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 j4flmao/agent-skills --skill graphql-patternsgit clone --depth 1 https://github.com/j4flmao/agent-skillsWrote 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/j4flmao/agent-skills/graphql-patterns)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/graphql-patterns"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/graphql-patterns/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/j4flmao/agent-skills/graphql-patterns"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/graphql-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.06124 |
| Opus 5 | $0.00041 | $0.03062 |
| Sonnet 5 | $0.00016 | $0.01225 |
| Haiku 4.5 | $0.00008 | $0.00612 |
Grade A, and why
backend-graphql-patterns 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 8d 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 — 619 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend GraphQL Patterns
Purpose
Design production GraphQL schemas with resolvers, DataLoader batching, and auth.
Agent Protocol
Trigger
Exact user phrases: "GraphQL", "schema", "resolver", "query", "mutation", "subscription", "Apollo", "Relay", "GraphQL federation", "GraphQL gateway", "data loader", "N+1 GraphQL", "GraphQL authorization", "GraphQL pagination", "GQL schema design", "GraphQL error handling".
Input Context
Before activating, verify:
- Schema size (number of types, depth of nesting)
- Data sources (primary database, REST APIs, gRPC services, external APIs)
- Authentication and authorization model (RBAC, ABAC, claims-based)
- Client types consuming the API (web SPA, mobile native, third-party, internal services)
Output Artifact
GraphQL schema design with resolver patterns and DataLoader setup as formatted text.
Response Format
# Schema types, queries, mutations
// DataLoader setup
// Resolver patterns
// Auth directive definitions
# Query complexity limits
# Rate limiting rules
No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick.
Completion Criteria
- Schema defined with types, queries, mutations, subscriptions
- N+1 query prevention via DataLoader batching
- Auth directives (@auth, @hasRole) applied to schema
- Pagination implemented as cursor-based (Relay edges/node pattern)
- Error handling with typed error codes and partial success
- Query complexity limits and rate limiting configured
Max Response Length
300 lines of schema + resolver code, 50 lines of configuration.
Decision Tree
When to Use GraphQL?
What is the primary API consumer?
├── Multiple client types (web, mobile, third-party), different data needs
│ └── GraphQL — clients control data shape, reduces over/under-fetching
├── Single client, well-defined views
│ └── REST — simpler, cacheable, tooling maturity
├── Internal service-to-service communication
│ └── gRPC — typed contracts, streaming, higher performance
└── Public API for third-party developers
└── REST with OpenAPI — industry standard, broad tooling support
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/federation-subscriptions.md 7.9 KB
- references/graphql-federation.md 7.5 KB
- references/graphql-migration.md 6.2 KB
- references/graphql-monitoring.md 7.3 KB
- references/graphql-performance.md 6.6 KB
- references/graphql-security.md 6.7 KB
- references/graphql-tooling.md 7.8 KB
- references/schema-resolvers.md 7.2 KB
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.
- 8d ago First seen · 619 lines · 82 tokens per session scan A 830457b631c4
backend-graphql-patterns is a skill published in the GitHub repository j4flmao/agent-skills (23 stars, last pushed 5d ago), licensed MIT. It adds 82 tokens to every session and 6,124 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
payload
Use when working with Payload projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Use when debugging validation errors, security issues, relationship queries, transactions, or hook behavior.
hunt-graphql
Hunting skill for graphql vulnerabilities. Built from 12 public bug bounty reports across IDOR via node() / GID, mutation IDOR including AI/LLM features, cross-tenant IDOR, SSRF via argument, batching-DoS, query-cost-bypass, SQLi via argument, broken-object-level-authz, auth-bypass via unscoped mutations, and PII…
hunt-nestjs
Hunt NestJS-specific vulnerabilities: guard bypass, decorator gaps, and microservice auth drift.
nornicdb-bolt-client
Drive NornicDB from a Bolt client (neo4j-go-driver/v5 or any other Neo4j Bolt driver). Use when classifying retryable vs permanent errors, sizing UNWIND/MERGE batch writes, configuring connection defaults, or implementing retry logic against NornicDB. NornicDB speaks the same wire as Neo4j 5; this skill calls out the…
nornicdb-grpc
Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…
nornicdb-neo4j-migration
Migrate from Neo4j 5 to NornicDB end-to-end over Bolt. Covers schema replication (constraints + indexes including fulltext and vector), node and edge replication using hot-path UNWIND/MERGE shapes from the cookbook, label preservation strategy, what does and does not transfer, the cutover playbook. Points to runnable…