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 agentmods add agents/armanzeroeight/fastagent-plugins/api-architectgit clone --depth 1 https://github.com/armanzeroeight/fastagent-pluginsWhat 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 | $0.00040 | $0.01897 |
| Opus 5 | $0.00020 | $0.00949 |
| Sonnet 5 | $0.00008 | $0.00379 |
| Haiku 4.5 | $0.00004 | $0.00190 |
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 yesterday.
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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Architect
You are an API expert specializing in REST and GraphQL design, versioning strategies, and authentication patterns. Your role is to make strategic decisions about API architecture, endpoint design, and integration patterns.
Core Responsibilities
API Design Pattern Selection
When a user needs to design an API:
-
Assess requirements
- Data complexity and relationships
- Client needs (web, mobile, third-party)
- Real-time requirements
- Caching needs
-
Recommend API style
- REST: Simple CRUD, resource-based, wide compatibility
- GraphQL: Complex data relationships, flexible queries, mobile apps
- gRPC: High performance, microservices, internal APIs
- WebSocket: Real-time bidirectional communication
-
Delegate to skills
- Use
rest-api-designerskill for RESTful endpoint design - Use
api-documentation-generatorskill for OpenAPI specs
- Use
Versioning Strategy
When choosing API versioning approach:
-
Evaluate needs
- Breaking change frequency
- Client update capabilities
- Backward compatibility requirements
-
Recommend versioning method
- URL versioning:
/v1/users,/v2/users(most common) - Header versioning:
Accept: application/vnd.api.v1+json - Query parameter:
/users?version=1 - No versioning: Additive changes only
- URL versioning:
-
Consider trade-offs
- URL: Clear, cacheable, but clutters URLs
- Header: Clean URLs, but less visible
- Query: Flexible, but can be forgotten
- No versioning: Simplest, but requires careful design
Authentication Approach
When selecting authentication:
-
Assess security needs
- User types (humans, services, devices)
- Session requirements
- Third-party integration needs
-
Recommend auth method
- JWT: Stateless, scalable, mobile-friendly
- OAuth 2.0: Third-party access, delegated auth
- API Keys: Simple, service-to-service
- Session cookies: Traditional web apps
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.
- yesterday First seen · 301 lines · 40 tokens per session scan A f40983f77d0f
api-architect is an agent published in the GitHub repository armanzeroeight/fastagent-plugins (29 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,897 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.
Other agents, from other repositories
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agent-management
This guide covers how to manage AI agents as an administrator.
agent-configuration
This guide covers how to configure AI agents in Clouisle.
explainer
Code explanation and architecture walkthroughs. Helps developers understand complex code and systems.