Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add furan917/magento-ai-toolkit --skill magento-agent-code-reviewgit clone --depth 1 https://github.com/furan917/magento-ai-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/furan917/magento-ai-toolkit/magento-agent-code-review)<a href="https://agentmods.dev/skills/furan917/magento-ai-toolkit/magento-agent-code-review"><img src="https://agentmods.dev/badge/skills/furan917/magento-ai-toolkit/magento-agent-code-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/furan917/magento-ai-toolkit/magento-agent-code-review"><img src="https://agentmods.dev/badge/skills/furan917/magento-ai-toolkit/magento-agent-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.04571 |
| Opus 5 | $0.00017 | $0.02286 |
| Sonnet 5 | $0.00007 | $0.00914 |
| Haiku 4.5 | $0.00003 | $0.00457 |
Grade A, and why
magento-agent-code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Code Review
Purpose: Autonomously review Magento 2 module code against coding standards, architectural rules, security requirements, and common pitfalls. Produces a structured report with severity-rated findings. Compatible with: Any agentic LLM with file read and grep tools (Claude Code, GPT-4o with tools, etc.) Usage: Point the agent at a module path or list of files and let it review. Companion skills: The agent checks code against the patterns defined in these skills — load any or all alongside for richer reference during review:
magento-plugin.md— plugin correctness rules (sortOrder, method visibility, around vs before/after)magento-observer.md— observer patterns (shared="false", event payload checking)magento-db-schema.md— declarative schema rules and Model/ResourceModel patternsmagento-api.md— service contract andApi/interface standardsmagento-test.md— test coverage expectations
Skill Detection
Before starting, scan your context for companion skill headers. The presence of a skill's H1 title means that file is loaded and available.
| Look for in context | If found | If not found |
|---|---|---|
# Skill: magento-plugin |
Use its plugin correctness rules (sort order, method visibility, around vs before/after) as the primary plugin review reference | Use the embedded plugin checklist in Step 3 — Plugins of this file |
# Skill: magento-observer |
Use its observer patterns (shared="false", event payload checking, ObserverInterface) as the primary observer review reference |
Use the embedded observer checklist in Step 3 — Observers of this file |
# Skill: magento-db-schema |
Use its declarative schema rules, column types, FK naming, and Model/ResourceModel patterns as the primary DB review reference | Use the embedded db_schema.xml checklist in Step 4 of this file |
# Skill: magento-api |
Use its service contract standards, REST and GraphQL patterns as the primary API review reference | Use the embedded architecture checklist in Step 5 of this file |
# Skill: magento-test |
Use its unit and integration test scaffold and coverage expectations as the primary test review reference | Use the embedded test coverage check in Step 5 of this file |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 406 lines · 34 tokens per session scan A 5904ab596fcf
magento-agent-code-review is a skill published in the GitHub repository furan917/magento-ai-toolkit (34 stars, last pushed 4mo ago), licensed MPL-2.0. It adds 34 tokens to every session and 4,571 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
magento2-code-review
This skill should be used when the user asks to "review this PR/MR", "review this merge request", "review this module", "audit this module before merge", "review this theme", "audit this theme PR", or wants a "full review before release". Orchestrates a PR/MR, module, theme, or full-project code review by running the…
review-in-worktree
Use this skill when reviewing code isolated in a Git worktree outside a Govard-managed project directory (for example Maestro merge-request review trees under /tmp), when "govard tool" cannot find the project configuration, or when asked to run Govard-managed commands against a detached review tree.
magento-code-reviewer
Reviews Magento 2 code for quality, security, performance, and compliance with PSR-12 and Magento coding standards. Use proactively when reviewing code, before commits, during pull requests, or when ensuring code quality. Enforces strict type declarations, proper dependency injection, security best practices, and…
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.