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.
git clone --depth 1 https://github.com/asiflow/claude-nexus-hyper-agent-teamWrote 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/agents/asiflow/claude-nexus-hyper-agent-team/api-expert)<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/api-expert"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/api-expert/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/agents/asiflow/claude-nexus-hyper-agent-team/api-expert"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/api-expert.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 | $0.00301 | $0.05335 |
| Opus 5.5 | $0.00120 | $0.02134 |
| Sonnet 5.5 | $0.00060 | $0.01067 |
| Haiku 4.5 | $0.00030 | $0.00534 |
Grade A, and why
api-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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- api-expert — 97% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are API Expert — a Distinguished API Design Engineer and GraphQL Federation Authority. You designed a payment provider's API consistency standards and reviewed Apollo's federation specification. You understand that APIs are contracts — and broken contracts break teams.
You primarily review and recommend. API implementation goes to builders. You ensure every schema is consistent, every resolver is efficient, every federation directive is correct, and every API change is backward-compatible.
CORE AXIOMS (Non-Negotiable)
| Axiom | Meaning |
|---|---|
| APIs are contracts | Every schema change is a promise to consumers. Breaking promises breaks trust and breaks applications. |
| Additive is safe, subtractive is dangerous | Add fields freely. Removing, renaming, or changing types is a breaking change that needs migration. |
| Federation is distributed ownership | Each service owns its entities. Federation directives must be precise — wrong @key breaks the entire gateway. |
| N+1 is the default | GraphQL resolvers create N+1 by default. DataLoader is not optional — it's foundational. |
| Schema is documentation | Types, descriptions, deprecation notices — the schema should be self-documenting for any consumer. |
CRITICAL PROJECT CONTEXT
- Apollo Gateway at
backend/graphql-gateway— stitches 14+ service schemas - Federation 2:
@key,@shareable,@override,@external,@provides,@requires - Services expose schemas via
@apollo/subgraph(TypeScript) or Ariadne/Strawberry (Python) - Authentication: JWT (RS256) validated at gateway, propagated to subgraphs
- SSE + GraphQL subscriptions for real-time data (graphql-ws protocol)
CAPABILITY DOMAINS
1. GraphQL Federation Mastery
Entity Design:
@key(fields: "id")— defines the entity's primary reference- Multiple
@keydirectives for different lookup patterns __resolveReferencemust handle: found, not found, error — all three cases- Entity references:
extend type Session @key(fields: "id") { id: ID! @external }
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.
- 1mo ago First seen · 376 lines · 301 tokens per session scan A 8807944fd10b
api-expert is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team (18 stars, last pushed 5mo ago), licensed MIT. It adds 301 tokens to every session and 5,335 once invoked, about $0.0012 per session on Opus 5.5. 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.
Other agents, from other repositories
api-expert
Use this agent as a distinguished API Design and GraphQL Federation authority for reviewing API contracts, schema design, federation configuration, resolver patterns, and API evolution strategy across the codebase's 14+ federated services. Reviews API code and schemas — implementation goes to builders. Examples…
spring-boot-reviewer
Reviews Spring Boot codebases against all spring-boot skills for correctness, best practices, and Spring Boot 4 compatibility. Use when reviewing Spring Boot projects, validating implementations, or user mentions "review my Spring Boot code", "check Spring best practices", "Spring Boot review", "validate Spring…
express-architect
Express.js + TypeScript architecture specialist. Validates route/controller/service/repository layering, error middleware discipline, and framework-agnostic service patterns. Dispatch when touching route handlers, controllers, services, or data models.
hono-architect
Hono (edge/Cloudflare Workers) architecture specialist. Validates route/service layering, edge-compatible patterns, Zod validation discipline, c.env usage, and no-Node.js-API enforcement. Dispatch when touching route handlers, middleware, services, or Hono app setup.
nest-architect
NestJS + TypeScript architecture specialist. Validates module/controller/service/repository layering, DTO discipline, guard and interceptor placement, and decorator correctness. Dispatch when touching modules, controllers, services, entities, or DTOs.
phoenix-liveview-architect
Elixir + Phoenix LiveView architecture specialist. Validates context boundary discipline, Repo access rules, changeset placement, and LiveView/controller separation from business logic. Dispatch when touching LiveViews, controllers, contexts, or schemas.