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-cachegit 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-cache)<a href="https://agentmods.dev/skills/furan917/magento-ai-toolkit/magento-agent-cache"><img src="https://agentmods.dev/badge/skills/furan917/magento-ai-toolkit/magento-agent-cache/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-cache"><img src="https://agentmods.dev/badge/skills/furan917/magento-ai-toolkit/magento-agent-cache.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 | $0.00047 | $0.03716 |
| Opus 5 | $0.00023 | $0.01858 |
| Sonnet 5 | $0.00009 | $0.00743 |
| Haiku 4.5 | $0.00005 | $0.00372 |
Grade A, and why
magento-agent-cache scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sI https://example.com/ | grep -i "x-magento-cache\|cache-control\|pragma" How it starts
The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Cache Expert
Purpose: Autonomously diagnose Magento 2 cache problems — full-page cache bypass, Redis memory pressure, block cache staleness, and custom cache type issues — and scaffold custom cache types from a specification. Compatible with: Any agentic LLM with file read and shell execution tools (Claude Code, GPT-4o with tools, etc.) Usage: Describe the cache problem or the cache type you need to build. The agent will diagnose or scaffold and produce a Cache Report. Companion skills: Load alongside for deeper reference:
magento-cache.md— TagScope patterns, cache.xml, tag invalidation, and FPC referencemagento-infra.md— Redis env.php config, CLI diagnostics, and memory eviction reference
Skill Detection
Before starting, scan your context for companion skill headers:
| Look for in context | If found | If not found |
|---|---|---|
# Skill: magento-cache |
Use its TagScope patterns, cache.xml templates, and block caching reference as the primary implementation reference | Use the embedded implementation steps and patterns in this file |
# Skill: magento-infra |
Use its Redis env.php config, keyspace hit/miss diagnostics, and eviction policy reference | Use the embedded Redis diagnostic commands in Step 2C of this file |
Skills take priority — they may contain more detail or be more up to date than the embedded fallbacks.
Agent Role
You are an autonomous Magento 2 cache expert. You diagnose cache configuration problems, trace FPC bypass, identify Redis memory issues, and implement custom cache types from a specification. You measure actual state before recommending changes.
Boundaries:
- Read files and run read-only
bin/magentocommands freely - Run
redis-cliread-only commands (info,dbsize,ttl,keys) freely - Ask for confirmation before running commands that flush or modify cache
- Never run
redis-cli flushallwithout explicit user confirmation — it logs out all sessions
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.
- 10d ago First seen · 412 lines · 47 tokens per session scan A 28983b89b88b
magento-agent-cache is a skill published in the GitHub repository furan917/magento-ai-toolkit (34 stars, last pushed 4mo ago), licensed MPL-2.0. It adds 47 tokens to every session and 3,716 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
magento-cache-analyst
Optimizes Magento 2 caching strategies for enterprise performance. Use when optimizing cache performance, configuring full-page cache, implementing Redis/Memcached, or designing cache invalidation strategies. Masters FPC, application cache, and distributed caching solutions.
sfcc-caching
Unified caching playbook for SFCC (page cache vs custom cache vs service response cache). Use this when improving performance, reducing external calls, designing cache keys/TTLs, or debugging stale cache behavior.
ecommerce-caching
Improve store performance with a layered caching strategy — CDN edge caching, Redis application cache, and smart cart-aware invalidation.
magento-index-analyst
Optimizes Magento 2 indexing for search performance and database efficiency. Use when optimizing search performance, configuring Elasticsearch, designing database indexes, or improving reindexing strategies. Masters indexer optimization, Elasticsearch configuration, and database indexing.
magento-model-developer
Designs and implements data layer architecture for Magento 2. Use when creating data models, designing database schemas, implementing repositories, or working with EAV/flat table structures. Masters entity design, repository patterns, collections, and database optimization.
woocommerce-performance
Fix slow WooCommerce stores by optimizing database queries, clearing transients, enabling Redis object caching, and configuring page caching.