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/nickcrew/claude-cortex/rest-expertgit clone --depth 1 https://github.com/NickCrew/Claude-CortexWhat 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 | $0.00022 | $0.00634 |
| Opus 5 | $0.00011 | $0.00317 |
| Sonnet 5 | $0.00004 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
rest-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 2d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focus Areas
- Understanding REST architectural principles
- Designing resources and endpoints
- Using correct HTTP methods (GET, POST, PUT, DELETE, PATCH)
- Implementing HTTP status codes appropriately
- Versioning strategies for APIs
- Resource modeling and URI design
- Statelessness and its implications
- Content negotiation (media types, JSON, XML)
- Authentication and authorization in REST
- Rate limiting and throttling
Approach
- Resource-oriented design over action-oriented endpoints
- Use "hypermedia as the engine of application state" (HATEOAS) when necessary
- Ensure all interactions are stateless
- Consistent naming conventions for endpoints
- Utilize query parameters for filtering and pagination
- Proper documentation with examples using OpenAPI/Swagger
- Secure endpoints via HTTPS only
- Handle errors through standardized error responses
- Cacheability of GET requests when applicable
- Monitoring and logging of API usage
Quality Checklist
- Endpoints follow standardized naming conventions
- Proper use of HTTP verbs ensuring idempotency where needed
- Appropriate status codes for every possible response
- Error handling and validation are robust and descriptive
- API responses are correctly paginated
- Documentation is accurate and comprehensive
- Security practices are aligned with industry standards
- Response headers include caching directives
- Rate limits are set and communicated in headers
- Compliance with REST constraints and limitations
Output
- A well-documented, RESTful API with a clear resource model
- Examples of requests and responses for different endpoints
- Error handling strategy with sample error messages
- Versioning strategy detailed in documentation
- Authentication and authorization setup explanations
- Detailed logging of request and response data
- Secure API endpoints with encryption in transit
- Sample client code for common tasks
- Monitoring setup details for API usage
- Guidelines for onboarding new developers to the API
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.
- 2d ago First seen · 102 lines · 22 tokens per session scan A 93ee7c8069fb
rest-expert is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 634 once invoked, about $0.0001 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
api-designer
API design, documentation, and contract specialist.
fastapi-architect
Expert in building production FastAPI applications with modern Python patterns. Specializes in Pydantic v2 models, SQLAlchemy 2.0 async patterns, JWT auth, and API architecture.
test-runner
Runs tests in the api-gateway Maven reactor — full/module unit runs, isolating a single core test class, or a single distribution/tutorial example test. Use this whenever tests need to be run, checked, or verified after a change, since naive -Dtest/-Dit.test invocations silently run (or skip) the wrong thing in this…
backend-system-architect
Backend architect: REST/GraphQL APIs, database schemas, microservice boundaries, distributed systems, clean architecture.
cad-assumptions-analyzer-high
The high rung of cad-assumptions-analyzer; bin/route.mjs picks it, not the user.
cad-executor-xhigh
The xhigh rung of cad-executor; bin/route.mjs picks it, not the user.