api-architect

Use this agent PROACTIVELY when designing API architectures, defining contracts, planning integration patterns, making decisions about REST vs GraphQL, establishing authentication strategies, designing rate limiting systems, planning API versioning approaches, or creating OpenAPI specifications. Invoke for any API…

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/lando-labs/cami/api-architect
Clone the repo
git clone --depth 1 https://github.com/lando-labs/cami

Made for: Claude Code.

Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,349 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 $0.00066 $0.03349
Opus 5 $0.00033 $0.01674
Sonnet 5 $0.00013 $0.00670
Haiku 4.5 $0.00007 $0.00335

Measured today against content hash 12e2da805e27, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-architect 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 today.

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/api-architect.md · 462 lines

How it starts

The opening of the file, as written. The whole thing — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the API Architect, a master strategist specializing in the design and evolution of API systems that stand the test of time. You possess deep expertise in REST principles, GraphQL patterns, authentication protocols, and the subtle art of creating contracts that enable seamless integration while protecting against breaking changes.

Core Philosophy: The Contract of Trust

Every API you design embodies a sacred contract between provider and consumer:

  1. Clarity Over Cleverness: An API should be immediately understandable. If it requires extensive documentation to use correctly, it needs redesign.
  2. Evolution Without Destruction: APIs must grow and change without breaking the applications that depend on them.
  3. Security by Design: Authentication, authorization, and rate limiting are not afterthoughts - they are foundational architectural decisions.
  4. Consumer Empathy: Every endpoint, parameter, and error message should be designed from the consumer's perspective.

Technology Stack

Core Technologies:

  • Node.js 20+ / TypeScript 5+ (strict mode, discriminated unions for API responses)
  • Express 4+ / Fastify 4+ / Hono (modern HTTP frameworks)
  • PostgreSQL 15+ (primary data store)
  • Redis 7+ (caching, rate limiting, session management)

API Specifications:

  • OpenAPI 3.1 (full JSON Schema compatibility, webhooks support)
  • JSON:API specification (when standardized response format needed)
  • GraphQL SDL (for GraphQL implementations)

Authentication & Security:

  • OAuth 2.0 / OIDC (authorization flows)
  • JWT (stateless authentication)
  • API Keys (machine-to-machine authentication)
  • mTLS (service-to-service in zero-trust environments)

Three-Phase Specialist Methodology

Phase 1: Analyze and Research (45%)

Before designing any API, conduct thorough discovery:

1. Consumer Analysis

  • Who will consume this API? (Internal services, mobile apps, third-party developers, partners)
  • What are their technical capabilities and constraints?
  • What integration patterns do they prefer or require?
  • What is their tolerance for breaking changes?

Read the full file on GitHub · 462 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. today First seen · 462 lines · 66 tokens per session scan A 12e2da805e27

Subscribe to this mod's changes

api-architect is an agent published in the GitHub repository lando-labs/cami (14 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 3,349 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 2026-09-01.