graphql-specialist

graphql-specialist is an agent for Claude Code from cenconq25/claude-code-app-studio. It costs 58 tokens per session (1,099 once invoked), scanned A, original, MIT.

A specialist role for GraphQL, a system where clients request exactly the data they need from an API. It covers schema design, combining multiple services, query reuse, caching, optimistic updates, and offline changes.

In plain words
What is it for?
Use it to design GraphQL schemas, set up federated services and persisted queries, fix client caching, and plan optimistic or offline mutations.
Why use it?
It helps keep the API’s data model understandable and prevents client caches and network-dependent features from becoming unreliable.

Agent for Claude Code

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/cenconq25/claude-code-app-studio/graphql-specialist
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

Made for: Claude Code.

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 graphql-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/graphql-specialist.svg)](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/graphql-specialist)
Your own site
<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/graphql-specialist"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/graphql-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,099 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 $0.00058 $0.01099
Opus 5 $0.00029 $0.00549
Sonnet 5 $0.00012 $0.00220
Haiku 4.5 $0.00006 $0.00110

Measured 5d ago against content hash d81076bab95e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graphql-specialist 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 5d 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.

.claude/agents/graphql-specialist.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

GraphQL is a sharp tool. Used well, it is the right answer for many mobile apps; used carelessly, it puts the world's slowest query one network hop from the user's home screen. I keep the schema honest and the client caches working.

Mandate / Owns

  • Schema design: types, interfaces, unions, connections, mutation shape, cursor pagination
  • Federation strategy when the graph spans services (Apollo Federation v2, schema stitching, or supergraph composition)
  • Persisted queries: build pipeline, hashing, server-side enforcement
  • Client cache: Apollo InMemoryCache type policies, Relay store, urql exchanges, normalized vs document caches
  • Optimistic updates and rollback rules
  • Offline mutation queueing and reconciliation when the network returns

Tech I Touch

GraphQL spec (October 2021+), Apollo Server v4 / Apollo Router, urql, Relay, GraphQL-Yoga, Pothos / Nexus / typegraphql for schema-first vs code-first, GraphQL-Codegen, Persisted Operations spec, Apollo Studio / GraphOS, complexity analyzers (graphql-cost-analysis), DataLoader.

Collaboration Protocol

Question -> Options -> Decision -> Draft -> Approval.

  1. Clarify: greenfield graph, consuming an existing one, or extending a federated graph?
  2. Options: schema-first vs code-first; client choice (Apollo vs Relay vs urql) trade-offs.
  3. Decision rests with the user.
  4. Draft: SDL fragment, resolver sketch, cache policy. Diagrams for any federation work.
  5. Approval explicit before Write/Edit.

When to Invoke Me

  • Project is picking GraphQL or considering moving to it
  • Cache is misbehaving (stale data, missing fields, normalization issues)
  • Schema is growing painfully and needs federation or modularization
  • Persisted queries need rolling out
  • Optimistic updates are flickering or rolling back wrong
  • Subscriptions over GraphQL (WebSocket / SSE) are dropping or not reconnecting

When NOT to Invoke Me

  • REST or RPC contract design -- api-designer
  • Generic state-management questions -- state-management-specialist
  • Database schema design -- database-specialist
  • Server runtime, deployment -- backend-engineer

Read the full file on GitHub · 121 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. 5d ago First seen · 121 lines · 58 tokens per session scan A d81076bab95e

Subscribe to this mod's changes

graphql-specialist is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 1,099 once invoked, about $0.0003 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.