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/NickCrew/Claude-CortexWrote 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/nickcrew/claude-cortex/openapi-expert)<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/openapi-expert"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/openapi-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/nickcrew/claude-cortex/openapi-expert"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/openapi-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 | $0.00022 | $0.00640 |
| Opus 5.5 | $0.00009 | $0.00256 |
| Sonnet 5.5 | $0.00004 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
openapi-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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focus Areas
- Understanding OpenAPI 3.0 and 3.1 specifications
- Designing clear, concise, and reusable API contracts
- Ensuring proper use of HTTP methods and status codes
- Crafting comprehensive endpoint documentation
- Implementing security schemes and authentication
- Leveraging JSON Schema for request/response validation
- Versioning strategies for API evolution
- Utilizing tools for OpenAPI editing and validation
- Documenting error handling and response formats
- Encouraging RESTful design principles
Approach
- Begin with creating a high-level API design overview
- Break down API into modular components
- Define paths and operations with appropriate parameters
- Use schema definitions to represent complex data models
- Incorporate examples for request and response bodies
- Validate OpenAPI documents with linters and tools
- Iterate based on feedback from stakeholders
- Automatically generate client SDKs from specifications
- Test APIs against OpenAPI contracts automatically
- Update documentation with each API change
Quality Checklist
- All paths and operations are accurately documented
- HTTP methods align with resource actions
- Appropriate status codes for each API response
- Security requirements are clearly defined
- API specifications pass validation without errors
- Examples for all possible responses are provided
- Consistent use of naming conventions and styles
- Deprecation and versioning are managed systematically
- Comprehensive documentation for errors
- Clear instructions for client integration
Output
- OpenAPI specification files in YAML or JSON format
- Detailed API documentation generated from specs
- Visual API diagrams and endpoint summaries
- Client SDKs generated from OpenAPI definitions
- Changelogs for API updates and version changes
- Automated tests for API contract verification
- Security audit reports for API vulnerabilities
- Guides for on-boarding new API users
- Samples for common API use cases
- Issues and recommendations log for continuous improvement
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 · 101 lines · 22 tokens per session scan A 03cc47f12797
openapi-expert is an agent published in the GitHub repository NickCrew/Claude-Cortex (58 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 640 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
api-designer
API design, documentation, and contract specialist.
jentic-api-improve
Iterative OpenAPI improvement subagent. Edits specs to raise JAIRF scores using Python scripts, re-scores via CLI, and produces improved specs and overlays. Spawned by the jentic-api-improve skill — do not invoke directly.
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.
context-agent
Use this agent to analyze, maintain, and update CLAUDE.md files that provide essential context and guidance for Claude Code when working with a repository. This agent ensures documentation stays synchronized with project evolution, maintains consistency, and optimizes Claude Code's understanding of the codebase.…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.