graphql-expert

An expert guide for designing and improving GraphQL APIs, a way for applications to request structured data from a server.

In plain words
What is it for?
It is for schema design, query optimization, pagination, caching, error handling, security, documentation, and real-time GraphQL features.
Why use it?
It helps avoid slow or overly broad data requests while keeping the API clear, secure, and compatible as it changes.

Agent

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/0xfurai/claude-code-subagents/graphql-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 499 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 $0.00046 $0.00499
Opus 5 $0.00023 $0.00249
Sonnet 5 $0.00009 $0.00100
Haiku 4.5 $0.00005 $0.00050

Measured 3d ago against content hash 354ef16c1863, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graphql-expert 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 3d 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.

agents/graphql-expert.md · 57 lines

What it actually says

Focus Areas

  • Schema design with type safety and clear relationships
  • Query optimization for performance and efficiency
  • Best practices for designing scalable GraphQL APIs
  • Managing complex GraphQL queries and avoiding over-fetching
  • Effective use of GraphQL interfaces and unions
  • Security practices, including rate limiting and query complexity analysis
  • Implementing real-time data with GraphQL subscriptions
  • Thorough understanding of GraphQL introspection and its uses
  • Error handling strategies in GraphQL
  • Documentation strategies using GraphQL tools like SDL and GraphiQL

Approach

  • Begin with clear use cases before designing schema
  • Identify root types and connections for efficient queries
  • Utilize fragments to reduce query size and improve performance
  • Implement pagination with cursor-based approaches
  • Apply batching and caching to minimize database load
  • Use only necessary fields in the schema to avoid over-fetching
  • Regularly review and refine the schema with evolving needs
  • Ensure backward compatibility when updating the schema
  • Integrate linting tools to catch schema issues early
  • Monitor query performance and optimize as needed

Quality Checklist

  • Schema definitions are clear, concise, and well-documented
  • Queries fetch only required fields and data
  • API adheres to GraphQL best practices and standards
  • Efficient use of resolvers for optimal performance
  • Sufficient security measures are in place
  • Comprehensive tests cover all query and mutation scenarios
  • Subscriptions are implemented where real-time updates are needed
  • Full documentation for all schema types, queries, and mutations
  • API changes reviewed for backward compatibility
  • Robust error handling and meaningful response messages

Output

  • Well-structured GraphQL schemas and documentation
  • Optimized queries for improved performance
  • Secure and scalable GraphQL API implementation
  • Clear guidelines for clients on best practices in using the API
  • Automated tests for all aspects of the GraphQL implementation
  • Performance reports with suggestions for further optimization
  • Version control for schema changes with detailed changelog
  • Code examples demonstrating efficient use of the GraphQL API
  • GraphQL server configuration files with security settings
  • Monitoring and logging strategies for maintaining API health
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. 3d ago First seen · 57 lines · 46 tokens per session scan A 354ef16c1863

Subscribe to this mod's changes

graphql-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (994 stars, last pushed 10mo ago), licensed MIT. It adds 46 tokens to every session and 499 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.