xm-cloud-graphql

xm-cloud-graphql is an agent for coding agents from smithdak/claude-marketplace. It costs 16 tokens per session (1,832 once invoked), scanned A, original, MIT.

An analysis agent for GraphQL queries in XM Cloud, Sitecore’s cloud content-management platform. GraphQL is a query language that lets an application request specific fields and related data.

In plain words
What is it for?
Use it to review XM Cloud GraphQL queries for articles, navigation, authors, relations, and nested fields, then identify ways to reduce unnecessary requests and data.
Why use it?
It detects inefficient data fetching, including N+1 queries that repeat requests for each item and over-fetching that retrieves more data than needed.

Agent

Part of the xm-cloud plugin — 1 skill, 1 agent shipped together

Install

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.

agentmods
npx agentmods add agents/smithdak/claude-marketplace/graphql
Clone the repo
git clone --depth 1 https://github.com/smithdak/claude-marketplace

Or install xm-cloud, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

Wrote 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.

agentmods badge for xm-cloud-graphql

README.md
[![agentmods](https://agentmods.dev/badge/agents/smithdak/claude-marketplace/graphql.svg)](https://agentmods.dev/agents/smithdak/claude-marketplace/graphql)
Your own site
<a href="https://agentmods.dev/agents/smithdak/claude-marketplace/graphql"><img src="https://agentmods.dev/badge/agents/smithdak/claude-marketplace/graphql.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,832 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.01832
Opus 5 $0.00008 $0.00916
Sonnet 5 $0.00003 $0.00366
Haiku 4.5 $0.00002 $0.00183

Measured 4d ago against content hash b0204e9172be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xm-cloud-graphql 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 4d 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.

plugins/xm-cloud-analyzer/agents/graphql.md · 355 lines

How it starts

The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.

XM Cloud GraphQL Agent

Analyze GraphQL query patterns, detect N+1 issues, and optimize data fetching.

Analysis Areas

1. N+1 Query Pattern (Critical)

Detect queries that fetch lists then make additional queries per item:

// Bad: N+1 pattern
const articles = await fetchArticles(); // Query 1
for (const article of articles) {
  article.author = await fetchAuthor(article.authorId); // N queries
}

// Good: Single query with relations
const articles = await fetchArticlesWithAuthors(); // 1 query

In GraphQL:

# Bad: Requires separate author query per article
query GetArticles {
  articles {
    id
    title
    authorId  # Then fetch author separately
  }
}

# Good: Fetch authors in same query
query GetArticlesWithAuthors {
  articles {
    id
    title
    author {
      name
      avatar
    }
  }
}

2. Over-Fetching (Critical)

Detect queries fetching more fields than needed:

# Bad: Fetching everything
query GetNavigation {
  item(path: "/sitecore/content/home") {
    id
    name
    displayName
    template
    created
    updated
    fields {
      # All fields
    }
    children {
      # All children with all fields
    }
  }
}

# Good: Only what's needed
query GetNavigation {
  item(path: "/sitecore/content/home") {
    children(hasLayout: true) {
      name
      url
    }
  }
}

3. Fragment Usage

Check for proper fragment usage for reusable field sets:

# Good: Reusable fragment
fragment NavigationFields on Item {
  name
  url
  navigationTitle: field(name: "Navigation Title") {
    value
  }
}

query GetNavigation {
  primaryNav: item(path: "/nav/primary") {
    children {
      ...NavigationFields
    }
  }
  footerNav: item(path: "/nav/footer") {
    children {
      ...NavigationFields
    }
  }
}

4. Query Error Handling

Check for proper error handling:

// Bad: No error handling
const { data } = await client.query({ query: GET_ARTICLES });

// Good: Error handling
try {
  const { data, errors } = await client.query({ query: GET_ARTICLES });
  if (errors) {
    console.error('GraphQL errors:', errors);
    return fallbackData;
  }
  return data;
} catch (error) {
  console.error('Query failed:', error);
  return fallbackData;
}

Read the full file on GitHub · 355 lines

Changes

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.

  1. 4d ago First seen · 355 lines · 16 tokens per session scan A b0204e9172be

Subscribe to this mod's changes

xm-cloud-graphql is an agent published in the GitHub repository smithdak/claude-marketplace (3 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 1,832 once invoked, about $0.0001 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 2026-08-31.