tests, deploys, audits, releases |
| New project guide | Bootstrapping a new Magento 2 project with the toolkit, from CLAUDE.md to first release |
| Flows and scenarios | Architecture, per-skill phase flows with diagrams, approval-gate map, artifact map, end-to-end scenarios |
| Skills reference | Per-skill quick reference: invocation, flags, phases, outputs |
| Configuration | Context resolver, overrides, CLAUDE.md hints, CI integration (validate-only deploys, SARIF) |
33 skills under skills/, each self-contained (SKILL.md + references/ +
scripts/ + templates/). Per-skill flags, phases, and outputs are documented in
docs/skills-reference.md.
npx claudepluginhub muon-m2/magento2-toolsComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
The most comprehensive Claude Code plugin — 14+ agents, 56+ skills, 33+ commands, and production-ready hooks for TDD, security scanning, code review, and continuous learning
v9.52.0 - Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification